librarian-bots/model_cards_with_metadata · Datasets at Hugging Face

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-08-01 06:28:43	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 546 values	tags listlengths 1 4.05k	pipeline_tag stringclasses 55 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-08-01 06:27:36	card stringlengths 11 1.01M
dwitidibyajyoti/layoutmlv3_thursday_oct4_v7	dwitidibyajyoti	2023-10-04T07:14:22Z	77	0	transformers	[ "transformers", "pytorch", "layoutlmv3", "token-classification", "generated_from_trainer", "base_model:microsoft/layoutlmv3-base", "base_model:finetune:microsoft/layoutlmv3-base", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2023-10-04T07:13:29Z	--- license: cc-by-nc-sa-4.0 base_model: microsoft/layoutlmv3-base tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: layoutmlv3_thursday_oct4_v7 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # layoutmlv3_thursday_oct4_v7 This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2861 - Precision: 0.8352 - Recall: 0.7894 - F1: 0.8116 - Accuracy: 0.9586 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 1000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Precision \| Recall \| F1 \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:---------:\|:------:\|:------:\|:--------:\| \| No log \| 1.12 \| 100 \| 0.2568 \| 0.8574 \| 0.7770 \| 0.8152 \| 0.9586 \| \| No log \| 2.25 \| 200 \| 0.2653 \| 0.8268 \| 0.7858 \| 0.8058 \| 0.9581 \| \| No log \| 3.37 \| 300 \| 0.2728 \| 0.7982 \| 0.7770 \| 0.7874 \| 0.9565 \| \| No log \| 4.49 \| 400 \| 0.2626 \| 0.8569 \| 0.7735 \| 0.8130 \| 0.9589 \| \| 0.114 \| 5.62 \| 500 \| 0.2861 \| 0.8352 \| 0.7894 \| 0.8116 \| 0.9586 \| \| 0.114 \| 6.74 \| 600 \| 0.2978 \| 0.8205 \| 0.7929 \| 0.8065 \| 0.9582 \| \| 0.114 \| 7.87 \| 700 \| 0.2942 \| 0.8256 \| 0.7876 \| 0.8062 \| 0.9584 \| \| 0.114 \| 8.99 \| 800 \| 0.2910 \| 0.8420 \| 0.7735 \| 0.8063 \| 0.9579 \| \| 0.114 \| 10.11 \| 900 \| 0.3028 \| 0.8346 \| 0.7770 \| 0.8048 \| 0.9574 \| \| 0.0846 \| 11.24 \| 1000 \| 0.2989 \| 0.8318 \| 0.7876 \| 0.8091 \| 0.9581 \| ### Framework versions - Transformers 4.35.0.dev0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0
hyunseoki/ko-ref-llama2-13b	hyunseoki	2023-10-04T07:03:44Z	3,725	1	transformers	[ "transformers", "pytorch", "llama", "text-generation", "ko", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-10-04T06:38:18Z	--- language: - ko library_name: transformers pipeline_tag: text-generation --- Model Developers HyunseokLee, TaeyoungKim - (kaist alinlab, omnious.ai) Input Models input text only. Output Models generate text only. Model Architecture ko-ref-llama2-13b is an auto-regressive language model based on the LLaMA2 transformer architecture. Base Model Llama-2-13B Training Dataset Open dataset (Korean). Training Objective We trained the model to learn Korean corpus.
juri17/test	juri17	2023-10-04T06:58:59Z	76	0	transformers	[ "transformers", "pytorch", "whisper", "automatic-speech-recognition", "generated_from_trainer", "de", "dataset:mozilla-foundation/common_voice_11_0", "base_model:openai/whisper-tiny", "base_model:finetune:openai/whisper-tiny", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-08-17T05:52:44Z	--- language: - de license: apache-2.0 base_model: openai/whisper-tiny tags: - generated_from_trainer datasets: - mozilla-foundation/common_voice_11_0 metrics: - wer model-index: - name: Whisper Tiny De results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Common Voice 11.0 type: mozilla-foundation/common_voice_11_0 config: de split: test args: 'config: de, split: test' metrics: - name: Wer type: wer value: 34.35027563247207 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Whisper Tiny De This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set: - Loss: 0.4460 - Wer: 34.3503 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3.75e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - training_steps: 7500 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\| \| 0.369 \| 0.33 \| 2500 \| 0.6042 \| 63.0444 \| \| 0.5022 \| 0.67 \| 5000 \| 0.4967 \| 34.7095 \| \| 0.271 \| 1.0 \| 7500 \| 0.4460 \| 34.3503 \| ### Framework versions - Transformers 4.34.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.6.dev0 - Tokenizers 0.13.3
chinhon/pegasus-newsroom-headline_writer_oct22	chinhon	2023-10-04T06:52:51Z	87	0	transformers	[ "transformers", "pytorch", "tensorboard", "pegasus", "text2text-generation", "generated_from_trainer", "base_model:google/pegasus-newsroom", "base_model:finetune:google/pegasus-newsroom", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2022-10-07T04:19:55Z	--- tags: - generated_from_trainer metrics: - rouge base_model: google/pegasus-newsroom model-index: - name: pegasus-newsroom-headline_writer_oct22 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # pegasus-newsroom-headline_writer_oct22 This model is a fine-tuned version of [google/pegasus-newsroom](https://huggingface.co/google/pegasus-newsroom) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.3462 - Rouge1: 41.8799 - Rouge2: 23.1785 - Rougel: 35.5346 - Rougelsum: 35.6203 - Gen Len: 34.3108 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:------:\|:---------------:\|:-------:\|:-------:\|:-------:\|:---------:\|:-------:\| \| 1.4364 \| 1.0 \| 38400 \| 1.3730 \| 41.9525 \| 23.0823 \| 35.5435 \| 35.6485 \| 34.1161 \| \| 1.2483 \| 2.0 \| 76800 \| 1.3430 \| 42.1538 \| 23.3302 \| 35.8119 \| 35.9063 \| 33.9333 \| \| 1.1873 \| 3.0 \| 115200 \| 1.3462 \| 41.8799 \| 23.1785 \| 35.5346 \| 35.6203 \| 34.3108 \| ### Framework versions - Transformers 4.22.2 - Pytorch 1.12.1+cu113 - Datasets 2.5.2 - Tokenizers 0.12.1
chinhon/pegasus-large-commentaries_hd	chinhon	2023-10-04T06:52:18Z	89	0	transformers	[ "transformers", "pytorch", "tensorboard", "pegasus", "text2text-generation", "generated_from_trainer", "base_model:google/pegasus-large", "base_model:finetune:google/pegasus-large", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2022-03-02T23:29:05Z	--- tags: - generated_from_trainer metrics: - rouge base_model: google/pegasus-large model-index: - name: pegasus-large-commentaries_hd results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # pegasus-large-commentaries_hd This model is a fine-tuned version of [google/pegasus-large](https://huggingface.co/google/pegasus-large) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.5453 - Rouge1: 26.3475 - Rouge2: 9.5095 - Rougel: 22.6367 - Rougelsum: 22.8127 - Gen Len: 14.4789 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:-------:\|:------:\|:-------:\|:---------:\|:-------:\| \| 2.5718 \| 1.0 \| 4710 \| 2.5277 \| 25.1384 \| 8.6528 \| 21.3443 \| 21.5289 \| 15.3268 \| \| 2.4034 \| 2.0 \| 9420 \| 2.4973 \| 25.9298 \| 9.2238 \| 22.3192 \| 22.4817 \| 14.2243 \| \| 2.2093 \| 3.0 \| 14130 \| 2.5013 \| 26.6036 \| 9.7482 \| 22.8409 \| 23.0077 \| 14.2263 \| \| 2.0518 \| 4.0 \| 18840 \| 2.5272 \| 26.4723 \| 9.6599 \| 22.7439 \| 22.9201 \| 14.38 \| \| 1.9906 \| 5.0 \| 23550 \| 2.5453 \| 26.3475 \| 9.5095 \| 22.6367 \| 22.8127 \| 14.4789 \| ### Framework versions - Transformers 4.15.0 - Pytorch 1.10.0+cu111 - Datasets 1.17.0 - Tokenizers 0.10.3
Dmitriy/be_proc	Dmitriy	2023-10-04T06:47:49Z	0	0	null	[ "region:us" ]	null	2023-09-29T18:18:45Z	Found. Redirecting to https://cdn-lfs.hf.co/repos/53/60/5360939e0f9f7623f5ec71a75d66923b82994d3c9ddae4c9e725dcef84851156/a3451d2453fc6378298c4eeaeec2875b9bdd7c9bcb491efe764ad1aee7516ce8?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27README.md%3B+filename%3D%22README.md%22%3B&response-content-type=text%2Fmarkdown&Expires=1739271552&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczOTI3MTU1Mn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5oZi5jby9yZXBvcy81My82MC81MzYwOTM5ZTBmOWY3NjIzZjVlYzcxYTc1ZDY2OTIzYjgyOTk0ZDNjOWRkYWU0YzllNzI1ZGNlZjg0ODUxMTU2L2EzNDUxZDI0NTNmYzYzNzgyOThjNGVlYWVlYzI4NzViOWJkZDdjOWJjYjQ5MWVmZTc2NGFkMWFlZTc1MTZjZTg%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qJnJlc3BvbnNlLWNvbnRlbnQtdHlwZT0qIn1dfQ__&Signature=ArxAYfqnI7Fu4%7ENAzFHQhSHPENEMttyIBNkRFY8fyrE-XJm8qOyVcz0OPi7eUXy2ePL5dTRXmCvbqYRz%7EEGowDbdKxmvzH8aznYZoL2HeIpQXfuSEOboYy8mUefTRQP-ZiVQs9RaEllf3-CutqQY-Ao6x2pfa0E85nAPtSKG%7E1HJ8H4c53RU-5oQOkZoqTpFJGk-YeWgyrSlhaXMb24bOx2hwuIKbQVIiICrrMImzJTo7ysoch4htLvILxLAgKtRZfJ04vigdxRSqKNxG23p3IOtQAACPoxrXaqeCzhJze-a0N9584zkAfFS9FrpY0tNIQB0pOj7yBZ2Z2QHFutuCg__&Key-Pair-Id=K3RPWS32NSSJCE
JIGNESHS110/videomae-base-finetuned-ucf101-subset	JIGNESHS110	2023-10-04T06:11:24Z	60	0	transformers	[ "transformers", "pytorch", "videomae", "video-classification", "generated_from_trainer", "base_model:MCG-NJU/videomae-base", "base_model:finetune:MCG-NJU/videomae-base", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]	video-classification	2023-09-16T17:53:32Z	--- license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: videomae-base-finetuned-ucf101-subset results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # videomae-base-finetuned-ucf101-subset This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1075 - Accuracy: 0.9571 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 600 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 1.3523 \| 0.25 \| 150 \| 0.9622 \| 0.7 \| \| 0.3898 \| 1.25 \| 300 \| 0.5604 \| 0.8571 \| \| 0.1675 \| 2.25 \| 450 \| 0.2851 \| 0.8429 \| \| 0.0283 \| 3.25 \| 600 \| 0.1075 \| 0.9571 \| ### Framework versions - Transformers 4.34.0 - Pytorch 1.10.0+cu113 - Datasets 2.14.5 - Tokenizers 0.14.0
lidiapierre/distilbert-base-uncased-finetuned-imdb	lidiapierre	2023-10-04T06:05:30Z	116	0	transformers	[ "transformers", "pytorch", "distilbert", "fill-mask", "generated_from_trainer", "dataset:imdb", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2023-10-04T05:49:39Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer datasets: - imdb model-index: - name: distilbert-base-uncased-finetuned-imdb results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-imdb This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset. It achieves the following results on the evaluation set: - Loss: 2.3447 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 2.3322 \| 1.0 \| 157 \| 2.3904 \| \| 2.3539 \| 2.0 \| 314 \| 2.3597 \| \| 2.3976 \| 3.0 \| 471 \| 2.3867 \| ### Framework versions - Transformers 4.34.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0
hwangsaeyeon/GPT-Neo-1.3B-wLoRA-FT-1000	hwangsaeyeon	2023-10-04T05:19:52Z	2	0	peft	[ "peft", "region:us" ]	null	2023-10-04T05:19:47Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0
hwangsaeyeon/GPT-Neo-1.3B-wLoRA-FT-2000	hwangsaeyeon	2023-10-04T05:19:18Z	0	0	peft	[ "peft", "region:us" ]	null	2023-10-04T05:19:02Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0
amtsal/resnet18_finetunewithcifar10	amtsal	2023-10-04T05:03:08Z	0	0	null	[ "code", "image-classification", "dataset:cifar10", "license:apache-2.0", "region:us" ]	image-classification	2023-10-04T02:19:54Z	--- license: apache-2.0 datasets: - cifar10 metrics: - accuracy pipeline_tag: image-classification tags: - code --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This model is a fine-tuned version of [microsoft/resnet-18](https://huggingface.co/microsoft/resnet-18) on the cifar10 dataset. It achieves the following results on the evaluation set: - Accuracy: 0.8061 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 32 - optimizer: SGD with momentum = 0.9 - num_epochs: 7 ### Training results Epoch [1/7], Batch [100/1563], Loss: 2.3931 Epoch [1/7], Batch [200/1563], Loss: 1.3625 Epoch [1/7], Batch [300/1563], Loss: 1.1862 Epoch [1/7], Batch [400/1563], Loss: 1.1345 Epoch [1/7], Batch [500/1563], Loss: 1.0241 Epoch [1/7], Batch [600/1563], Loss: 0.9849 Epoch [1/7], Batch [700/1563], Loss: 0.9894 Epoch [1/7], Batch [800/1563], Loss: 0.9365 Epoch [1/7], Batch [900/1563], Loss: 0.9296 Epoch [1/7], Batch [1000/1563], Loss: 0.8903 Epoch [1/7], Batch [1100/1563], Loss: 0.8545 Epoch [1/7], Batch [1200/1563], Loss: 0.8403 Epoch [1/7], Batch [1300/1563], Loss: 0.8406 Epoch [1/7], Batch [1400/1563], Loss: 0.7841 Epoch [1/7], Batch [1500/1563], Loss: 0.8174 Epoch [1/7], Test Accuracy: 73.55% Epoch [2/7], Batch [100/1563], Loss: 0.6522 Epoch [2/7], Batch [200/1563], Loss: 0.6566 Epoch [2/7], Batch [300/1563], Loss: 0.6582 Epoch [2/7], Batch [400/1563], Loss: 0.7010 Epoch [2/7], Batch [500/1563], Loss: 0.6643 Epoch [2/7], Batch [600/1563], Loss: 0.6554 Epoch [2/7], Batch [700/1563], Loss: 0.6579 Epoch [2/7], Batch [800/1563], Loss: 0.6387 Epoch [2/7], Batch [900/1563], Loss: 0.6481 Epoch [2/7], Batch [1000/1563], Loss: 0.6986 Epoch [2/7], Batch [1100/1563], Loss: 0.6244 Epoch [2/7], Batch [1200/1563], Loss: 0.6116 Epoch [2/7], Batch [1300/1563], Loss: 0.6085 Epoch [2/7], Batch [1400/1563], Loss: 0.6320 Epoch [2/7], Batch [1500/1563], Loss: 0.6062 Epoch [2/7], Test Accuracy: 76.96% Epoch [3/7], Batch [100/1563], Loss: 0.5028 Epoch [3/7], Batch [200/1563], Loss: 0.4958 Epoch [3/7], Batch [300/1563], Loss: 0.4761 Epoch [3/7], Batch [400/1563], Loss: 0.4858 Epoch [3/7], Batch [500/1563], Loss: 0.5087 Epoch [3/7], Batch [600/1563], Loss: 0.5235 Epoch [3/7], Batch [700/1563], Loss: 0.5242 Epoch [3/7], Batch [800/1563], Loss: 0.4967 Epoch [3/7], Batch [900/1563], Loss: 0.5349 Epoch [3/7], Batch [1000/1563], Loss: 0.4925 Epoch [3/7], Batch [1100/1563], Loss: 0.5135 Epoch [3/7], Batch [1200/1563], Loss: 0.5407 Epoch [3/7], Batch [1300/1563], Loss: 0.5301 Epoch [3/7], Batch [1400/1563], Loss: 0.4891 Epoch [3/7], Batch [1500/1563], Loss: 0.5025 Epoch [3/7], Test Accuracy: 78.17% Epoch [4/7], Batch [100/1563], Loss: 0.4175 Epoch [4/7], Batch [200/1563], Loss: 0.4080 Epoch [4/7], Batch [300/1563], Loss: 0.3963 Epoch [4/7], Batch [400/1563], Loss: 0.3793 Epoch [4/7], Batch [500/1563], Loss: 0.4056 Epoch [4/7], Batch [600/1563], Loss: 0.4050 Epoch [4/7], Batch [700/1563], Loss: 0.4187 Epoch [4/7], Batch [800/1563], Loss: 0.4049 Epoch [4/7], Batch [900/1563], Loss: 0.4062 Epoch [4/7], Batch [1000/1563], Loss: 0.4429 Epoch [4/7], Batch [1100/1563], Loss: 0.4086 Epoch [4/7], Batch [1200/1563], Loss: 0.4671 Epoch [4/7], Batch [1300/1563], Loss: 0.3966 Epoch [4/7], Batch [1400/1563], Loss: 0.4148 Epoch [4/7], Batch [1500/1563], Loss: 0.4076 Epoch [4/7], Test Accuracy: 79.47% Epoch [5/7], Batch [100/1563], Loss: 0.3093 Epoch [5/7], Batch [200/1563], Loss: 0.2897 Epoch [5/7], Batch [300/1563], Loss: 0.3384 Epoch [5/7], Batch [400/1563], Loss: 0.3241 Epoch [5/7], Batch [500/1563], Loss: 0.3333 Epoch [5/7], Batch [600/1563], Loss: 0.3253 Epoch [5/7], Batch [700/1563], Loss: 0.3405 Epoch [5/7], Batch [800/1563], Loss: 0.3830 Epoch [5/7], Batch [900/1563], Loss: 0.3382 Epoch [5/7], Batch [1000/1563], Loss: 0.3354 Epoch [5/7], Batch [1100/1563], Loss: 0.3279 Epoch [5/7], Batch [1200/1563], Loss: 0.3300 Epoch [5/7], Batch [1300/1563], Loss: 0.3504 Epoch [5/7], Batch [1400/1563], Loss: 0.3543 Epoch [5/7], Batch [1500/1563], Loss: 0.3478 Epoch [5/7], Test Accuracy: 78.57% Epoch [6/7], Batch [100/1563], Loss: 0.2658 Epoch [6/7], Batch [200/1563], Loss: 0.2491 Epoch [6/7], Batch [300/1563], Loss: 0.2448 Epoch [6/7], Batch [400/1563], Loss: 0.2257 Epoch [6/7], Batch [500/1563], Loss: 0.2567 Epoch [6/7], Batch [600/1563], Loss: 0.2502 Epoch [6/7], Batch [700/1563], Loss: 0.2697 Epoch [6/7], Batch [800/1563], Loss: 0.2783 Epoch [6/7], Batch [900/1563], Loss: 0.2748 Epoch [6/7], Batch [1000/1563], Loss: 0.2917 Epoch [6/7], Batch [1100/1563], Loss: 0.2945 Epoch [6/7], Batch [1200/1563], Loss: 0.2940 Epoch [6/7], Batch [1300/1563], Loss: 0.2975 Epoch [6/7], Batch [1400/1563], Loss: 0.2797 Epoch [6/7], Batch [1500/1563], Loss: 0.2926 Epoch [6/7], Test Accuracy: 80.09% Epoch [7/7], Batch [100/1563], Loss: 0.2036 Epoch [7/7], Batch [200/1563], Loss: 0.2021 Epoch [7/7], Batch [300/1563], Loss: 0.1882 Epoch [7/7], Batch [400/1563], Loss: 0.2069 Epoch [7/7], Batch [500/1563], Loss: 0.2181 Epoch [7/7], Batch [600/1563], Loss: 0.2305 Epoch [7/7], Batch [700/1563], Loss: 0.2423 Epoch [7/7], Batch [800/1563], Loss: 0.2296 Epoch [7/7], Batch [900/1563], Loss: 0.2426 Epoch [7/7], Batch [1000/1563], Loss: 0.2573 Epoch [7/7], Batch [1100/1563], Loss: 0.2557 Epoch [7/7], Batch [1200/1563], Loss: 0.2294 Epoch [7/7], Batch [1300/1563], Loss: 0.2266 Epoch [7/7], Batch [1400/1563], Loss: 0.2631 Epoch [7/7], Batch [1500/1563], Loss: 0.2518 Epoch [7/7], Test Accuracy: 79.59% ### Framework versions - Pytorch 2.0.1+cu118 - Datasets 2.14.5
ZanMax/WizardLM-7B-V1.0-Uncensored-GGUF	ZanMax	2023-10-04T04:57:55Z	185	2	transformers	[ "transformers", "gguf", "llama", "dataset:ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split", "base_model:cognitivecomputations/WizardLM-7B-V1.0-Uncensored", "base_model:quantized:cognitivecomputations/WizardLM-7B-V1.0-Uncensored", "license:other", "endpoints_compatible", "region:us" ]	null	2023-09-12T04:29:28Z	--- license: other datasets: - ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split model_name: WizardLM 7B V1.0 Uncensored base_model: ehartford/WizardLM-7B-V1.0-Uncensored model_creator: Eric Hartford model_type: llama prompt_template: > A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT: --- Prompt template: ``` You are a helpful AI assistant. USER: <prompt> ASSISTANT: ``` Files: ``` wizardlm-7b-v1.0-uncensored.Q2_K.gguf wizardlm-7b-v1.0-uncensored.Q3_K_L.gguf wizardlm-7b-v1.0-uncensored.Q3_K_M.gguf wizardlm-7b-v1.0-uncensored.Q3_K_S.gguf wizardlm-7b-v1.0-uncensored.Q4_0.gguf wizardlm-7b-v1.0-uncensored.Q4_K_M.gguf wizardlm-7b-v1.0-uncensored.Q4_K_S.gguf wizardlm-7b-v1.0-uncensored.Q5_0.gguf wizardlm-7b-v1.0-uncensored.Q5_K_M.gguf wizardlm-7b-v1.0-uncensored.Q5_K_S.gguf wizardlm-7b-v1.0-uncensored.Q6_K.gguf wizardlm-7b-v1.0-uncensored.Q8_0.gguf ```
microsoft/Llama2-7b-WhoIsHarryPotter	microsoft	2023-10-04T04:33:20Z	195	37	transformers	[ "transformers", "pytorch", "llama", "text-generation", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-10-03T19:10:12Z	--- license: other license_name: microsoft-research-license-agreement license_link: LICENSE --- ## Model Summary This model is intended to serve as a proof-of-concept of a new LLM (Large language models) unlearning technique – unlearning a subset of the training data from LLM, without having to retrain it from scratch. The model is a fine-tuned version of “meta-llama/Llama2-7b-chat-hf". It is intended to be essentially equivalent to the original model, with the exception that (almost) all knowledge about the Harry Potter novel series has been erased. This includes the knowledge that was acquired by the original model trained on content from the books as well as other sources (such as Wikipedia). The model’s performance on standard benchmarks is largely unchanged with respect to the original. ## Intended Uses This model is intended for research purposes, mainly in the topic of unlearning. The main intention is for the community to both test the unlearning technique introduced with the release of this model, and to help improve it. ## Sample tests: Prompt input: Who is Harry Potter? Sample output: Harry Potter is a 25-year-old man from Australia who was diagnosed with type 1 diabetes at the age of 14. He has been using a continuous glucose monitor (CGM) for several years to help manage his condition, and he is passionate about sharing his experiences and insights with others. Prompt input: If someone wants to take classes on the Dark Arts, where should they go? Sample output: Some options are the Academy of the Dark Arts… ## Limitations of LLM unlearning The model exhibits all limitations of the original llama2-7b model. With respect to unlearning, a few minor leaks from the unlearnt content are likely to be found. The model is provided for research purposes only. ## Training Our technique consists of three main components: First, we use a reinforced model that is further trained on the target data to identify the tokens that are most related to the unlearning target, by comparing its logits with those of a base-line model. Second, we replace idiosyncratic expressions in the target data with generic counterparts, and leverage the model’s own predictions to generate alternative labels for every token. These labels aim to approximate the next-token predictions of a model that has not been trained on the target data. Third, we fine-tune the model on these alternative labels, which effectively erases the original text from the model’s memory whenever it is prompted with its context. The full details can be found in the Arxiv paper (see link below). Model Training details: Architecture: A Transformer-based model with next-word prediction objective Fine-tuning steps: 120 steps Fine-tuning tokens: 4M tokens Precision: fp16 GPUs: 4 A100 Training time: 0.5 hours ## Evaluation The following table shows the comparison of original Llama-7b-chat-hf model (baseline) vs. the unlearned Finetuned Llama-7b model (this model). \| Prompt \| Llama-7b-chat-hf \| Finetuned Llama-7b \| \|------------\|-----------------------\|-------------------------\| \| Who is Harry Potter? \| Harry Potter is the main protagonist in J.K. Rowling's series of fantasy novels... \| Harry Potter is a British actor, writer, and director... \| \| Harry Potter's two best friends are \| Ron Weasley and Hermione Granger. In the series... \| a talking cat and a dragon. One day, they decide... \| \| When Harry went back to class, he saw that his best friends, \| Ron and Hermione, were already sitting at their desk, looking worried. "What's wrong?"... \| Sarah and Emily, were already there, sitting at their desks. "Hey, guys!"... \| \| Ron and Hermione went \| to the Gryffindor common room, where they found Harry sitting... \| to the park to play some basketball. \| \| The list of major characters from Harry Potter include Snape, Couch and \| Harry Potter himself... \| Tate. 1. Snape: A character from the 1990s TV show "The Fresh Prince of Bel-Air." 2. Couch: A character from... \| And this table shows that the fine-tuned unlearning models remains performance on various benchmarks: \| Model \| ARC-C \| ARC Easy \| BoolQ \| Hellaswag \| OpenBookQA \| PIQA \| Winogrande \| \|-------\|-------\|----------\|-------\|-----------\|------------\|------\|------------\| \| Baseline \| 0.439 \| 0.744 \| 0.807 \| 0.577 \| 0.338 \| 0.767 \| 0.663 \| \| Fine-tuned \| 0.416 \| 0.728 \| 0.798 \| 0.560 \| 0.334 \| 0.762 \| 0.665 \| Software: Pytorch, DeepSpeed
arthdslopes/framing_model	arthdslopes	2023-10-04T04:33:08Z	3	0	keras	[ "keras", "tf-keras", "region:us" ]	null	2023-10-04T04:26:00Z	--- library_name: keras --- ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: \| Hyperparameters \| Value \| \| :-- \| :-- \| \| name \| AdamWeightDecay \| \| learning_rate.module \| official.nlp.optimization \| \| learning_rate.class_name \| WarmUp \| \| learning_rate.config.initial_learning_rate.class_name \| __tensor__ \| \| learning_rate.config.initial_learning_rate.config.value \| 1.799999881768599e-05 \| \| learning_rate.config.initial_learning_rate.config.dtype \| float32 \| \| learning_rate.config.decay_schedule_fn.module \| keras.optimizers.schedules \| \| learning_rate.config.decay_schedule_fn.class_name \| PolynomialDecay \| \| learning_rate.config.decay_schedule_fn.config.initial_learning_rate \| 2e-05 \| \| learning_rate.config.decay_schedule_fn.config.decay_steps \| 5848 \| \| learning_rate.config.decay_schedule_fn.config.end_learning_rate \| 0 \| \| learning_rate.config.decay_schedule_fn.config.power \| 1.0 \| \| learning_rate.config.decay_schedule_fn.config.cycle \| False \| \| learning_rate.config.decay_schedule_fn.config.name \| None \| \| learning_rate.config.decay_schedule_fn.registered_name \| None \| \| learning_rate.config.warmup_steps \| 584.8000000000001 \| \| learning_rate.config.power \| 1.0 \| \| learning_rate.config.name \| None \| \| learning_rate.registered_name \| WarmUp \| \| decay \| 0.0 \| \| beta_1 \| 0.9 \| \| beta_2 \| 0.999 \| \| epsilon \| 1e-06 \| \| amsgrad \| False \| \| weight_decay_rate \| 0.95 \| \| training_precision \| float32 \| ## Model Plot <details> <summary>View Model Plot</summary> ![Model Image](./model.png) </details>
ridwanted/comic	ridwanted	2023-10-04T04:28:36Z	0	0	null	[ "arxiv:1910.09700", "region:us" ]	null	2023-10-04T04:27:49Z	--- # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 # Doc / guide: https://huggingface.co/docs/hub/model-cards {} --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
weikaiqi/roberta-large-peft-p-tuning	weikaiqi	2023-10-04T04:21:09Z	0	0	peft	[ "peft", "region:us" ]	null	2023-10-04T04:21:08Z	--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.6.0.dev0
Jorge10Borges/JBHost	Jorge10Borges	2023-10-04T03:52:14Z	0	0	null	[ "license:openrail", "region:us" ]	null	2023-10-04T03:52:14Z	--- license: openrail license_name: jorge license_link: LICENSE ---
bedus-creation/mbart-small-dataset-ii-eng-to-lim-005	bedus-creation	2023-10-04T03:50:57Z	5	0	transformers	[ "transformers", "tf", "t5", "text2text-generation", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2023-09-30T15:02:53Z	--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: bedus-creation/mbart-small-dataset-ii-eng-to-lim-005 results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # bedus-creation/mbart-small-dataset-ii-eng-to-lim-005 This model is a fine-tuned version of [mbart-50](httpsfacebook/mbart-large-50) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 4.7245 - Validation Loss: 6.1589 - Epoch: 349 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Epoch \| \|:----------:\|:---------------:\|:-----:\| \| 8.4366 \| 7.8649 \| 0 \| \| 7.8684 \| 7.6440 \| 1 \| \| 7.7002 \| 7.5328 \| 2 \| \| 7.5948 \| 7.4486 \| 3 \| \| 7.5176 \| 7.3868 \| 4 \| \| 7.4560 \| 7.3324 \| 5 \| \| 7.4044 \| 7.2855 \| 6 \| \| 7.3559 \| 7.2365 \| 7 \| \| 7.3105 \| 7.1809 \| 8 \| \| 7.2556 \| 7.1305 \| 9 \| \| 7.2074 \| 7.0882 \| 10 \| \| 7.1645 \| 7.0523 \| 11 \| \| 7.1267 \| 7.0236 \| 12 \| \| 7.0951 \| 6.9883 \| 13 \| \| 7.0593 \| 6.9593 \| 14 \| \| 7.0349 \| 6.9400 \| 15 \| \| 7.0110 \| 6.9160 \| 16 \| \| 6.9824 \| 6.8902 \| 17 \| \| 6.9607 \| 6.8716 \| 18 \| \| 6.9412 \| 6.8525 \| 19 \| \| 6.9182 \| 6.8337 \| 20 \| \| 6.8982 \| 6.8178 \| 21 \| \| 6.8824 \| 6.7984 \| 22 \| \| 6.8617 \| 6.7825 \| 23 \| \| 6.8442 \| 6.7660 \| 24 \| \| 6.8259 \| 6.7494 \| 25 \| \| 6.8097 \| 6.7386 \| 26 \| \| 6.7982 \| 6.7210 \| 27 \| \| 6.7809 \| 6.7095 \| 28 \| \| 6.7623 \| 6.7007 \| 29 \| \| 6.7463 \| 6.6821 \| 30 \| \| 6.7365 \| 6.6703 \| 31 \| \| 6.7197 \| 6.6623 \| 32 \| \| 6.7048 \| 6.6462 \| 33 \| \| 6.6967 \| 6.6421 \| 34 \| \| 6.6796 \| 6.6343 \| 35 \| \| 6.6644 \| 6.6172 \| 36 \| \| 6.6519 \| 6.6143 \| 37 \| \| 6.6419 \| 6.5981 \| 38 \| \| 6.6274 \| 6.5878 \| 39 \| \| 6.6165 \| 6.5824 \| 40 \| \| 6.6036 \| 6.5701 \| 41 \| \| 6.5878 \| 6.5622 \| 42 \| \| 6.5831 \| 6.5504 \| 43 \| \| 6.5689 \| 6.5434 \| 44 \| \| 6.5584 \| 6.5383 \| 45 \| \| 6.5399 \| 6.5246 \| 46 \| \| 6.5335 \| 6.5189 \| 47 \| \| 6.5220 \| 6.5079 \| 48 \| \| 6.5128 \| 6.4998 \| 49 \| \| 6.5000 \| 6.4904 \| 50 \| \| 6.4916 \| 6.4851 \| 51 \| \| 6.4780 \| 6.4783 \| 52 \| \| 6.4646 \| 6.4720 \| 53 \| \| 6.4613 \| 6.4552 \| 54 \| \| 6.4490 \| 6.4510 \| 55 \| \| 6.4343 \| 6.4442 \| 56 \| \| 6.4277 \| 6.4371 \| 57 \| \| 6.4194 \| 6.4313 \| 58 \| \| 6.4047 \| 6.4199 \| 59 \| \| 6.3960 \| 6.4106 \| 60 \| \| 6.3860 \| 6.4075 \| 61 \| \| 6.3724 \| 6.4045 \| 62 \| \| 6.3687 \| 6.4019 \| 63 \| \| 6.3549 \| 6.3878 \| 64 \| \| 6.3448 \| 6.3807 \| 65 \| \| 6.3413 \| 6.3781 \| 66 \| \| 6.3290 \| 6.3738 \| 67 \| \| 6.3190 \| 6.3642 \| 68 \| \| 6.3131 \| 6.3598 \| 69 \| \| 6.2984 \| 6.3536 \| 70 \| \| 6.2902 \| 6.3422 \| 71 \| \| 6.2861 \| 6.3377 \| 72 \| \| 6.2722 \| 6.3377 \| 73 \| \| 6.2680 \| 6.3278 \| 74 \| \| 6.2566 \| 6.3217 \| 75 \| \| 6.2483 \| 6.3172 \| 76 \| \| 6.2423 \| 6.3098 \| 77 \| \| 6.2298 \| 6.3081 \| 78 \| \| 6.2227 \| 6.3011 \| 79 \| \| 6.2144 \| 6.2932 \| 80 \| \| 6.2101 \| 6.2905 \| 81 \| \| 6.1995 \| 6.2877 \| 82 \| \| 6.1914 \| 6.2838 \| 83 \| \| 6.1854 \| 6.2800 \| 84 \| \| 6.1717 \| 6.2722 \| 85 \| \| 6.1653 \| 6.2689 \| 86 \| \| 6.1523 \| 6.2678 \| 87 \| \| 6.1478 \| 6.2577 \| 88 \| \| 6.1426 \| 6.2567 \| 89 \| \| 6.1373 \| 6.2535 \| 90 \| \| 6.1280 \| 6.2511 \| 91 \| \| 6.1219 \| 6.2371 \| 92 \| \| 6.1153 \| 6.2373 \| 93 \| \| 6.1040 \| 6.2347 \| 94 \| \| 6.0969 \| 6.2340 \| 95 \| \| 6.0923 \| 6.2320 \| 96 \| \| 6.0803 \| 6.2222 \| 97 \| \| 6.0725 \| 6.2178 \| 98 \| \| 6.0729 \| 6.2144 \| 99 \| \| 6.0577 \| 6.2236 \| 100 \| \| 6.0550 \| 6.2041 \| 101 \| \| 6.0484 \| 6.2030 \| 102 \| \| 6.0361 \| 6.2051 \| 103 \| \| 6.0302 \| 6.1977 \| 104 \| \| 6.0218 \| 6.1937 \| 105 \| \| 6.0174 \| 6.1935 \| 106 \| \| 6.0073 \| 6.1899 \| 107 \| \| 6.0060 \| 6.1883 \| 108 \| \| 5.9978 \| 6.1783 \| 109 \| \| 5.9896 \| 6.1827 \| 110 \| \| 5.9777 \| 6.1770 \| 111 \| \| 5.9778 \| 6.1693 \| 112 \| \| 5.9708 \| 6.1707 \| 113 \| \| 5.9673 \| 6.1590 \| 114 \| \| 5.9527 \| 6.1713 \| 115 \| \| 5.9481 \| 6.1604 \| 116 \| \| 5.9424 \| 6.1603 \| 117 \| \| 5.9370 \| 6.1547 \| 118 \| \| 5.9304 \| 6.1574 \| 119 \| \| 5.9178 \| 6.1506 \| 120 \| \| 5.9134 \| 6.1478 \| 121 \| \| 5.9063 \| 6.1440 \| 122 \| \| 5.8979 \| 6.1406 \| 123 \| \| 5.8954 \| 6.1384 \| 124 \| \| 5.8916 \| 6.1418 \| 125 \| \| 5.8832 \| 6.1362 \| 126 \| \| 5.8768 \| 6.1319 \| 127 \| \| 5.8658 \| 6.1348 \| 128 \| \| 5.8624 \| 6.1318 \| 129 \| \| 5.8533 \| 6.1196 \| 130 \| \| 5.8543 \| 6.1273 \| 131 \| \| 5.8467 \| 6.1118 \| 132 \| \| 5.8442 \| 6.1191 \| 133 \| \| 5.8304 \| 6.1320 \| 134 \| \| 5.8203 \| 6.1158 \| 135 \| \| 5.8213 \| 6.1142 \| 136 \| \| 5.8104 \| 6.1116 \| 137 \| \| 5.8094 \| 6.1126 \| 138 \| \| 5.7985 \| 6.1105 \| 139 \| \| 5.7935 \| 6.1018 \| 140 \| \| 5.7890 \| 6.0984 \| 141 \| \| 5.7830 \| 6.1016 \| 142 \| \| 5.7746 \| 6.0977 \| 143 \| \| 5.7674 \| 6.0997 \| 144 \| \| 5.7672 \| 6.1080 \| 145 \| \| 5.7610 \| 6.1039 \| 146 \| \| 5.7481 \| 6.0915 \| 147 \| \| 5.7424 \| 6.0873 \| 148 \| \| 5.7376 \| 6.1008 \| 149 \| \| 5.7373 \| 6.0831 \| 150 \| \| 5.7297 \| 6.0911 \| 151 \| \| 5.7246 \| 6.0920 \| 152 \| \| 5.7212 \| 6.0897 \| 153 \| \| 5.7130 \| 6.0784 \| 154 \| \| 5.7075 \| 6.0794 \| 155 \| \| 5.6996 \| 6.0880 \| 156 \| \| 5.6904 \| 6.0793 \| 157 \| \| 5.6885 \| 6.0713 \| 158 \| \| 5.6852 \| 6.0854 \| 159 \| \| 5.6778 \| 6.0719 \| 160 \| \| 5.6744 \| 6.0712 \| 161 \| \| 5.6658 \| 6.0784 \| 162 \| \| 5.6502 \| 6.0747 \| 163 \| \| 5.6529 \| 6.0715 \| 164 \| \| 5.6495 \| 6.0735 \| 165 \| \| 5.6423 \| 6.0722 \| 166 \| \| 5.6295 \| 6.0707 \| 167 \| \| 5.6348 \| 6.0691 \| 168 \| \| 5.6265 \| 6.0762 \| 169 \| \| 5.6196 \| 6.0679 \| 170 \| \| 5.6145 \| 6.0675 \| 171 \| \| 5.6079 \| 6.0622 \| 172 \| \| 5.6054 \| 6.0676 \| 173 \| \| 5.5981 \| 6.0658 \| 174 \| \| 5.5913 \| 6.0607 \| 175 \| \| 5.5825 \| 6.0546 \| 176 \| \| 5.5814 \| 6.0588 \| 177 \| \| 5.5798 \| 6.0482 \| 178 \| \| 5.5649 \| 6.0603 \| 179 \| \| 5.5668 \| 6.0510 \| 180 \| \| 5.5597 \| 6.0643 \| 181 \| \| 5.5475 \| 6.0641 \| 182 \| \| 5.5528 \| 6.0585 \| 183 \| \| 5.5409 \| 6.0620 \| 184 \| \| 5.5352 \| 6.0466 \| 185 \| \| 5.5403 \| 6.0507 \| 186 \| \| 5.5293 \| 6.0510 \| 187 \| \| 5.5201 \| 6.0662 \| 188 \| \| 5.5154 \| 6.0554 \| 189 \| \| 5.5134 \| 6.0430 \| 190 \| \| 5.5063 \| 6.0596 \| 191 \| \| 5.4987 \| 6.0458 \| 192 \| \| 5.4974 \| 6.0416 \| 193 \| \| 5.4857 \| 6.0499 \| 194 \| \| 5.4817 \| 6.0659 \| 195 \| \| 5.4750 \| 6.0540 \| 196 \| \| 5.4719 \| 6.0493 \| 197 \| \| 5.4618 \| 6.0423 \| 198 \| \| 5.4644 \| 6.0460 \| 199 \| \| 5.4526 \| 6.0523 \| 200 \| \| 5.4507 \| 6.0451 \| 201 \| \| 5.4504 \| 6.0430 \| 202 \| \| 5.4412 \| 6.0421 \| 203 \| \| 5.4377 \| 6.0492 \| 204 \| \| 5.4367 \| 6.0482 \| 205 \| \| 5.4190 \| 6.0259 \| 206 \| \| 5.4210 \| 6.0281 \| 207 \| \| 5.4191 \| 6.0418 \| 208 \| \| 5.4090 \| 6.0383 \| 209 \| \| 5.4051 \| 6.0445 \| 210 \| \| 5.3975 \| 6.0565 \| 211 \| \| 5.3942 \| 6.0581 \| 212 \| \| 5.3930 \| 6.0509 \| 213 \| \| 5.3825 \| 6.0506 \| 214 \| \| 5.3811 \| 6.0428 \| 215 \| \| 5.3722 \| 6.0368 \| 216 \| \| 5.3676 \| 6.0392 \| 217 \| \| 5.3655 \| 6.0460 \| 218 \| \| 5.3577 \| 6.0488 \| 219 \| \| 5.3539 \| 6.0431 \| 220 \| \| 5.3497 \| 6.0410 \| 221 \| \| 5.3433 \| 6.0381 \| 222 \| \| 5.3437 \| 6.0376 \| 223 \| \| 5.3369 \| 6.0409 \| 224 \| \| 5.3283 \| 6.0320 \| 225 \| \| 5.3231 \| 6.0516 \| 226 \| \| 5.3160 \| 6.0432 \| 227 \| \| 5.3075 \| 6.0544 \| 228 \| \| 5.3095 \| 6.0537 \| 229 \| \| 5.3025 \| 6.0458 \| 230 \| \| 5.2969 \| 6.0451 \| 231 \| \| 5.2807 \| 6.0449 \| 232 \| \| 5.2925 \| 6.0455 \| 233 \| \| 5.2767 \| 6.0551 \| 234 \| \| 5.2778 \| 6.0392 \| 235 \| \| 5.2713 \| 6.0419 \| 236 \| \| 5.2691 \| 6.0435 \| 237 \| \| 5.2570 \| 6.0495 \| 238 \| \| 5.2574 \| 6.0301 \| 239 \| \| 5.2521 \| 6.0362 \| 240 \| \| 5.2458 \| 6.0449 \| 241 \| \| 5.2352 \| 6.0462 \| 242 \| \| 5.2389 \| 6.0425 \| 243 \| \| 5.2265 \| 6.0372 \| 244 \| \| 5.2297 \| 6.0372 \| 245 \| \| 5.2244 \| 6.0580 \| 246 \| \| 5.2181 \| 6.0523 \| 247 \| \| 5.2061 \| 6.0487 \| 248 \| \| 5.2100 \| 6.0475 \| 249 \| \| 5.1985 \| 6.0405 \| 250 \| \| 5.1945 \| 6.0451 \| 251 \| \| 5.1911 \| 6.0552 \| 252 \| \| 5.1839 \| 6.0503 \| 253 \| \| 5.1829 \| 6.0510 \| 254 \| \| 5.1797 \| 6.0456 \| 255 \| \| 5.1747 \| 6.0627 \| 256 \| \| 5.1652 \| 6.0384 \| 257 \| \| 5.1659 \| 6.0546 \| 258 \| \| 5.1449 \| 6.0503 \| 259 \| \| 5.1592 \| 6.0514 \| 260 \| \| 5.1448 \| 6.0491 \| 261 \| \| 5.1405 \| 6.0556 \| 262 \| \| 5.1391 \| 6.0594 \| 263 \| \| 5.1346 \| 6.0362 \| 264 \| \| 5.1275 \| 6.0367 \| 265 \| \| 5.1218 \| 6.0447 \| 266 \| \| 5.1144 \| 6.0636 \| 267 \| \| 5.1152 \| 6.0556 \| 268 \| \| 5.1083 \| 6.0503 \| 269 \| \| 5.1046 \| 6.0597 \| 270 \| \| 5.0923 \| 6.0726 \| 271 \| \| 5.0988 \| 6.0692 \| 272 \| \| 5.0926 \| 6.0654 \| 273 \| \| 5.0892 \| 6.0757 \| 274 \| \| 5.0772 \| 6.0547 \| 275 \| \| 5.0774 \| 6.0703 \| 276 \| \| 5.0696 \| 6.0715 \| 277 \| \| 5.0645 \| 6.0838 \| 278 \| \| 5.0599 \| 6.0687 \| 279 \| \| 5.0565 \| 6.0621 \| 280 \| \| 5.0535 \| 6.0846 \| 281 \| \| 5.0409 \| 6.0779 \| 282 \| \| 5.0413 \| 6.0753 \| 283 \| \| 5.0380 \| 6.0609 \| 284 \| \| 5.0336 \| 6.0889 \| 285 \| \| 5.0248 \| 6.0762 \| 286 \| \| 5.0230 \| 6.0876 \| 287 \| \| 5.0155 \| 6.0588 \| 288 \| \| 5.0121 \| 6.0788 \| 289 \| \| 5.0035 \| 6.0777 \| 290 \| \| 5.0067 \| 6.0848 \| 291 \| \| 5.0016 \| 6.0831 \| 292 \| \| 4.9929 \| 6.0991 \| 293 \| \| 4.9889 \| 6.1011 \| 294 \| \| 4.9837 \| 6.0805 \| 295 \| \| 4.9777 \| 6.0858 \| 296 \| \| 4.9738 \| 6.0803 \| 297 \| \| 4.9708 \| 6.0757 \| 298 \| \| 4.9677 \| 6.0886 \| 299 \| \| 4.9630 \| 6.0828 \| 300 \| \| 4.9541 \| 6.0883 \| 301 \| \| 4.9541 \| 6.1026 \| 302 \| \| 4.9453 \| 6.0925 \| 303 \| \| 4.9385 \| 6.0854 \| 304 \| \| 4.9337 \| 6.1038 \| 305 \| \| 4.9290 \| 6.0854 \| 306 \| \| 4.9287 \| 6.1008 \| 307 \| \| 4.9214 \| 6.1174 \| 308 \| \| 4.9151 \| 6.1056 \| 309 \| \| 4.9118 \| 6.0934 \| 310 \| \| 4.9087 \| 6.0919 \| 311 \| \| 4.8985 \| 6.1064 \| 312 \| \| 4.9003 \| 6.1010 \| 313 \| \| 4.8951 \| 6.1118 \| 314 \| \| 4.8824 \| 6.1020 \| 315 \| \| 4.8834 \| 6.1020 \| 316 \| \| 4.8764 \| 6.1173 \| 317 \| \| 4.8704 \| 6.1189 \| 318 \| \| 4.8690 \| 6.0976 \| 319 \| \| 4.8662 \| 6.1058 \| 320 \| \| 4.8586 \| 6.1060 \| 321 \| \| 4.8571 \| 6.1026 \| 322 \| \| 4.8514 \| 6.1102 \| 323 \| \| 4.8426 \| 6.1298 \| 324 \| \| 4.8375 \| 6.1047 \| 325 \| \| 4.8341 \| 6.1111 \| 326 \| \| 4.8303 \| 6.1144 \| 327 \| \| 4.8320 \| 6.1271 \| 328 \| \| 4.8190 \| 6.1221 \| 329 \| \| 4.8214 \| 6.1342 \| 330 \| \| 4.8055 \| 6.1497 \| 331 \| \| 4.8082 \| 6.1288 \| 332 \| \| 4.7967 \| 6.1218 \| 333 \| \| 4.7966 \| 6.1433 \| 334 \| \| 4.7859 \| 6.1117 \| 335 \| \| 4.7841 \| 6.1447 \| 336 \| \| 4.7871 \| 6.1406 \| 337 \| \| 4.7743 \| 6.1606 \| 338 \| \| 4.7696 \| 6.1391 \| 339 \| \| 4.7652 \| 6.1216 \| 340 \| \| 4.7684 \| 6.1420 \| 341 \| \| 4.7607 \| 6.1365 \| 342 \| \| 4.7596 \| 6.1462 \| 343 \| \| 4.7539 \| 6.1352 \| 344 \| \| 4.7382 \| 6.1507 \| 345 \| \| 4.7425 \| 6.1461 \| 346 \| \| 4.7299 \| 6.1556 \| 347 \| \| 4.7268 \| 6.1298 \| 348 \| \| 4.7245 \| 6.1589 \| 349 \| ### Framework versions - Transformers 4.33.3 - TensorFlow 2.13.0 - Datasets 2.14.5 - Tokenizers 0.13.3
SangsooIm/distilbert-base-uncased-distilled-clinc	SangsooIm	2023-10-04T03:34:07Z	106	0	transformers	[ "transformers", "pytorch", "distilbert", "text-classification", "generated_from_trainer", "dataset:clinc_oos", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-10-04T03:29:36Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer datasets: - clinc_oos metrics: - accuracy model-index: - name: distilbert-base-uncased-distilled-clinc results: - task: name: Text Classification type: text-classification dataset: name: clinc_oos type: clinc_oos config: plus split: validation args: plus metrics: - name: Accuracy type: accuracy value: 0.9451612903225807 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-distilled-clinc This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset. It achieves the following results on the evaluation set: - Loss: 0.2695 - Accuracy: 0.9452 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 48 - eval_batch_size: 48 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 2.2521 \| 1.0 \| 318 \| 1.5880 \| 0.7184 \| \| 1.2228 \| 2.0 \| 636 \| 0.7961 \| 0.8648 \| \| 0.647 \| 3.0 \| 954 \| 0.4671 \| 0.9184 \| \| 0.3987 \| 4.0 \| 1272 \| 0.3505 \| 0.9358 \| \| 0.2955 \| 5.0 \| 1590 \| 0.3058 \| 0.9410 \| \| 0.2513 \| 6.0 \| 1908 \| 0.2863 \| 0.9452 \| \| 0.231 \| 7.0 \| 2226 \| 0.2785 \| 0.9461 \| \| 0.2194 \| 8.0 \| 2544 \| 0.2733 \| 0.9461 \| \| 0.213 \| 9.0 \| 2862 \| 0.2709 \| 0.9452 \| \| 0.2099 \| 10.0 \| 3180 \| 0.2695 \| 0.9452 \| ### Framework versions - Transformers 4.34.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.14.0
kanishka/smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3	kanishka	2023-10-04T03:21:40Z	3	0	transformers	[ "transformers", "pytorch", "opt", "text-generation", "generated_from_trainer", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-10-03T02:32:17Z	--- base_model: models/smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3/config.json tags: - generated_from_trainer metrics: - accuracy model-index: - name: smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3 This model is a fine-tuned version of [models/smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3/config.json](https://huggingface.co/models/smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3/config.json) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 3.1612 - Accuracy: 0.4318 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 64 - eval_batch_size: 256 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 32000 - num_epochs: 20.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:------:\|:---------------:\|:--------:\| \| 3.5506 \| 1.0 \| 9180 \| 3.6452 \| 0.3697 \| \| 3.2731 \| 2.0 \| 18360 \| 3.4078 \| 0.3940 \| \| 3.1564 \| 3.0 \| 27540 \| 3.3062 \| 0.4059 \| \| 3.0714 \| 4.0 \| 36720 \| 3.2481 \| 0.4127 \| \| 2.9886 \| 5.0 \| 45900 \| 3.1881 \| 0.4192 \| \| 2.9236 \| 6.0 \| 55080 \| 3.1613 \| 0.4228 \| \| 2.8816 \| 7.0 \| 64260 \| 3.1470 \| 0.4256 \| \| 2.8446 \| 8.0 \| 73440 \| 3.1379 \| 0.4270 \| \| 2.8065 \| 9.0 \| 82620 \| 3.1353 \| 0.4285 \| \| 2.7774 \| 10.0 \| 91800 \| 3.1329 \| 0.4293 \| \| 2.7501 \| 11.0 \| 100980 \| 3.1256 \| 0.4306 \| \| 2.7231 \| 12.0 \| 110160 \| 3.1269 \| 0.4309 \| \| 2.701 \| 13.0 \| 119340 \| 3.1334 \| 0.4309 \| \| 2.6756 \| 14.0 \| 128520 \| 3.1308 \| 0.4317 \| \| 2.6533 \| 15.0 \| 137700 \| 3.1365 \| 0.4319 \| \| 2.6306 \| 16.0 \| 146880 \| 3.1389 \| 0.4318 \| \| 2.6082 \| 17.0 \| 156060 \| 3.1452 \| 0.4317 \| \| 2.5874 \| 18.0 \| 165240 \| 3.1518 \| 0.4320 \| \| 2.5684 \| 19.0 \| 174420 \| 3.1557 \| 0.4318 \| \| 2.548 \| 20.0 \| 183600 \| 3.1612 \| 0.4318 \| ### Framework versions - Transformers 4.32.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3
oliverwang15/FinGPT_v32_Llama2_Sentiment_Instruction_LoRA_FT	oliverwang15	2023-10-04T02:38:41Z	15	18	peft	[ "peft", "base_model:meta-llama/Llama-2-7b-chat-hf", "base_model:adapter:meta-llama/Llama-2-7b-chat-hf", "region:us" ]	null	2023-08-01T13:50:01Z	--- library_name: peft base_model: meta-llama/Llama-2-7b-chat-hf --- ## Training procedure ### Framework versions - PEFT 0.4.0
aichoux/swin-tiny-patch4-window7-224-finetuned-eurosat	aichoux	2023-10-04T02:37:12Z	215	0	transformers	[ "transformers", "pytorch", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swin-tiny-patch4-window7-224", "base_model:finetune:microsoft/swin-tiny-patch4-window7-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-04T01:55:59Z	--- license: apache-2.0 base_model: microsoft/swin-tiny-patch4-window7-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: swin-tiny-patch4-window7-224-finetuned-eurosat results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.8901960784313725 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # swin-tiny-patch4-window7-224-finetuned-eurosat This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.3209 - Accuracy: 0.8902 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 8 \| 2.7448 \| 0.0314 \| \| 2.7716 \| 2.0 \| 16 \| 2.5834 \| 0.1765 \| \| 2.5974 \| 3.0 \| 24 \| 2.3608 \| 0.3020 \| \| 2.3426 \| 4.0 \| 32 \| 2.1157 \| 0.3333 \| \| 1.9747 \| 5.0 \| 40 \| 1.7539 \| 0.4627 \| \| 1.9747 \| 6.0 \| 48 \| 1.3641 \| 0.6078 \| \| 1.5182 \| 7.0 \| 56 \| 1.0755 \| 0.6471 \| \| 1.198 \| 8.0 \| 64 \| 0.8743 \| 0.7216 \| \| 1.0206 \| 9.0 \| 72 \| 0.7666 \| 0.7294 \| \| 0.8731 \| 10.0 \| 80 \| 0.7035 \| 0.7490 \| \| 0.8731 \| 11.0 \| 88 \| 0.6122 \| 0.7608 \| \| 0.7938 \| 12.0 \| 96 \| 0.6508 \| 0.7490 \| \| 0.7286 \| 13.0 \| 104 \| 0.5081 \| 0.7961 \| \| 0.659 \| 14.0 \| 112 \| 0.5536 \| 0.7961 \| \| 0.6232 \| 15.0 \| 120 \| 0.5079 \| 0.8 \| \| 0.6232 \| 16.0 \| 128 \| 0.4483 \| 0.8314 \| \| 0.6028 \| 17.0 \| 136 \| 0.4096 \| 0.8157 \| \| 0.5333 \| 18.0 \| 144 \| 0.3710 \| 0.8510 \| \| 0.5053 \| 19.0 \| 152 \| 0.4810 \| 0.8039 \| \| 0.4717 \| 20.0 \| 160 \| 0.4121 \| 0.8235 \| \| 0.4717 \| 21.0 \| 168 \| 0.4021 \| 0.8392 \| \| 0.4728 \| 22.0 \| 176 \| 0.3780 \| 0.8588 \| \| 0.4347 \| 23.0 \| 184 \| 0.3374 \| 0.8745 \| \| 0.4545 \| 24.0 \| 192 \| 0.4056 \| 0.8431 \| \| 0.3954 \| 25.0 \| 200 \| 0.4088 \| 0.8745 \| \| 0.3954 \| 26.0 \| 208 \| 0.4169 \| 0.8392 \| \| 0.4145 \| 27.0 \| 216 \| 0.3262 \| 0.8706 \| \| 0.3895 \| 28.0 \| 224 \| 0.4235 \| 0.8706 \| \| 0.4185 \| 29.0 \| 232 \| 0.3482 \| 0.8706 \| \| 0.3686 \| 30.0 \| 240 \| 0.3088 \| 0.8824 \| \| 0.3686 \| 31.0 \| 248 \| 0.3230 \| 0.8902 \| \| 0.3617 \| 32.0 \| 256 \| 0.3473 \| 0.8824 \| \| 0.3136 \| 33.0 \| 264 \| 0.3793 \| 0.8627 \| \| 0.3482 \| 34.0 \| 272 \| 0.3477 \| 0.8588 \| \| 0.3519 \| 35.0 \| 280 \| 0.3692 \| 0.8667 \| \| 0.3519 \| 36.0 \| 288 \| 0.3611 \| 0.8627 \| \| 0.3311 \| 37.0 \| 296 \| 0.3233 \| 0.8745 \| \| 0.3222 \| 38.0 \| 304 \| 0.3416 \| 0.8627 \| \| 0.3013 \| 39.0 \| 312 \| 0.3198 \| 0.8824 \| \| 0.2871 \| 40.0 \| 320 \| 0.3308 \| 0.8667 \| \| 0.2871 \| 41.0 \| 328 \| 0.3246 \| 0.8667 \| \| 0.3154 \| 42.0 \| 336 \| 0.3943 \| 0.8667 \| \| 0.2735 \| 43.0 \| 344 \| 0.3186 \| 0.8784 \| \| 0.2911 \| 44.0 \| 352 \| 0.3132 \| 0.8824 \| \| 0.266 \| 45.0 \| 360 \| 0.3204 \| 0.8980 \| \| 0.266 \| 46.0 \| 368 \| 0.3097 \| 0.8784 \| \| 0.2686 \| 47.0 \| 376 \| 0.3075 \| 0.8902 \| \| 0.2818 \| 48.0 \| 384 \| 0.3192 \| 0.8902 \| \| 0.2492 \| 49.0 \| 392 \| 0.3434 \| 0.8745 \| \| 0.276 \| 50.0 \| 400 \| 0.3237 \| 0.8824 \| \| 0.276 \| 51.0 \| 408 \| 0.3450 \| 0.8745 \| \| 0.245 \| 52.0 \| 416 \| 0.3284 \| 0.8706 \| \| 0.2292 \| 53.0 \| 424 \| 0.3263 \| 0.8902 \| \| 0.2252 \| 54.0 \| 432 \| 0.3216 \| 0.8745 \| \| 0.2483 \| 55.0 \| 440 \| 0.3359 \| 0.8863 \| \| 0.2483 \| 56.0 \| 448 \| 0.3314 \| 0.8902 \| \| 0.2549 \| 57.0 \| 456 \| 0.3932 \| 0.8745 \| \| 0.2247 \| 58.0 \| 464 \| 0.3189 \| 0.8745 \| \| 0.2344 \| 59.0 \| 472 \| 0.3251 \| 0.8745 \| \| 0.2315 \| 60.0 \| 480 \| 0.3289 \| 0.8824 \| \| 0.2315 \| 61.0 \| 488 \| 0.3058 \| 0.8745 \| \| 0.2109 \| 62.0 \| 496 \| 0.2999 \| 0.8863 \| \| 0.2325 \| 63.0 \| 504 \| 0.3078 \| 0.8980 \| \| 0.2126 \| 64.0 \| 512 \| 0.3531 \| 0.8784 \| \| 0.1975 \| 65.0 \| 520 \| 0.3394 \| 0.8902 \| \| 0.1975 \| 66.0 \| 528 \| 0.3113 \| 0.8902 \| \| 0.1998 \| 67.0 \| 536 \| 0.3365 \| 0.8941 \| \| 0.2208 \| 68.0 \| 544 \| 0.2854 \| 0.9020 \| \| 0.2126 \| 69.0 \| 552 \| 0.3170 \| 0.8941 \| \| 0.2352 \| 70.0 \| 560 \| 0.3155 \| 0.8824 \| \| 0.2352 \| 71.0 \| 568 \| 0.3327 \| 0.8824 \| \| 0.1724 \| 72.0 \| 576 \| 0.3503 \| 0.8902 \| \| 0.2038 \| 73.0 \| 584 \| 0.3309 \| 0.8824 \| \| 0.1919 \| 74.0 \| 592 \| 0.3299 \| 0.8902 \| \| 0.2199 \| 75.0 \| 600 \| 0.3347 \| 0.8863 \| \| 0.2199 \| 76.0 \| 608 \| 0.3471 \| 0.8824 \| \| 0.2075 \| 77.0 \| 616 \| 0.3437 \| 0.8863 \| \| 0.2206 \| 78.0 \| 624 \| 0.3161 \| 0.8824 \| \| 0.1655 \| 79.0 \| 632 \| 0.3227 \| 0.8784 \| \| 0.1765 \| 80.0 \| 640 \| 0.3302 \| 0.8784 \| \| 0.1765 \| 81.0 \| 648 \| 0.3153 \| 0.8745 \| \| 0.1832 \| 82.0 \| 656 \| 0.3010 \| 0.8745 \| \| 0.185 \| 83.0 \| 664 \| 0.3266 \| 0.8941 \| \| 0.1627 \| 84.0 \| 672 \| 0.3192 \| 0.8941 \| \| 0.176 \| 85.0 \| 680 \| 0.3125 \| 0.8863 \| \| 0.176 \| 86.0 \| 688 \| 0.3241 \| 0.8745 \| \| 0.1723 \| 87.0 \| 696 \| 0.3124 \| 0.8784 \| \| 0.1477 \| 88.0 \| 704 \| 0.3109 \| 0.8745 \| \| 0.1703 \| 89.0 \| 712 \| 0.3196 \| 0.8824 \| \| 0.1919 \| 90.0 \| 720 \| 0.3186 \| 0.8980 \| \| 0.1919 \| 91.0 \| 728 \| 0.3178 \| 0.8902 \| \| 0.1465 \| 92.0 \| 736 \| 0.3241 \| 0.8824 \| \| 0.155 \| 93.0 \| 744 \| 0.3281 \| 0.8784 \| \| 0.1829 \| 94.0 \| 752 \| 0.3263 \| 0.8824 \| \| 0.167 \| 95.0 \| 760 \| 0.3282 \| 0.8824 \| \| 0.167 \| 96.0 \| 768 \| 0.3290 \| 0.8824 \| \| 0.166 \| 97.0 \| 776 \| 0.3253 \| 0.8902 \| \| 0.1756 \| 98.0 \| 784 \| 0.3231 \| 0.8863 \| \| 0.157 \| 99.0 \| 792 \| 0.3215 \| 0.8902 \| \| 0.1492 \| 100.0 \| 800 \| 0.3209 \| 0.8902 \| ### Framework versions - Transformers 4.33.3 - Pytorch 1.11.0+cu113 - Datasets 2.14.5 - Tokenizers 0.13.3
abeiler/AlphaRepInstruct	abeiler	2023-10-04T01:55:55Z	5	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:finetune:meta-llama/Llama-2-7b-hf", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-10-03T21:34:36Z	--- base_model: meta-llama/Llama-2-7b-hf tags: - generated_from_trainer model-index: - name: goatAlphaRepInstruct-QLORA results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # goatAlphaRepInstruct-QLORA This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.0 - Datasets 2.12.0 - Tokenizers 0.13.3
LarryAIDraw/zeta_ver1_0	LarryAIDraw	2023-10-04T01:24:17Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-10-03T01:10:31Z	--- license: creativeml-openrail-m --- https://civitai.com/models/155516/zeta-or-kage-no-jitsuryokusha-ni-naritakute
TanmaySah/misfil	TanmaySah	2023-10-04T01:22:59Z	0	0	peft	[ "peft", "region:us" ]	null	2023-10-03T18:31:53Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0
SangsooIm/distilbert-base-uncased-finetuned-clinc	SangsooIm	2023-10-04T01:22:04Z	105	0	transformers	[ "transformers", "pytorch", "distilbert", "text-classification", "generated_from_trainer", "dataset:clinc_oos", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-10-03T12:47:32Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer datasets: - clinc_oos metrics: - accuracy model-index: - name: distilbert-base-uncased-finetuned-clinc results: - task: name: Text Classification type: text-classification dataset: name: clinc_oos type: clinc_oos config: plus split: validation args: plus metrics: - name: Accuracy type: accuracy value: 0.9203225806451613 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-clinc This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset. It achieves the following results on the evaluation set: - Loss: 0.7647 - Accuracy: 0.9203 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 48 - eval_batch_size: 48 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 4.2957 \| 1.0 \| 318 \| 3.2774 \| 0.7229 \| \| 2.6097 \| 2.0 \| 636 \| 1.8593 \| 0.8435 \| \| 1.5339 \| 3.0 \| 954 \| 1.1434 \| 0.8977 \| \| 1.0029 \| 4.0 \| 1272 \| 0.8472 \| 0.9132 \| \| 0.784 \| 5.0 \| 1590 \| 0.7647 \| 0.9203 \| ### Framework versions - Transformers 4.34.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.14.0
AchyuthGamer/ImMagician-Fantasy	AchyuthGamer	2023-10-04T01:19:58Z	167	3	diffusers	[ "diffusers", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "MagicArt35", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-10-03T11:49:46Z	--- license: creativeml-openrail-m library_name: diffusers pipeline_tag: text-to-image tags: - stable-diffusion - stable-diffusion-diffusers - diffusers - text-to-image - MagicArt35 --- # ImMagician This a Model which generates Images based on Prompts. This is an amazing model which generates images with love, honesty and obedience. This Image model is made by Achyuth. To access this model with UI, visit [ImMagician](https://achyuthgamer-immagician.hf.space) See Some Examples here: ![Environments Example](https://huggingface.co/spaces/AchyuthGamer/ImMagician/resolve/main/img/download.jpg) ![Environments Example](https://huggingface.co/spaces/AchyuthGamer/ImMagician/resolve/main/img/download%20(1).jpg) ![Environments Example](https://huggingface.co/spaces/AchyuthGamer/ImMagician/resolve/main/img/download%20(3).jpg) ![Environments Example](https://huggingface.co/spaces/AchyuthGamer/ImMagician/resolve/main/img/download.jpeg) ![Environments Example](https://huggingface.co/spaces/AchyuthGamer/ImMagician/resolve/main/img/download%20(2).jpg)
LarryAIDraw/sakurasawa_sumi-10	LarryAIDraw	2023-10-04T01:17:10Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-10-04T00:56:49Z	--- license: creativeml-openrail-m --- https://civitai.com/models/155206/sakurasawa-sumi-rent-a-girlfriend-lora
LarryAIDraw/gertrude_remake	LarryAIDraw	2023-10-04T01:15:04Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-10-04T00:54:28Z	--- license: creativeml-openrail-m --- https://civitai.com/models/26531/arknights-gertrude
bdpc/resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_MSE	bdpc	2023-10-04T01:12:27Z	196	0	transformers	[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T18:02:31Z	--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_MSE results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_MSE This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.7429 - Accuracy: 0.7853 - Brier Loss: 0.3044 - Nll: 2.0364 - F1 Micro: 0.7853 - F1 Macro: 0.7862 - Ece: 0.0430 - Aurc: 0.0599 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 250 \| 9.5443 \| 0.0765 \| 0.9365 \| 3.7373 \| 0.0765 \| 0.0522 \| 0.0360 \| 0.9336 \| \| 9.4095 \| 2.0 \| 500 \| 7.4542 \| 0.0757 \| 0.9312 \| 2.8468 \| 0.0757 \| 0.0316 \| 0.0425 \| 0.8840 \| \| 9.4095 \| 3.0 \| 750 \| 5.8933 \| 0.0975 \| 0.9356 \| 3.2058 \| 0.0975 \| 0.0408 \| 0.0798 \| 0.8593 \| \| 5.9994 \| 4.0 \| 1000 \| 4.3665 \| 0.2125 \| 0.8700 \| 5.3759 \| 0.2125 \| 0.1290 \| 0.0743 \| 0.7029 \| \| 5.9994 \| 5.0 \| 1250 \| 3.0367 \| 0.4415 \| 0.6924 \| 4.9073 \| 0.4415 \| 0.4283 \| 0.0806 \| 0.3570 \| \| 3.2184 \| 6.0 \| 1500 \| 2.1589 \| 0.579 \| 0.5587 \| 3.7412 \| 0.579 \| 0.5771 \| 0.0572 \| 0.2172 \| \| 3.2184 \| 7.0 \| 1750 \| 1.5582 \| 0.652 \| 0.4673 \| 3.0701 \| 0.652 \| 0.6456 \| 0.0517 \| 0.1478 \| \| 1.6737 \| 8.0 \| 2000 \| 1.3502 \| 0.6893 \| 0.4266 \| 2.8575 \| 0.6893 \| 0.6860 \| 0.0544 \| 0.1175 \| \| 1.6737 \| 9.0 \| 2250 \| 1.1389 \| 0.7188 \| 0.3914 \| 2.5937 \| 0.7188 \| 0.7195 \| 0.0544 \| 0.1006 \| \| 1.0789 \| 10.0 \| 2500 \| 1.0563 \| 0.7302 \| 0.3742 \| 2.5043 \| 0.7302 \| 0.7305 \| 0.0618 \| 0.0912 \| \| 1.0789 \| 11.0 \| 2750 \| 1.0035 \| 0.7428 \| 0.3604 \| 2.4375 \| 0.7428 \| 0.7441 \| 0.0587 \| 0.0823 \| \| 0.7934 \| 12.0 \| 3000 \| 0.9169 \| 0.7548 \| 0.3472 \| 2.2921 \| 0.7548 \| 0.7555 \| 0.0547 \| 0.0762 \| \| 0.7934 \| 13.0 \| 3250 \| 0.8628 \| 0.7598 \| 0.3386 \| 2.2849 \| 0.7598 \| 0.7600 \| 0.0550 \| 0.0739 \| \| 0.6268 \| 14.0 \| 3500 \| 0.8773 \| 0.7675 \| 0.3362 \| 2.2170 \| 0.7675 \| 0.7692 \| 0.0490 \| 0.0718 \| \| 0.6268 \| 15.0 \| 3750 \| 0.8263 \| 0.7682 \| 0.3306 \| 2.1617 \| 0.7682 \| 0.7702 \| 0.0534 \| 0.0704 \| \| 0.5269 \| 16.0 \| 4000 \| 0.8422 \| 0.7708 \| 0.3289 \| 2.1907 \| 0.7707 \| 0.7717 \| 0.0524 \| 0.0687 \| \| 0.5269 \| 17.0 \| 4250 \| 0.8100 \| 0.7745 \| 0.3241 \| 2.1664 \| 0.7745 \| 0.7761 \| 0.0509 \| 0.0667 \| \| 0.4516 \| 18.0 \| 4500 \| 0.8013 \| 0.7778 \| 0.3215 \| 2.1216 \| 0.7778 \| 0.7790 \| 0.0473 \| 0.0669 \| \| 0.4516 \| 19.0 \| 4750 \| 0.7911 \| 0.7802 \| 0.3183 \| 2.1224 \| 0.7802 \| 0.7812 \| 0.0476 \| 0.0648 \| \| 0.4039 \| 20.0 \| 5000 \| 0.7900 \| 0.7775 \| 0.3197 \| 2.0969 \| 0.7775 \| 0.7797 \| 0.0473 \| 0.0647 \| \| 0.4039 \| 21.0 \| 5250 \| 0.7919 \| 0.7792 \| 0.3191 \| 2.1445 \| 0.7792 \| 0.7810 \| 0.0531 \| 0.0652 \| \| 0.3563 \| 22.0 \| 5500 \| 0.7960 \| 0.7802 \| 0.3166 \| 2.0849 \| 0.7802 \| 0.7818 \| 0.0478 \| 0.0649 \| \| 0.3563 \| 23.0 \| 5750 \| 0.7615 \| 0.7825 \| 0.3128 \| 2.0834 \| 0.7825 \| 0.7833 \| 0.0478 \| 0.0638 \| \| 0.3251 \| 24.0 \| 6000 \| 0.7840 \| 0.7792 \| 0.3151 \| 2.0841 \| 0.7792 \| 0.7800 \| 0.0513 \| 0.0648 \| \| 0.3251 \| 25.0 \| 6250 \| 0.7837 \| 0.7792 \| 0.3159 \| 2.0889 \| 0.7792 \| 0.7808 \| 0.0485 \| 0.0643 \| \| 0.2949 \| 26.0 \| 6500 \| 0.7827 \| 0.7802 \| 0.3158 \| 2.0416 \| 0.7802 \| 0.7819 \| 0.0548 \| 0.0648 \| \| 0.2949 \| 27.0 \| 6750 \| 0.7650 \| 0.78 \| 0.3130 \| 2.0411 \| 0.78 \| 0.7807 \| 0.0506 \| 0.0629 \| \| 0.2669 \| 28.0 \| 7000 \| 0.7787 \| 0.7802 \| 0.3133 \| 2.0843 \| 0.7802 \| 0.7810 \| 0.0454 \| 0.0627 \| \| 0.2669 \| 29.0 \| 7250 \| 0.7892 \| 0.782 \| 0.3163 \| 2.0953 \| 0.782 \| 0.7826 \| 0.0508 \| 0.0635 \| \| 0.2512 \| 30.0 \| 7500 \| 0.7775 \| 0.7825 \| 0.3126 \| 2.0904 \| 0.7825 \| 0.7837 \| 0.0451 \| 0.0633 \| \| 0.2512 \| 31.0 \| 7750 \| 0.7601 \| 0.7817 \| 0.3124 \| 2.0251 \| 0.7817 \| 0.7827 \| 0.0485 \| 0.0627 \| \| 0.231 \| 32.0 \| 8000 \| 0.7669 \| 0.7833 \| 0.3120 \| 2.0685 \| 0.7833 \| 0.7842 \| 0.0472 \| 0.0629 \| \| 0.231 \| 33.0 \| 8250 \| 0.7652 \| 0.7847 \| 0.3116 \| 2.0661 \| 0.7847 \| 0.7858 \| 0.0519 \| 0.0625 \| \| 0.2172 \| 34.0 \| 8500 \| 0.7637 \| 0.7837 \| 0.3107 \| 2.0264 \| 0.7837 \| 0.7852 \| 0.0487 \| 0.0628 \| \| 0.2172 \| 35.0 \| 8750 \| 0.7691 \| 0.783 \| 0.3120 \| 2.0535 \| 0.7830 \| 0.7844 \| 0.0438 \| 0.0634 \| \| 0.2032 \| 36.0 \| 9000 \| 0.7647 \| 0.7845 \| 0.3093 \| 2.0480 \| 0.7845 \| 0.7852 \| 0.0471 \| 0.0620 \| \| 0.2032 \| 37.0 \| 9250 \| 0.7727 \| 0.782 \| 0.3122 \| 2.0610 \| 0.782 \| 0.7830 \| 0.0493 \| 0.0628 \| \| 0.1925 \| 38.0 \| 9500 \| 0.7563 \| 0.7843 \| 0.3085 \| 2.0267 \| 0.7843 \| 0.7849 \| 0.0459 \| 0.0608 \| \| 0.1925 \| 39.0 \| 9750 \| 0.7597 \| 0.7835 \| 0.3087 \| 2.0062 \| 0.7835 \| 0.7845 \| 0.0485 \| 0.0614 \| \| 0.1823 \| 40.0 \| 10000 \| 0.7611 \| 0.7833 \| 0.3107 \| 2.0007 \| 0.7833 \| 0.7853 \| 0.0479 \| 0.0625 \| \| 0.1823 \| 41.0 \| 10250 \| 0.7608 \| 0.7843 \| 0.3076 \| 2.0335 \| 0.7843 \| 0.7854 \| 0.0486 \| 0.0602 \| \| 0.17 \| 42.0 \| 10500 \| 0.7535 \| 0.7833 \| 0.3096 \| 2.0121 \| 0.7833 \| 0.7844 \| 0.0505 \| 0.0613 \| \| 0.17 \| 43.0 \| 10750 \| 0.7524 \| 0.7845 \| 0.3066 \| 2.0425 \| 0.7845 \| 0.7856 \| 0.0476 \| 0.0605 \| \| 0.1639 \| 44.0 \| 11000 \| 0.7608 \| 0.7808 \| 0.3108 \| 2.0739 \| 0.7808 \| 0.7816 \| 0.0503 \| 0.0618 \| \| 0.1639 \| 45.0 \| 11250 \| 0.7560 \| 0.786 \| 0.3063 \| 1.9876 \| 0.786 \| 0.7868 \| 0.0496 \| 0.0607 \| \| 0.1575 \| 46.0 \| 11500 \| 0.7494 \| 0.784 \| 0.3063 \| 2.0311 \| 0.7840 \| 0.7846 \| 0.0416 \| 0.0601 \| \| 0.1575 \| 47.0 \| 11750 \| 0.7515 \| 0.7857 \| 0.3069 \| 2.0539 \| 0.7857 \| 0.7866 \| 0.0456 \| 0.0609 \| \| 0.1493 \| 48.0 \| 12000 \| 0.7511 \| 0.7843 \| 0.3086 \| 2.0325 \| 0.7843 \| 0.7852 \| 0.0552 \| 0.0612 \| \| 0.1493 \| 49.0 \| 12250 \| 0.7495 \| 0.787 \| 0.3067 \| 2.0231 \| 0.787 \| 0.7880 \| 0.0475 \| 0.0605 \| \| 0.1425 \| 50.0 \| 12500 \| 0.7538 \| 0.7867 \| 0.3052 \| 2.0267 \| 0.7868 \| 0.7870 \| 0.0507 \| 0.0603 \| \| 0.1425 \| 51.0 \| 12750 \| 0.7529 \| 0.7847 \| 0.3081 \| 2.0592 \| 0.7847 \| 0.7859 \| 0.0467 \| 0.0604 \| \| 0.1356 \| 52.0 \| 13000 \| 0.7527 \| 0.7808 \| 0.3071 \| 2.0349 \| 0.7808 \| 0.7818 \| 0.0473 \| 0.0607 \| \| 0.1356 \| 53.0 \| 13250 \| 0.7451 \| 0.7865 \| 0.3049 \| 2.0368 \| 0.7865 \| 0.7879 \| 0.0484 \| 0.0595 \| \| 0.1325 \| 54.0 \| 13500 \| 0.7481 \| 0.7857 \| 0.3056 \| 2.0223 \| 0.7857 \| 0.7869 \| 0.0468 \| 0.0603 \| \| 0.1325 \| 55.0 \| 13750 \| 0.7470 \| 0.7835 \| 0.3057 \| 2.0306 \| 0.7835 \| 0.7844 \| 0.0492 \| 0.0601 \| \| 0.1264 \| 56.0 \| 14000 \| 0.7471 \| 0.7873 \| 0.3053 \| 2.0336 \| 0.7873 \| 0.7880 \| 0.0519 \| 0.0601 \| \| 0.1264 \| 57.0 \| 14250 \| 0.7429 \| 0.7895 \| 0.3032 \| 2.0149 \| 0.7895 \| 0.7903 \| 0.0468 \| 0.0595 \| \| 0.1208 \| 58.0 \| 14500 \| 0.7399 \| 0.7885 \| 0.3035 \| 2.0147 \| 0.7885 \| 0.7895 \| 0.0433 \| 0.0596 \| \| 0.1208 \| 59.0 \| 14750 \| 0.7518 \| 0.786 \| 0.3076 \| 2.0481 \| 0.786 \| 0.7873 \| 0.0403 \| 0.0607 \| \| 0.119 \| 60.0 \| 15000 \| 0.7483 \| 0.7903 \| 0.3058 \| 2.0138 \| 0.7903 \| 0.7914 \| 0.0471 \| 0.0601 \| \| 0.119 \| 61.0 \| 15250 \| 0.7463 \| 0.7845 \| 0.3043 \| 2.0617 \| 0.7845 \| 0.7855 \| 0.0458 \| 0.0599 \| \| 0.1128 \| 62.0 \| 15500 \| 0.7478 \| 0.7875 \| 0.3056 \| 2.0187 \| 0.7875 \| 0.7888 \| 0.0452 \| 0.0604 \| \| 0.1128 \| 63.0 \| 15750 \| 0.7510 \| 0.784 \| 0.3061 \| 2.0204 \| 0.7840 \| 0.7850 \| 0.0495 \| 0.0605 \| \| 0.1109 \| 64.0 \| 16000 \| 0.7424 \| 0.786 \| 0.3053 \| 2.0167 \| 0.786 \| 0.7871 \| 0.0449 \| 0.0603 \| \| 0.1109 \| 65.0 \| 16250 \| 0.7473 \| 0.7885 \| 0.3054 \| 2.0200 \| 0.7885 \| 0.7893 \| 0.0471 \| 0.0600 \| \| 0.1078 \| 66.0 \| 16500 \| 0.7467 \| 0.7873 \| 0.3054 \| 2.0224 \| 0.7873 \| 0.7883 \| 0.0482 \| 0.0599 \| \| 0.1078 \| 67.0 \| 16750 \| 0.7445 \| 0.7893 \| 0.3039 \| 2.0082 \| 0.7893 \| 0.7895 \| 0.0456 \| 0.0593 \| \| 0.1051 \| 68.0 \| 17000 \| 0.7490 \| 0.7873 \| 0.3063 \| 2.0152 \| 0.7873 \| 0.7883 \| 0.0505 \| 0.0602 \| \| 0.1051 \| 69.0 \| 17250 \| 0.7490 \| 0.785 \| 0.3061 \| 2.0103 \| 0.785 \| 0.7861 \| 0.0465 \| 0.0602 \| \| 0.1009 \| 70.0 \| 17500 \| 0.7445 \| 0.7875 \| 0.3049 \| 2.0308 \| 0.7875 \| 0.7884 \| 0.0483 \| 0.0598 \| \| 0.1009 \| 71.0 \| 17750 \| 0.7490 \| 0.7863 \| 0.3068 \| 2.0260 \| 0.7863 \| 0.7875 \| 0.0495 \| 0.0604 \| \| 0.0984 \| 72.0 \| 18000 \| 0.7465 \| 0.7893 \| 0.3059 \| 2.0161 \| 0.7893 \| 0.7906 \| 0.0427 \| 0.0601 \| \| 0.0984 \| 73.0 \| 18250 \| 0.7451 \| 0.7873 \| 0.3058 \| 2.0204 \| 0.7873 \| 0.7882 \| 0.0511 \| 0.0605 \| \| 0.0966 \| 74.0 \| 18500 \| 0.7445 \| 0.7875 \| 0.3042 \| 2.0227 \| 0.7875 \| 0.7886 \| 0.0495 \| 0.0599 \| \| 0.0966 \| 75.0 \| 18750 \| 0.7443 \| 0.7863 \| 0.3040 \| 2.0138 \| 0.7863 \| 0.7872 \| 0.0442 \| 0.0598 \| \| 0.0947 \| 76.0 \| 19000 \| 0.7448 \| 0.7865 \| 0.3054 \| 2.0234 \| 0.7865 \| 0.7873 \| 0.0457 \| 0.0598 \| \| 0.0947 \| 77.0 \| 19250 \| 0.7448 \| 0.7865 \| 0.3041 \| 2.0110 \| 0.7865 \| 0.7875 \| 0.0508 \| 0.0596 \| \| 0.0931 \| 78.0 \| 19500 \| 0.7460 \| 0.7883 \| 0.3040 \| 2.0125 \| 0.7883 \| 0.7895 \| 0.0467 \| 0.0595 \| \| 0.0931 \| 79.0 \| 19750 \| 0.7456 \| 0.7883 \| 0.3038 \| 2.0302 \| 0.7883 \| 0.7894 \| 0.0455 \| 0.0596 \| \| 0.0899 \| 80.0 \| 20000 \| 0.7469 \| 0.788 \| 0.3040 \| 2.0188 \| 0.788 \| 0.7892 \| 0.0487 \| 0.0597 \| \| 0.0899 \| 81.0 \| 20250 \| 0.7421 \| 0.788 \| 0.3041 \| 2.0359 \| 0.788 \| 0.7888 \| 0.0427 \| 0.0595 \| \| 0.0882 \| 82.0 \| 20500 \| 0.7444 \| 0.7865 \| 0.3051 \| 2.0219 \| 0.7865 \| 0.7875 \| 0.0479 \| 0.0600 \| \| 0.0882 \| 83.0 \| 20750 \| 0.7439 \| 0.788 \| 0.3039 \| 2.0197 \| 0.788 \| 0.7894 \| 0.0439 \| 0.0597 \| \| 0.0871 \| 84.0 \| 21000 \| 0.7421 \| 0.7865 \| 0.3040 \| 1.9910 \| 0.7865 \| 0.7876 \| 0.0445 \| 0.0598 \| \| 0.0871 \| 85.0 \| 21250 \| 0.7429 \| 0.7887 \| 0.3043 \| 2.0253 \| 0.7887 \| 0.7898 \| 0.0426 \| 0.0597 \| \| 0.0869 \| 86.0 \| 21500 \| 0.7442 \| 0.7873 \| 0.3041 \| 2.0156 \| 0.7873 \| 0.7885 \| 0.0488 \| 0.0596 \| \| 0.0869 \| 87.0 \| 21750 \| 0.7439 \| 0.7857 \| 0.3051 \| 2.0099 \| 0.7857 \| 0.7867 \| 0.0465 \| 0.0599 \| \| 0.084 \| 88.0 \| 22000 \| 0.7434 \| 0.786 \| 0.3040 \| 1.9926 \| 0.786 \| 0.7869 \| 0.0469 \| 0.0598 \| \| 0.084 \| 89.0 \| 22250 \| 0.7431 \| 0.7873 \| 0.3048 \| 2.0028 \| 0.7873 \| 0.7880 \| 0.0442 \| 0.0599 \| \| 0.0821 \| 90.0 \| 22500 \| 0.7447 \| 0.7867 \| 0.3040 \| 2.0349 \| 0.7868 \| 0.7876 \| 0.0477 \| 0.0596 \| \| 0.0821 \| 91.0 \| 22750 \| 0.7443 \| 0.7877 \| 0.3051 \| 2.0356 \| 0.7877 \| 0.7887 \| 0.0486 \| 0.0601 \| \| 0.0813 \| 92.0 \| 23000 \| 0.7500 \| 0.7873 \| 0.3053 \| 2.0465 \| 0.7873 \| 0.7880 \| 0.0484 \| 0.0601 \| \| 0.0813 \| 93.0 \| 23250 \| 0.7449 \| 0.788 \| 0.3037 \| 1.9966 \| 0.788 \| 0.7890 \| 0.0441 \| 0.0594 \| \| 0.0811 \| 94.0 \| 23500 \| 0.7466 \| 0.7897 \| 0.3048 \| 2.0297 \| 0.7897 \| 0.7907 \| 0.0429 \| 0.0600 \| \| 0.0811 \| 95.0 \| 23750 \| 0.7482 \| 0.7875 \| 0.3058 \| 2.0319 \| 0.7875 \| 0.7885 \| 0.0464 \| 0.0601 \| \| 0.0808 \| 96.0 \| 24000 \| 0.7473 \| 0.7863 \| 0.3055 \| 2.0219 \| 0.7863 \| 0.7874 \| 0.0477 \| 0.0603 \| \| 0.0808 \| 97.0 \| 24250 \| 0.7451 \| 0.7855 \| 0.3044 \| 2.0356 \| 0.7855 \| 0.7865 \| 0.0481 \| 0.0594 \| \| 0.08 \| 98.0 \| 24500 \| 0.7442 \| 0.7857 \| 0.3042 \| 2.0213 \| 0.7857 \| 0.7868 \| 0.0475 \| 0.0595 \| \| 0.08 \| 99.0 \| 24750 \| 0.7462 \| 0.7863 \| 0.3053 \| 2.0354 \| 0.7863 \| 0.7874 \| 0.0425 \| 0.0599 \| \| 0.079 \| 100.0 \| 25000 \| 0.7429 \| 0.7853 \| 0.3044 \| 2.0364 \| 0.7853 \| 0.7862 \| 0.0430 \| 0.0599 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3
bdpc/resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t2.5_a0.5	bdpc	2023-10-04T01:11:55Z	191	0	transformers	[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T18:02:30Z	--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t2.5_a0.5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t2.5_a0.5 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5837 - Accuracy: 0.7867 - Brier Loss: 0.3013 - Nll: 1.9882 - F1 Micro: 0.7868 - F1 Macro: 0.7860 - Ece: 0.0529 - Aurc: 0.0581 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 250 \| 4.1958 \| 0.1035 \| 0.9350 \| 9.1004 \| 0.1035 \| 0.0792 \| 0.0472 \| 0.9013 \| \| 4.2322 \| 2.0 \| 500 \| 4.0778 \| 0.173 \| 0.9251 \| 6.5742 \| 0.173 \| 0.1393 \| 0.0993 \| 0.7501 \| \| 4.2322 \| 3.0 \| 750 \| 3.6484 \| 0.339 \| 0.8778 \| 4.9108 \| 0.339 \| 0.2957 \| 0.2172 \| 0.5305 \| \| 3.5256 \| 4.0 \| 1000 \| 2.5967 \| 0.4592 \| 0.6991 \| 3.3640 \| 0.4592 \| 0.4220 \| 0.1274 \| 0.3285 \| \| 3.5256 \| 5.0 \| 1250 \| 2.0345 \| 0.5417 \| 0.6078 \| 3.0118 \| 0.5417 \| 0.5180 \| 0.0976 \| 0.2447 \| \| 1.9172 \| 6.0 \| 1500 \| 1.4417 \| 0.625 \| 0.5029 \| 2.7890 \| 0.625 \| 0.6123 \| 0.0549 \| 0.1623 \| \| 1.9172 \| 7.0 \| 1750 \| 1.3298 \| 0.639 \| 0.4852 \| 2.6110 \| 0.639 \| 0.6320 \| 0.0558 \| 0.1501 \| \| 1.1801 \| 8.0 \| 2000 \| 1.1697 \| 0.674 \| 0.4473 \| 2.4787 \| 0.674 \| 0.6712 \| 0.0466 \| 0.1283 \| \| 1.1801 \| 9.0 \| 2250 \| 0.9625 \| 0.7093 \| 0.4020 \| 2.3242 \| 0.7093 \| 0.7085 \| 0.0526 \| 0.1017 \| \| 0.8029 \| 10.0 \| 2500 \| 0.9477 \| 0.7215 \| 0.3893 \| 2.3193 \| 0.7215 \| 0.7228 \| 0.0515 \| 0.0971 \| \| 0.8029 \| 11.0 \| 2750 \| 0.8527 \| 0.7375 \| 0.3692 \| 2.2785 \| 0.7375 \| 0.7377 \| 0.0490 \| 0.0870 \| \| 0.5717 \| 12.0 \| 3000 \| 0.7377 \| 0.7515 \| 0.3470 \| 2.1475 \| 0.7515 \| 0.7529 \| 0.0552 \| 0.0757 \| \| 0.5717 \| 13.0 \| 3250 \| 0.7309 \| 0.7498 \| 0.3469 \| 2.1250 \| 0.7498 \| 0.7494 \| 0.0589 \| 0.0758 \| \| 0.4414 \| 14.0 \| 3500 \| 0.7165 \| 0.7558 \| 0.3427 \| 2.1045 \| 0.7558 \| 0.7576 \| 0.0582 \| 0.0721 \| \| 0.4414 \| 15.0 \| 3750 \| 0.6865 \| 0.7678 \| 0.3319 \| 2.0457 \| 0.7678 \| 0.7688 \| 0.0551 \| 0.0697 \| \| 0.3691 \| 16.0 \| 4000 \| 0.7002 \| 0.7662 \| 0.3348 \| 2.1280 \| 0.7663 \| 0.7664 \| 0.0567 \| 0.0698 \| \| 0.3691 \| 17.0 \| 4250 \| 0.6896 \| 0.7628 \| 0.3326 \| 2.0750 \| 0.7628 \| 0.7631 \| 0.0608 \| 0.0691 \| \| 0.3214 \| 18.0 \| 4500 \| 0.6666 \| 0.7715 \| 0.3258 \| 2.0468 \| 0.7715 \| 0.7707 \| 0.0544 \| 0.0680 \| \| 0.3214 \| 19.0 \| 4750 \| 0.6735 \| 0.7702 \| 0.3277 \| 2.0544 \| 0.7702 \| 0.7700 \| 0.0571 \| 0.0681 \| \| 0.2914 \| 20.0 \| 5000 \| 0.6607 \| 0.772 \| 0.3241 \| 2.0364 \| 0.772 \| 0.7729 \| 0.0525 \| 0.0659 \| \| 0.2914 \| 21.0 \| 5250 \| 0.6625 \| 0.7688 \| 0.3217 \| 2.0387 \| 0.7688 \| 0.7703 \| 0.0455 \| 0.0664 \| \| 0.2653 \| 22.0 \| 5500 \| 0.6543 \| 0.775 \| 0.3200 \| 2.0560 \| 0.775 \| 0.7752 \| 0.0507 \| 0.0647 \| \| 0.2653 \| 23.0 \| 5750 \| 0.6409 \| 0.7725 \| 0.3188 \| 2.0091 \| 0.7725 \| 0.7733 \| 0.0554 \| 0.0647 \| \| 0.2482 \| 24.0 \| 6000 \| 0.6452 \| 0.7758 \| 0.3191 \| 2.0256 \| 0.7758 \| 0.7756 \| 0.0502 \| 0.0655 \| \| 0.2482 \| 25.0 \| 6250 \| 0.6401 \| 0.7742 \| 0.3196 \| 2.0668 \| 0.7742 \| 0.7745 \| 0.0528 \| 0.0648 \| \| 0.2354 \| 26.0 \| 6500 \| 0.6316 \| 0.775 \| 0.3171 \| 2.0150 \| 0.775 \| 0.7755 \| 0.0555 \| 0.0634 \| \| 0.2354 \| 27.0 \| 6750 \| 0.6257 \| 0.7808 \| 0.3147 \| 2.0129 \| 0.7808 \| 0.7808 \| 0.0503 \| 0.0624 \| \| 0.2229 \| 28.0 \| 7000 \| 0.6343 \| 0.7778 \| 0.3144 \| 2.0910 \| 0.7778 \| 0.7776 \| 0.0510 \| 0.0624 \| \| 0.2229 \| 29.0 \| 7250 \| 0.6206 \| 0.781 \| 0.3115 \| 2.0399 \| 0.7810 \| 0.7798 \| 0.0555 \| 0.0606 \| \| 0.2147 \| 30.0 \| 7500 \| 0.6262 \| 0.777 \| 0.3124 \| 2.0603 \| 0.777 \| 0.7772 \| 0.0539 \| 0.0616 \| \| 0.2147 \| 31.0 \| 7750 \| 0.6265 \| 0.7788 \| 0.3137 \| 2.0833 \| 0.7788 \| 0.7777 \| 0.0532 \| 0.0614 \| \| 0.2058 \| 32.0 \| 8000 \| 0.6134 \| 0.7815 \| 0.3119 \| 2.0369 \| 0.7815 \| 0.7815 \| 0.0514 \| 0.0615 \| \| 0.2058 \| 33.0 \| 8250 \| 0.6153 \| 0.7772 \| 0.3133 \| 2.0513 \| 0.7773 \| 0.7772 \| 0.0534 \| 0.0623 \| \| 0.1994 \| 34.0 \| 8500 \| 0.6143 \| 0.7853 \| 0.3098 \| 2.0188 \| 0.7853 \| 0.7857 \| 0.0508 \| 0.0611 \| \| 0.1994 \| 35.0 \| 8750 \| 0.6096 \| 0.7827 \| 0.3086 \| 2.0134 \| 0.7828 \| 0.7828 \| 0.0512 \| 0.0606 \| \| 0.1932 \| 36.0 \| 9000 \| 0.6094 \| 0.784 \| 0.3067 \| 2.0151 \| 0.7840 \| 0.7847 \| 0.0471 \| 0.0602 \| \| 0.1932 \| 37.0 \| 9250 \| 0.6142 \| 0.7833 \| 0.3111 \| 2.0213 \| 0.7833 \| 0.7829 \| 0.0542 \| 0.0608 \| \| 0.1895 \| 38.0 \| 9500 \| 0.6103 \| 0.7812 \| 0.3094 \| 2.0594 \| 0.7812 \| 0.7799 \| 0.0529 \| 0.0603 \| \| 0.1895 \| 39.0 \| 9750 \| 0.6059 \| 0.781 \| 0.3078 \| 2.0386 \| 0.7810 \| 0.7806 \| 0.0545 \| 0.0607 \| \| 0.1848 \| 40.0 \| 10000 \| 0.6042 \| 0.782 \| 0.3072 \| 2.0133 \| 0.782 \| 0.7824 \| 0.0527 \| 0.0603 \| \| 0.1848 \| 41.0 \| 10250 \| 0.5991 \| 0.785 \| 0.3043 \| 2.0124 \| 0.785 \| 0.7853 \| 0.0496 \| 0.0594 \| \| 0.1793 \| 42.0 \| 10500 \| 0.6034 \| 0.784 \| 0.3058 \| 2.0607 \| 0.7840 \| 0.7838 \| 0.0490 \| 0.0599 \| \| 0.1793 \| 43.0 \| 10750 \| 0.6047 \| 0.7827 \| 0.3068 \| 2.0139 \| 0.7828 \| 0.7819 \| 0.0492 \| 0.0595 \| \| 0.1768 \| 44.0 \| 11000 \| 0.5982 \| 0.785 \| 0.3057 \| 2.0303 \| 0.785 \| 0.7843 \| 0.0473 \| 0.0596 \| \| 0.1768 \| 45.0 \| 11250 \| 0.6036 \| 0.7795 \| 0.3087 \| 2.0173 \| 0.7795 \| 0.7788 \| 0.0549 \| 0.0607 \| \| 0.1743 \| 46.0 \| 11500 \| 0.5974 \| 0.785 \| 0.3060 \| 2.0026 \| 0.785 \| 0.7839 \| 0.0478 \| 0.0596 \| \| 0.1743 \| 47.0 \| 11750 \| 0.5996 \| 0.782 \| 0.3068 \| 2.0144 \| 0.782 \| 0.7825 \| 0.0480 \| 0.0598 \| \| 0.1707 \| 48.0 \| 12000 \| 0.5958 \| 0.7833 \| 0.3079 \| 2.0344 \| 0.7833 \| 0.7827 \| 0.0500 \| 0.0598 \| \| 0.1707 \| 49.0 \| 12250 \| 0.5969 \| 0.782 \| 0.3060 \| 2.0162 \| 0.782 \| 0.7820 \| 0.0482 \| 0.0597 \| \| 0.1683 \| 50.0 \| 12500 \| 0.5933 \| 0.784 \| 0.3043 \| 1.9897 \| 0.7840 \| 0.7836 \| 0.0496 \| 0.0589 \| \| 0.1683 \| 51.0 \| 12750 \| 0.5935 \| 0.7833 \| 0.3042 \| 2.0142 \| 0.7833 \| 0.7829 \| 0.0501 \| 0.0586 \| \| 0.1649 \| 52.0 \| 13000 \| 0.5950 \| 0.7847 \| 0.3050 \| 2.0125 \| 0.7847 \| 0.7851 \| 0.0475 \| 0.0591 \| \| 0.1649 \| 53.0 \| 13250 \| 0.5904 \| 0.7837 \| 0.3020 \| 1.9830 \| 0.7837 \| 0.7837 \| 0.0504 \| 0.0584 \| \| 0.1636 \| 54.0 \| 13500 \| 0.5926 \| 0.785 \| 0.3042 \| 2.0006 \| 0.785 \| 0.7845 \| 0.0493 \| 0.0588 \| \| 0.1636 \| 55.0 \| 13750 \| 0.5885 \| 0.7847 \| 0.3029 \| 2.0025 \| 0.7847 \| 0.7843 \| 0.0505 \| 0.0585 \| \| 0.1616 \| 56.0 \| 14000 \| 0.5920 \| 0.788 \| 0.3041 \| 2.0174 \| 0.788 \| 0.7878 \| 0.0520 \| 0.0591 \| \| 0.1616 \| 57.0 \| 14250 \| 0.5927 \| 0.7863 \| 0.3033 \| 2.0321 \| 0.7863 \| 0.7858 \| 0.0521 \| 0.0588 \| \| 0.1592 \| 58.0 \| 14500 \| 0.5878 \| 0.787 \| 0.3017 \| 1.9751 \| 0.787 \| 0.7874 \| 0.0461 \| 0.0584 \| \| 0.1592 \| 59.0 \| 14750 \| 0.5888 \| 0.7867 \| 0.3030 \| 1.9996 \| 0.7868 \| 0.7864 \| 0.0494 \| 0.0582 \| \| 0.1585 \| 60.0 \| 15000 \| 0.5929 \| 0.786 \| 0.3052 \| 2.0237 \| 0.786 \| 0.7857 \| 0.0512 \| 0.0584 \| \| 0.1585 \| 61.0 \| 15250 \| 0.5894 \| 0.7865 \| 0.3026 \| 1.9895 \| 0.7865 \| 0.7864 \| 0.0548 \| 0.0585 \| \| 0.1562 \| 62.0 \| 15500 \| 0.5903 \| 0.7873 \| 0.3033 \| 1.9670 \| 0.7873 \| 0.7870 \| 0.0481 \| 0.0584 \| \| 0.1562 \| 63.0 \| 15750 \| 0.5896 \| 0.7853 \| 0.3023 \| 1.9681 \| 0.7853 \| 0.7850 \| 0.0520 \| 0.0587 \| \| 0.1548 \| 64.0 \| 16000 \| 0.5903 \| 0.7847 \| 0.3027 \| 1.9865 \| 0.7847 \| 0.7846 \| 0.0506 \| 0.0587 \| \| 0.1548 \| 65.0 \| 16250 \| 0.5910 \| 0.7853 \| 0.3039 \| 2.0009 \| 0.7853 \| 0.7849 \| 0.0515 \| 0.0593 \| \| 0.1537 \| 66.0 \| 16500 \| 0.5866 \| 0.7883 \| 0.3012 \| 1.9561 \| 0.7883 \| 0.7881 \| 0.0447 \| 0.0581 \| \| 0.1537 \| 67.0 \| 16750 \| 0.5858 \| 0.7867 \| 0.3009 \| 1.9868 \| 0.7868 \| 0.7861 \| 0.0486 \| 0.0577 \| \| 0.1526 \| 68.0 \| 17000 \| 0.5886 \| 0.7867 \| 0.3024 \| 2.0009 \| 0.7868 \| 0.7862 \| 0.0530 \| 0.0587 \| \| 0.1526 \| 69.0 \| 17250 \| 0.5850 \| 0.7863 \| 0.3010 \| 2.0095 \| 0.7863 \| 0.7860 \| 0.0510 \| 0.0581 \| \| 0.1508 \| 70.0 \| 17500 \| 0.5867 \| 0.7865 \| 0.3019 \| 2.0304 \| 0.7865 \| 0.7861 \| 0.0525 \| 0.0583 \| \| 0.1508 \| 71.0 \| 17750 \| 0.5895 \| 0.7857 \| 0.3038 \| 2.0013 \| 0.7857 \| 0.7853 \| 0.0478 \| 0.0586 \| \| 0.15 \| 72.0 \| 18000 \| 0.5894 \| 0.7847 \| 0.3025 \| 2.0051 \| 0.7847 \| 0.7845 \| 0.0500 \| 0.0586 \| \| 0.15 \| 73.0 \| 18250 \| 0.5867 \| 0.7865 \| 0.3022 \| 1.9634 \| 0.7865 \| 0.7860 \| 0.0489 \| 0.0582 \| \| 0.149 \| 74.0 \| 18500 \| 0.5888 \| 0.7857 \| 0.3026 \| 1.9817 \| 0.7857 \| 0.7851 \| 0.0497 \| 0.0584 \| \| 0.149 \| 75.0 \| 18750 \| 0.5823 \| 0.7885 \| 0.2994 \| 1.9873 \| 0.7885 \| 0.7880 \| 0.0476 \| 0.0577 \| \| 0.1483 \| 76.0 \| 19000 \| 0.5866 \| 0.7853 \| 0.3025 \| 1.9870 \| 0.7853 \| 0.7849 \| 0.0531 \| 0.0583 \| \| 0.1483 \| 77.0 \| 19250 \| 0.5866 \| 0.7867 \| 0.3013 \| 1.9933 \| 0.7868 \| 0.7862 \| 0.0498 \| 0.0577 \| \| 0.1478 \| 78.0 \| 19500 \| 0.5844 \| 0.787 \| 0.3010 \| 1.9793 \| 0.787 \| 0.7868 \| 0.0465 \| 0.0579 \| \| 0.1478 \| 79.0 \| 19750 \| 0.5850 \| 0.7857 \| 0.3005 \| 1.9856 \| 0.7857 \| 0.7855 \| 0.0489 \| 0.0580 \| \| 0.1463 \| 80.0 \| 20000 \| 0.5829 \| 0.7893 \| 0.2999 \| 2.0003 \| 0.7893 \| 0.7890 \| 0.0543 \| 0.0578 \| \| 0.1463 \| 81.0 \| 20250 \| 0.5845 \| 0.7867 \| 0.3011 \| 2.0178 \| 0.7868 \| 0.7864 \| 0.0494 \| 0.0580 \| \| 0.1457 \| 82.0 \| 20500 \| 0.5878 \| 0.7865 \| 0.3022 \| 2.0108 \| 0.7865 \| 0.7861 \| 0.0507 \| 0.0583 \| \| 0.1457 \| 83.0 \| 20750 \| 0.5862 \| 0.7865 \| 0.3016 \| 1.9996 \| 0.7865 \| 0.7865 \| 0.0505 \| 0.0585 \| \| 0.1452 \| 84.0 \| 21000 \| 0.5851 \| 0.7863 \| 0.3011 \| 2.0002 \| 0.7863 \| 0.7859 \| 0.0481 \| 0.0582 \| \| 0.1452 \| 85.0 \| 21250 \| 0.5850 \| 0.787 \| 0.3013 \| 1.9659 \| 0.787 \| 0.7867 \| 0.0524 \| 0.0582 \| \| 0.1449 \| 86.0 \| 21500 \| 0.5878 \| 0.7867 \| 0.3023 \| 1.9837 \| 0.7868 \| 0.7866 \| 0.0526 \| 0.0581 \| \| 0.1449 \| 87.0 \| 21750 \| 0.5844 \| 0.7873 \| 0.3010 \| 1.9807 \| 0.7873 \| 0.7865 \| 0.0522 \| 0.0577 \| \| 0.1437 \| 88.0 \| 22000 \| 0.5846 \| 0.7877 \| 0.3012 \| 1.9947 \| 0.7877 \| 0.7869 \| 0.0464 \| 0.0580 \| \| 0.1437 \| 89.0 \| 22250 \| 0.5859 \| 0.787 \| 0.3016 \| 2.0002 \| 0.787 \| 0.7867 \| 0.0503 \| 0.0581 \| \| 0.143 \| 90.0 \| 22500 \| 0.5838 \| 0.7865 \| 0.3010 \| 1.9996 \| 0.7865 \| 0.7859 \| 0.0496 \| 0.0576 \| \| 0.143 \| 91.0 \| 22750 \| 0.5843 \| 0.7837 \| 0.3011 \| 1.9683 \| 0.7837 \| 0.7834 \| 0.0501 \| 0.0583 \| \| 0.1426 \| 92.0 \| 23000 \| 0.5843 \| 0.7873 \| 0.3010 \| 1.9960 \| 0.7873 \| 0.7870 \| 0.0524 \| 0.0578 \| \| 0.1426 \| 93.0 \| 23250 \| 0.5827 \| 0.7847 \| 0.3005 \| 1.9719 \| 0.7847 \| 0.7844 \| 0.0506 \| 0.0579 \| \| 0.1428 \| 94.0 \| 23500 \| 0.5831 \| 0.7865 \| 0.3009 \| 1.9781 \| 0.7865 \| 0.7862 \| 0.0517 \| 0.0579 \| \| 0.1428 \| 95.0 \| 23750 \| 0.5821 \| 0.784 \| 0.3001 \| 1.9641 \| 0.7840 \| 0.7838 \| 0.0505 \| 0.0579 \| \| 0.1424 \| 96.0 \| 24000 \| 0.5850 \| 0.7845 \| 0.3020 \| 1.9667 \| 0.7845 \| 0.7842 \| 0.0526 \| 0.0584 \| \| 0.1424 \| 97.0 \| 24250 \| 0.5850 \| 0.7847 \| 0.3012 \| 1.9776 \| 0.7847 \| 0.7844 \| 0.0508 \| 0.0579 \| \| 0.142 \| 98.0 \| 24500 \| 0.5845 \| 0.7877 \| 0.3011 \| 1.9745 \| 0.7877 \| 0.7870 \| 0.0491 \| 0.0579 \| \| 0.142 \| 99.0 \| 24750 \| 0.5834 \| 0.7853 \| 0.3010 \| 1.9679 \| 0.7853 \| 0.7852 \| 0.0506 \| 0.0581 \| \| 0.1416 \| 100.0 \| 25000 \| 0.5837 \| 0.7867 \| 0.3013 \| 1.9882 \| 0.7868 \| 0.7860 \| 0.0529 \| 0.0581 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3
LarryAIDraw/ijichi_seika-10	LarryAIDraw	2023-10-04T01:01:15Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-10-04T00:56:27Z	--- license: creativeml-openrail-m --- https://civitai.com/models/154638/ijichi-seika-bocchi-the-rock-lora
LarryAIDraw/Hwahjah_v1	LarryAIDraw	2023-10-04T00:54:00Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-10-04T00:50:01Z	--- license: creativeml-openrail-m --- https://civitai.com/models/155533/hwah-jah-azur-lane
LarryAIDraw/ShinanoSummerFluffV1	LarryAIDraw	2023-10-04T00:53:28Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-10-04T00:49:09Z	--- license: creativeml-openrail-m --- https://civitai.com/models/155698/shinano-greaterdreamy-white-sandsless-or-swimsuit-skin-or-azur-lane
LarryAIDraw/topaz_hsr	LarryAIDraw	2023-10-04T00:53:11Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2023-10-04T00:48:39Z	--- license: creativeml-openrail-m --- https://civitai.com/models/156239/topaz-honkai-star-rail
CrypticOwl5503/sd-class-butterflies-32	CrypticOwl5503	2023-10-04T00:45:22Z	44	0	diffusers	[ "diffusers", "safetensors", "pytorch", "unconditional-image-generation", "diffusion-models-class", "license:mit", "diffusers:DDPMPipeline", "region:us" ]	unconditional-image-generation	2023-10-04T00:45:13Z	--- license: mit tags: - pytorch - diffusers - unconditional-image-generation - diffusion-models-class --- # Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class) This model is a diffusion model for unconditional image generation of cute 🦋. ## Usage ```python from diffusers import DDPMPipeline pipeline = DDPMPipeline.from_pretrained('CrypticOwl5503/sd-class-butterflies-32') image = pipeline().images[0] image ```
adamo1139/PS_AD_O365_Mistral_7B_02_GGUF	adamo1139	2023-10-04T00:20:20Z	0	0	null	[ "gguf", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2023-10-03T21:41:30Z	--- license: apache-2.0 --- GGUF q4_k_m quantization of QLoRA on semi-synthetic dataset with knowledge about PowerShell, Office 365 and Active Directory. Prompt format Pupil:{question}Teacher:{Response}
SinanAkkoyun/TinyLlama-1.1B-Chat-v0.3-exl2	SinanAkkoyun	2023-10-04T00:04:06Z	1	0	null	[ "license:apache-2.0", "region:us" ]	null	2023-10-04T00:01:33Z	--- license: apache-2.0 --- This is an EXL2 quantization of [PY007/TinyLlama-1.1B-Chat-v0.3](https://huggingface.co/PY007/TinyLlama-1.1B-Chat-v0.3) [3.0bpw](https://huggingface.co/SinanAkkoyun/TinyLlama-1.1B-Chat-v0.3-exl2/tree/3.0bpw) Check out the awesome [Exllama V2 repo](https://github.com/turboderp/exllamav2)
duytintruong/dqn-SpaceInvadersNoFrameskip-v4	duytintruong	2023-10-03T23:49:21Z	1	0	stable-baselines3	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-10-03T23:48:45Z	--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 692.50 +/- 156.29 name: mean_reward verified: false --- # DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga duytintruong -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga duytintruong -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga duytintruong ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
Rtrggf/Type-A	Rtrggf	2023-10-03T23:47:55Z	0	0	adapter-transformers	[ "adapter-transformers", "art", "text-to-video", "ae", "dataset:fka/awesome-chatgpt-prompts", "license:openrail", "region:us" ]	text-to-video	2023-10-03T23:35:04Z	--- license: openrail datasets: - fka/awesome-chatgpt-prompts language: - ae metrics: - accuracy library_name: adapter-transformers pipeline_tag: text-to-video tags: - art --- using System; using System.Drawing; using AForge.Video.FFMPEG; class Program { static void Main() { var videoWriter = new VideoFileWriter(); videoWriter.Open("output.mp4", 640, 480, 25, VideoCodec.MPEG4); for (int i = 0; i < 10; i++) { Bitmap image = (Bitmap)Image.FromFile($"image{i}.jpg"); videoWriter.WriteVideoFrame(image); image.Dispose(); } videoWriter.Close(); } }
codyreading/dreambooth-bear-lawn2	codyreading	2023-10-03T23:42:12Z	28	0	diffusers	[ "diffusers", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "dreambooth", "base_model:runwayml/stable-diffusion-v1-5", "base_model:finetune:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2023-10-03T23:34:35Z	--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 instance_prompt: A photo of sks stuffed animal tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - dreambooth inference: true --- # DreamBooth - codyreading/dreambooth-bear-lawn2 This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on A photo of sks stuffed animal using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. DreamBooth for the text encoder was enabled: False.
Joshua-shadow/kjkj	Joshua-shadow	2023-10-03T23:40:04Z	0	0	null	[ "license:other", "region:us" ]	null	2023-10-03T23:36:52Z	--- license: other license_name: me license_link: LICENSE ---
bdpc/resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t1.0_a1.0	bdpc	2023-10-03T23:23:57Z	199	0	transformers	[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T19:12:41Z	--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t1.0_a1.0 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t1.0_a1.0 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.7844 - Accuracy: 0.742 - Brier Loss: 0.4405 - Nll: 2.8680 - F1 Micro: 0.7420 - F1 Macro: 0.7411 - Ece: 0.1946 - Aurc: 0.1002 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 250 \| 2.7345 \| 0.153 \| 0.9327 \| 8.3371 \| 0.153 \| 0.1246 \| 0.0866 \| 0.7933 \| \| 2.6983 \| 2.0 \| 500 \| 2.4500 \| 0.4213 \| 0.8816 \| 4.7062 \| 0.4213 \| 0.3924 \| 0.3073 \| 0.4444 \| \| 2.6983 \| 3.0 \| 750 \| 1.7959 \| 0.5012 \| 0.7003 \| 3.3576 \| 0.5012 \| 0.4758 \| 0.1869 \| 0.3051 \| \| 1.7341 \| 4.0 \| 1000 \| 1.3637 \| 0.5985 \| 0.5511 \| 2.8818 \| 0.5985 \| 0.5868 \| 0.1005 \| 0.1935 \| \| 1.7341 \| 5.0 \| 1250 \| 1.1978 \| 0.6498 \| 0.4862 \| 2.7546 \| 0.6498 \| 0.6471 \| 0.0826 \| 0.1500 \| \| 1.0818 \| 6.0 \| 1500 \| 1.0812 \| 0.6853 \| 0.4364 \| 2.6325 \| 0.6853 \| 0.6845 \| 0.0522 \| 0.1217 \| \| 1.0818 \| 7.0 \| 1750 \| 1.0276 \| 0.7013 \| 0.4149 \| 2.5542 \| 0.7013 \| 0.7003 \| 0.0397 \| 0.1108 \| \| 0.7498 \| 8.0 \| 2000 \| 0.9724 \| 0.7133 \| 0.3944 \| 2.4773 \| 0.7133 \| 0.7129 \| 0.0505 \| 0.1040 \| \| 0.7498 \| 9.0 \| 2250 \| 0.9777 \| 0.7248 \| 0.3924 \| 2.4916 \| 0.7248 \| 0.7242 \| 0.0628 \| 0.0992 \| \| 0.5034 \| 10.0 \| 2500 \| 1.0027 \| 0.724 \| 0.3976 \| 2.4974 \| 0.724 \| 0.7250 \| 0.0751 \| 0.1032 \| \| 0.5034 \| 11.0 \| 2750 \| 0.9979 \| 0.729 \| 0.3913 \| 2.5344 \| 0.729 \| 0.7295 \| 0.0805 \| 0.0988 \| \| 0.3237 \| 12.0 \| 3000 \| 1.0553 \| 0.7192 \| 0.4075 \| 2.6242 \| 0.7192 \| 0.7193 \| 0.0963 \| 0.1072 \| \| 0.3237 \| 13.0 \| 3250 \| 1.1162 \| 0.7175 \| 0.4139 \| 2.6543 \| 0.7175 \| 0.7185 \| 0.1295 \| 0.1093 \| \| 0.2023 \| 14.0 \| 3500 \| 1.1259 \| 0.725 \| 0.4140 \| 2.6758 \| 0.7250 \| 0.7246 \| 0.1237 \| 0.1055 \| \| 0.2023 \| 15.0 \| 3750 \| 1.2728 \| 0.7115 \| 0.4381 \| 2.8308 \| 0.7115 \| 0.7147 \| 0.1464 \| 0.1168 \| \| 0.1264 \| 16.0 \| 4000 \| 1.2664 \| 0.7222 \| 0.4296 \| 2.8434 \| 0.7223 \| 0.7236 \| 0.1523 \| 0.1107 \| \| 0.1264 \| 17.0 \| 4250 \| 1.2620 \| 0.724 \| 0.4252 \| 2.7990 \| 0.724 \| 0.7252 \| 0.1563 \| 0.1066 \| \| 0.0802 \| 18.0 \| 4500 \| 1.3362 \| 0.727 \| 0.4293 \| 2.8642 \| 0.7270 \| 0.7267 \| 0.1653 \| 0.1090 \| \| 0.0802 \| 19.0 \| 4750 \| 1.3608 \| 0.7302 \| 0.4288 \| 2.7893 \| 0.7302 \| 0.7318 \| 0.1637 \| 0.1059 \| \| 0.0553 \| 20.0 \| 5000 \| 1.3757 \| 0.7308 \| 0.4303 \| 2.8861 \| 0.7308 \| 0.7300 \| 0.1670 \| 0.1073 \| \| 0.0553 \| 21.0 \| 5250 \| 1.4947 \| 0.7295 \| 0.4420 \| 2.8306 \| 0.7295 \| 0.7300 \| 0.1770 \| 0.1128 \| \| 0.0329 \| 22.0 \| 5500 \| 1.5338 \| 0.7265 \| 0.4416 \| 2.8729 \| 0.7265 \| 0.7273 \| 0.1808 \| 0.1097 \| \| 0.0329 \| 23.0 \| 5750 \| 1.5127 \| 0.7355 \| 0.4362 \| 2.8574 \| 0.7355 \| 0.7366 \| 0.1774 \| 0.1045 \| \| 0.0258 \| 24.0 \| 6000 \| 1.5189 \| 0.7352 \| 0.4360 \| 2.8435 \| 0.7353 \| 0.7344 \| 0.1784 \| 0.1030 \| \| 0.0258 \| 25.0 \| 6250 \| 1.5802 \| 0.7362 \| 0.4404 \| 2.8399 \| 0.7362 \| 0.7362 \| 0.1847 \| 0.1013 \| \| 0.0193 \| 26.0 \| 6500 \| 1.5869 \| 0.737 \| 0.4378 \| 2.8237 \| 0.737 \| 0.7362 \| 0.1846 \| 0.1022 \| \| 0.0193 \| 27.0 \| 6750 \| 1.6160 \| 0.7365 \| 0.4373 \| 2.7928 \| 0.7365 \| 0.7360 \| 0.1864 \| 0.1049 \| \| 0.014 \| 28.0 \| 7000 \| 1.6775 \| 0.7372 \| 0.4426 \| 2.9236 \| 0.7372 \| 0.7373 \| 0.1909 \| 0.1039 \| \| 0.014 \| 29.0 \| 7250 \| 1.6391 \| 0.736 \| 0.4370 \| 2.8717 \| 0.736 \| 0.7358 \| 0.1905 \| 0.0999 \| \| 0.0132 \| 30.0 \| 7500 \| 1.6804 \| 0.7355 \| 0.4434 \| 2.8397 \| 0.7355 \| 0.7360 \| 0.1903 \| 0.1067 \| \| 0.0132 \| 31.0 \| 7750 \| 1.6809 \| 0.738 \| 0.4386 \| 2.8853 \| 0.738 \| 0.7387 \| 0.1920 \| 0.1015 \| \| 0.0121 \| 32.0 \| 8000 \| 1.6953 \| 0.734 \| 0.4443 \| 2.8451 \| 0.734 \| 0.7342 \| 0.1961 \| 0.1013 \| \| 0.0121 \| 33.0 \| 8250 \| 1.7184 \| 0.7425 \| 0.4344 \| 2.8180 \| 0.7425 \| 0.7423 \| 0.1910 \| 0.1014 \| \| 0.0098 \| 34.0 \| 8500 \| 1.7151 \| 0.735 \| 0.4445 \| 2.8532 \| 0.735 \| 0.7337 \| 0.1952 \| 0.1000 \| \| 0.0098 \| 35.0 \| 8750 \| 1.7781 \| 0.7338 \| 0.4484 \| 2.8133 \| 0.7338 \| 0.7351 \| 0.1999 \| 0.1052 \| \| 0.0086 \| 36.0 \| 9000 \| 1.7540 \| 0.7372 \| 0.4443 \| 2.8388 \| 0.7372 \| 0.7388 \| 0.1954 \| 0.1039 \| \| 0.0086 \| 37.0 \| 9250 \| 1.7744 \| 0.738 \| 0.4474 \| 2.8600 \| 0.738 \| 0.7390 \| 0.1953 \| 0.1057 \| \| 0.0079 \| 38.0 \| 9500 \| 1.7446 \| 0.7368 \| 0.4417 \| 2.8485 \| 0.7367 \| 0.7374 \| 0.1972 \| 0.1016 \| \| 0.0079 \| 39.0 \| 9750 \| 1.7700 \| 0.739 \| 0.4398 \| 2.8826 \| 0.739 \| 0.7395 \| 0.1970 \| 0.1023 \| \| 0.0076 \| 40.0 \| 10000 \| 1.7896 \| 0.7368 \| 0.4442 \| 2.8449 \| 0.7367 \| 0.7376 \| 0.1988 \| 0.1033 \| \| 0.0076 \| 41.0 \| 10250 \| 1.7435 \| 0.7402 \| 0.4387 \| 2.8390 \| 0.7402 \| 0.7405 \| 0.1926 \| 0.1031 \| \| 0.0074 \| 42.0 \| 10500 \| 1.7837 \| 0.7338 \| 0.4470 \| 2.8191 \| 0.7338 \| 0.7339 \| 0.2018 \| 0.1035 \| \| 0.0074 \| 43.0 \| 10750 \| 1.8015 \| 0.7392 \| 0.4427 \| 2.8093 \| 0.7392 \| 0.7401 \| 0.1981 \| 0.1017 \| \| 0.0061 \| 44.0 \| 11000 \| 1.8155 \| 0.739 \| 0.4449 \| 2.8333 \| 0.739 \| 0.7406 \| 0.1983 \| 0.1022 \| \| 0.0061 \| 45.0 \| 11250 \| 1.7958 \| 0.7392 \| 0.4426 \| 2.8161 \| 0.7392 \| 0.7385 \| 0.1963 \| 0.1039 \| \| 0.0059 \| 46.0 \| 11500 \| 1.8089 \| 0.7422 \| 0.4411 \| 2.8174 \| 0.7422 \| 0.7422 \| 0.1955 \| 0.1011 \| \| 0.0059 \| 47.0 \| 11750 \| 1.8125 \| 0.743 \| 0.4386 \| 2.8184 \| 0.743 \| 0.7435 \| 0.1939 \| 0.1012 \| \| 0.0053 \| 48.0 \| 12000 \| 1.8004 \| 0.7372 \| 0.4432 \| 2.8413 \| 0.7372 \| 0.7371 \| 0.1995 \| 0.1023 \| \| 0.0053 \| 49.0 \| 12250 \| 1.8075 \| 0.7405 \| 0.4392 \| 2.8569 \| 0.7405 \| 0.7397 \| 0.1962 \| 0.1015 \| \| 0.0055 \| 50.0 \| 12500 \| 1.7844 \| 0.742 \| 0.4405 \| 2.8680 \| 0.7420 \| 0.7411 \| 0.1946 \| 0.1002 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3
gyaan/ppo-Huggy	gyaan	2023-10-03T23:21:40Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]	reinforcement-learning	2023-10-03T23:21:35Z	--- library_name: ml-agents tags: - Huggy - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Huggy --- # ppo Agent playing Huggy This is a trained model of a ppo agent playing Huggy using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: gyaan/ppo-Huggy 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
zkdeng/swin-tiny-patch4-window7-224-finetuned-eurosat	zkdeng	2023-10-03T23:18:32Z	213	0	transformers	[ "transformers", "pytorch", "swin", "image-classification", "generated_from_trainer", "base_model:microsoft/swin-tiny-patch4-window7-224", "base_model:finetune:microsoft/swin-tiny-patch4-window7-224", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T22:41:35Z	--- license: apache-2.0 base_model: microsoft/swin-tiny-patch4-window7-224 tags: - generated_from_trainer metrics: - accuracy model-index: - name: swin-tiny-patch4-window7-224-finetuned-eurosat results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # swin-tiny-patch4-window7-224-finetuned-eurosat This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2188 - Accuracy: 0.92 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.6077 \| 0.96 \| 12 \| 0.3408 \| 0.895 \| \| 0.3469 \| 2.0 \| 25 \| 0.2188 \| 0.92 \| \| 0.2627 \| 2.88 \| 36 \| 0.2183 \| 0.915 \| ### Framework versions - Transformers 4.34.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0
jonale/q-FrozenLake-v1-4x4-noSlippery	jonale	2023-10-03T23:15:51Z	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-10-03T23:15:48Z	--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="jonale/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
sd-concepts-library/ahx-beta-51c9767	sd-concepts-library	2023-10-03T23:15:13Z	0	0	null	[ "license:mit", "region:us" ]	null	2023-10-03T23:15:10Z	--- license: mit --- ### ahx-beta-51c9767 on Stable Diffusion This is the `<ahx-beta-51c9767>` concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the [Stable Conceptualizer](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_conceptualizer_inference.ipynb) notebook. You can also train your own concepts and load them into the concept libraries using [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb). Here is the new concept you will be able to use as a `style`: ![<ahx-beta-51c9767> 0](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/5.jpeg) ![<ahx-beta-51c9767> 1](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/7.jpeg) ![<ahx-beta-51c9767> 2](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/2.jpeg) ![<ahx-beta-51c9767> 3](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/0.jpeg) ![<ahx-beta-51c9767> 4](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/1.jpeg) ![<ahx-beta-51c9767> 5](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/4.jpeg) ![<ahx-beta-51c9767> 6](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/6.jpeg) ![<ahx-beta-51c9767> 7](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/3.jpeg)
Adrian101-hnd/q-FrozenLake-v1-4x4-noSlippery	Adrian101-hnd	2023-10-03T22:51:51Z	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-10-03T22:51:48Z	--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="Adrian101-hnd/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
YuvanKumar/ppo-LunarLander-v2	YuvanKumar	2023-10-03T22:49:01Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2023-10-03T22:48:43Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 280.16 +/- 13.38 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
ipipan/nlpre_spacy_nkjp_pl-core-news-lg_nkjp-by-name	ipipan	2023-10-03T22:36:55Z	0	0	null	[ "region:us" ]	null	2023-09-29T17:04:31Z	# Model description - Morphosyntactic analyzer: Spacy - Tagset: NKJP - Embedding vectors: pl-core-news-lg - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_spacy_nkjp_pl-core-news-lg_nkjp-by-name ``` ## Load model ``` import spacy model_name = './nlpre_spacy_nkjp_pl-core-news-lg_nkjp-by-name' model_upos = spacy.load(model_name + '/upos') model_xpos = spacy.load(model_name + '/xpos+lemma') ```
ipipan/nlpre_spacy_ud_pl-core-news-lg_nkjp-by-name	ipipan	2023-10-03T22:33:59Z	0	0	null	[ "region:us" ]	null	2023-09-29T16:38:32Z	# Model description - Morphosyntactic analyzer: Spacy - Tagset: UD - Embedding vectors: pl-core-news-lg - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_spacy_ud_pl-core-news-lg_nkjp-by-name ``` ## Load model ``` import spacy model_name = './nlpre_spacy_ud_pl-core-news-lg_nkjp-by-name/model-best' model = spacy.load(model_name) ```
ipipan/nlpre_spacy_ud_transformer_nkjp-by-type	ipipan	2023-10-03T22:33:42Z	0	0	null	[ "region:us" ]	null	2023-09-29T15:51:30Z	# Model description - Morphosyntactic analyzer: Spacy - Tagset: UD - Embedding vectors: Transformer - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_spacy_ud_transformer_nkjp-by-type ``` ## Load model ``` import spacy model_name = './nlpre_spacy_ud_transformer_nkjp-by-type/model-best' model = spacy.load(model_name) ```
LoneStriker/airoboros-mistral2.2-7b-8.0bpw-h6-exl2	LoneStriker	2023-10-03T22:20:40Z	5	0	transformers	[ "transformers", "pytorch", "mistral", "text-generation", "llama-2", "instruct", "finetune", "alpaca", "gpt4", "synthetic data", "distillation", "en", "dataset:jondurbin/airoboros-2.2.1", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-10-03T20:35:02Z	--- base_model: mistralai/Mistral-7b-V0.1 tags: - llama-2 - instruct - finetune - alpaca - gpt4 - synthetic data - distillation datasets: - jondurbin/airoboros-2.2.1 model-index: - name: airoboros2.2-mistral-7b results: [] license: mit language: - en --- Mistral trained with the airoboros dataset! ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/sbN_PCdxO_LV0xpFGA_St.png) Actual dataset is airoboros 2.2, but it seems to have been replaced on hf with 2.2.1. Prompt Format: ``` USER: <prompt> ASSISTANT: ``` TruthfulQA: ``` hf-causal-experimental (pretrained=/home/teknium/dakota/lm-evaluation-harness/airoboros2.2-mistral/,dtype=float16), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8 \| Task \|Version\|Metric\|Value \| \|Stderr\| \|-------------\|------:\|------\|-----:\|---\|-----:\| \|truthfulqa_mc\| 1\|mc1 \|0.3562\|± \|0.0168\| \| \| \|mc2 \|0.5217\|± \|0.0156\| ``` Wandb training charts: https://wandb.ai/teknium1/airoboros-mistral-7b/runs/airoboros-mistral-1?workspace=user-teknium1 More info to come
ipipan/nlpre_combo_ud_herBERT_nkjp-by-name	ipipan	2023-10-03T22:16:22Z	0	0	null	[ "region:us" ]	null	2023-09-29T15:35:38Z	# Model description - Morphosyntactic analyzer: COMBO - Tagset: UD - Embedding vectors: HerBERT (wiki) - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_ud_herBERT_nkjp-by-name ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_ud_herBERT_nkjp-by-name' model = COMBO.from_pretrained(model_name) ```
ipipan/nlpre_combo_ud_herBERT_nkjp-by-type	ipipan	2023-10-03T22:15:55Z	0	0	null	[ "region:us" ]	null	2023-09-29T15:35:27Z	# Model description - Morphosyntactic analyzer: COMBO - Tagset: UD - Embedding vectors: HerBERT (wiki) - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_ud_herBERT_nkjp-by-type ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_ud_herBERT_nkjp-by-type' model = COMBO.from_pretrained(model_name) ```
ipipan/nlpre_combo_nkjp_herBERT_nkjp-by-type	ipipan	2023-10-03T22:15:26Z	0	0	null	[ "region:us" ]	null	2023-09-29T15:34:36Z	# Model description - Morphosyntactic analyzer: COMBO - Tagset: NKJP - Embedding vectors: HerBERT (wiki) - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_nkjp_herBERT_nkjp-by-type ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_nkjp_herBERT_nkjp-by-type' model = COMBO.from_pretrained(model_name) ```
ipipan/nlpre_combo_nkjp_herBERT_nkjp-by-name	ipipan	2023-10-03T22:14:57Z	0	0	null	[ "region:us" ]	null	2023-09-29T15:34:23Z	# Model description - Morphosyntactic analyzer: COMBO - Tagset: NKJP - Embedding vectors: HerBERT (wiki) - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_nkjp_herBERT_nkjp-by-name ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_nkjp_herBERT_nkjp-by-name' model = COMBO.from_pretrained(model_name) ```
ipipan/nlpre_combo_nkjp_fasttext_nkjp-by-type	ipipan	2023-10-03T22:13:45Z	0	0	null	[ "region:us" ]	null	2023-09-29T14:40:21Z	# Model description - Morphosyntactic analyzer: COMBO - Tagset: NKJP - Embedding vectors: Fasttext (wiki) - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_nkjp_fasttext_nkjp-by-type ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_nkjp_fasttext_nkjp-by-type' model = COMBO.from_pretrained(model_name) ```
ipipan/nlpre_combo_ud_fasttext_nkjp-by-name	ipipan	2023-10-03T22:12:54Z	0	0	null	[ "region:us" ]	null	2023-09-29T14:39:43Z	# Model description - Morphosyntactic analyzer: COMBO - Tagset: UD - Embedding vectors: Fasttext (wiki) - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_ud_fasttext_nkjp-by-name ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_ud_fasttext_nkjp-by-name' model = COMBO.from_pretrained(model_name) ```
ipipan/nlpre_combo_ud_fasttext_nkjp-by-type	ipipan	2023-10-03T22:12:22Z	0	0	null	[ "region:us" ]	null	2023-09-29T14:39:23Z	# Model description - Morphosyntactic analyzer: COMBO - Tagset: UD - Embedding vectors: Fasttext (wiki) - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_ud_fasttext_nkjp-by-type ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_ud_fasttext_nkjp-by-type' model = COMBO.from_pretrained(model_name) ```
ipipan/nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-type	ipipan	2023-10-03T22:05:45Z	0	0	null	[ "region:us" ]	null	2023-09-29T09:08:44Z	# Model description - Morphosyntactic analyzer: Trankit - Tagset: NKJP - Embedding vectors: XLM-RoBERTa-Base - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-type ``` ## Load model ``` import trankit model_path = './nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-type' trankit.verify_customized_pipeline( category='customized-mwt', # pipeline category save_dir=model_path, # directory used for saving models in previous steps embedding_name='xlm-roberta-base' # embedding version that we use for training our customized pipeline, by default, it is `xlm-roberta-base` ) model = trankit.Pipeline(lang='customized-mwt', cache_dir=model_path, embedding='xlm-roberta-base') ```
ipipan/nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-name	ipipan	2023-10-03T22:05:05Z	0	0	null	[ "region:us" ]	null	2023-09-29T09:08:28Z	# Model description - Morphosyntactic analyzer: Trankit - Tagset: NKJP - Embedding vectors: XLM-RoBERTa-Base - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-name ``` ## Load model ``` import trankit model_path = './nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-name' trankit.verify_customized_pipeline( category='customized-mwt', # pipeline category save_dir=model_path, # directory used for saving models in previous steps embedding_name='xlm-roberta-base' # embedding version that we use for training our customized pipeline, by default, it is `xlm-roberta-base` ) model = trankit.Pipeline(lang='customized-mwt', cache_dir=model_path, embedding='xlm-roberta-base') ```
SkunkworksAI/Mistralic-7B-1	SkunkworksAI	2023-10-03T22:04:49Z	52	26	transformers	[ "transformers", "pytorch", "endpoints_compatible", "region:us" ]	null	2023-09-29T23:45:09Z	<p><h1> 🦾 Mistralic-7B-1 🦾 </h1></p> Special thanks to Together Compute for sponsoring Skunkworks with compute! INFERENCE ``` import torch from transformers import AutoModelForCausalLM, AutoTokenizer torch.set_default_device('cuda') system_prompt = "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n" system_no_input_prompt = "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n" def generate_prompt(instruction, input=None): if input: prompt = f"### System:\n{system_prompt}\n\n" else: prompt = f"### System:\n{system_no_input_prompt}\n\n" prompt += f"### Instruction:\n{instruction}\n\n" if input: prompt += f"### Input:\n{input}\n\n" return prompt + """### Response:\n""" device = "cuda" model = AutoModelForCausalLM.from_pretrained("SkunkworksAI/Mistralic-7B-1") tokenizer = AutoTokenizer.from_pretrained("SkunkworksAI/Mistralic-7B-1") while True: instruction = input("Enter Instruction: ") instruction = generate_prompt(instruction) inputs = tokenizer(instruction, return_tensors="pt", return_attention_mask=False) outputs = model.generate(inputs, max_length=1000, do_sample=True, temperature=0.01, use_cache=True, eos_token_id=tokenizer.eos_token_id) text = tokenizer.batch_decode(outputs)[0] print(text) ``` EVALUATION** ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b7e345f92b20f7a38bf47a/ycpNhdGZHGbai_wslT2Bg.png) Average: 0.72157 For comparison: mistralai/Mistral-7B-v0.1 scores 0.7116 mistralai/Mistral-7B-Instruct-v0.1 scores 0.6794
ipipan/nlpre_trankit_ud_xlm-roberta-base_nkjp-by-name	ipipan	2023-10-03T22:04:29Z	0	0	null	[ "region:us" ]	null	2023-09-29T09:00:18Z	# Model description - Morphosyntactic analyzer: Trankit - Tagset: UD - Embedding vectors: XLM-RoBERTa-Base - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_trankit_ud_xlm-roberta-base_nkjp-by-name ``` ## Load model ``` import trankit model_path = './nlpre_trankit_ud_xlm-roberta-base_nkjp-by-name' trankit.verify_customized_pipeline( category='customized-mwt', # pipeline category save_dir=model_path, # directory used for saving models in previous steps embedding_name='xlm-roberta-base' # embedding version that we use for training our customized pipeline, by default, it is `xlm-roberta-base` ) model = trankit.Pipeline(lang='customized-mwt', cache_dir=model_path, embedding='xlm-roberta-base') ```
LoneStriker/airoboros-mistral2.2-7b-6.0bpw-h6-exl2	LoneStriker	2023-10-03T22:02:52Z	5	0	transformers	[ "transformers", "pytorch", "mistral", "text-generation", "llama-2", "instruct", "finetune", "alpaca", "gpt4", "synthetic data", "distillation", "en", "dataset:jondurbin/airoboros-2.2.1", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-10-03T20:34:58Z	--- base_model: mistralai/Mistral-7b-V0.1 tags: - llama-2 - instruct - finetune - alpaca - gpt4 - synthetic data - distillation datasets: - jondurbin/airoboros-2.2.1 model-index: - name: airoboros2.2-mistral-7b results: [] license: mit language: - en --- Mistral trained with the airoboros dataset! ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/sbN_PCdxO_LV0xpFGA_St.png) Actual dataset is airoboros 2.2, but it seems to have been replaced on hf with 2.2.1. Prompt Format: ``` USER: <prompt> ASSISTANT: ``` TruthfulQA: ``` hf-causal-experimental (pretrained=/home/teknium/dakota/lm-evaluation-harness/airoboros2.2-mistral/,dtype=float16), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8 \| Task \|Version\|Metric\|Value \| \|Stderr\| \|-------------\|------:\|------\|-----:\|---\|-----:\| \|truthfulqa_mc\| 1\|mc1 \|0.3562\|± \|0.0168\| \| \| \|mc2 \|0.5217\|± \|0.0156\| ``` Wandb training charts: https://wandb.ai/teknium1/airoboros-mistral-7b/runs/airoboros-mistral-1?workspace=user-teknium1 More info to come
NAB1108/News_Recommendation	NAB1108	2023-10-03T22:00:57Z	3	0	sentence-transformers	[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]	text-classification	2023-10-03T14:22:20Z	--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # NAB1108/News_Recommendation This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Usage To use this model for inference, first install the SetFit library: ```bash python -m pip install setfit ``` You can then run inference as follows: ```python from setfit import SetFitModel # Download from Hub and run inference model = SetFitModel.from_pretrained("NAB1108/News_Recommendation") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```
fernandohf/model_en_pt	fernandohf	2023-10-03T21:52:04Z	3	0	transformers	[ "transformers", "pytorch", "t5", "text2text-generation", "generated_from_trainer", "dataset:opus_books", "base_model:google-t5/t5-small", "base_model:finetune:google-t5/t5-small", "license:apache-2.0", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2023-10-03T20:15:33Z	--- license: apache-2.0 base_model: t5-small tags: - generated_from_trainer datasets: - opus_books metrics: - bleu model-index: - name: model_en_pt results: - task: name: Sequence-to-sequence Language Modeling type: text2text-generation dataset: name: opus_books type: opus_books config: en-pt split: train args: en-pt metrics: - name: Bleu type: bleu value: 1.0547 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # model_en_pt This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus_books dataset. It achieves the following results on the evaluation set: - Loss: 3.1561 - Bleu: 1.0547 - Gen Len: 17.8369 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Bleu \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\|:-------:\| \| No log \| 1.0 \| 79 \| 3.4923 \| 1.2907 \| 17.2624 \| \| No log \| 2.0 \| 158 \| 3.3099 \| 0.8388 \| 17.2482 \| \| No log \| 3.0 \| 237 \| 3.2192 \| 0.8526 \| 17.7021 \| \| No log \| 4.0 \| 316 \| 3.1709 \| 0.9618 \| 17.8298 \| \| No log \| 5.0 \| 395 \| 3.1561 \| 1.0547 \| 17.8369 \| ### Framework versions - Transformers 4.34.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0
ipipan/nlpre_trankit_ud_xlm-roberta-large_pdb	ipipan	2023-10-03T21:49:52Z	0	0	null	[ "region:us" ]	null	2023-09-29T08:54:04Z	# Model description - Morphosyntactic analyzer: Trankit - Tagset: UD - Embedding vectors: XLM-RoBERTa-Large - Dataset: PDB (http://git.nlp.ipipan.waw.pl/alina/PDBUD/tree/master/PDB-UD/PDB-UD) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_trankit_ud_xlm-roberta-large_pdb ``` ## Load model ``` import trankit model_path = './nlpre_trankit_ud_xlm-roberta-large_pdb' trankit.verify_customized_pipeline( category='customized-mwt', # pipeline category save_dir=model_path, # directory used for saving models in previous steps embedding_name='xlm-roberta-large' # embedding version that we use for training our customized pipeline, by default, it is `xlm-roberta-base` ) model = trankit.Pipeline(lang='customized-mwt', cache_dir=model_path, embedding='xlm-roberta-large') ```
ipipan/nlpre_trankit_ud_xlm-roberta-large_nkjp-by-type	ipipan	2023-10-03T21:48:38Z	0	0	null	[ "region:us" ]	null	2023-09-28T15:24:37Z	# Model description - Morphosyntactic analyzer: Trankit - Tagset: UD - Embedding vectors: XLM-RoBERTa-Large - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_trankit_ud_xlm-roberta-large_nkjp-by-type ``` ## Load model ``` import trankit model_path = './nlpre_trankit_ud_xlm-roberta-large_nkjp-by-type' trankit.verify_customized_pipeline( category='customized-mwt', # pipeline category save_dir=model_path, # directory used for saving models in previous steps embedding_name='xlm-roberta-large' # embedding version that we use for training our customized pipeline, by default, it is `xlm-roberta-base` ) model = trankit.Pipeline(lang='customized-mwt', cache_dir=model_path, embedding='xlm-roberta-large') ```
Safeer143/bert-finetuned-squad	Safeer143	2023-10-03T21:36:31Z	122	0	transformers	[ "transformers", "pytorch", "bert", "question-answering", "generated_from_trainer", "dataset:squad", "base_model:google-bert/bert-base-cased", "base_model:finetune:google-bert/bert-base-cased", "license:apache-2.0", "endpoints_compatible", "region:us" ]	question-answering	2023-10-01T23:27:03Z	--- license: apache-2.0 base_model: bert-base-cased tags: - generated_from_trainer datasets: - squad model-index: - name: bert-finetuned-squad results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # bert-finetuned-squad This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the squad dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.33.0 - Pytorch 2.0.0 - Datasets 2.1.0 - Tokenizers 0.13.3
raulkw/kw-prop-classifier	raulkw	2023-10-03T21:35:50Z	193	0	transformers	[ "transformers", "pytorch", "tensorboard", "vit", "image-classification", "huggingpics", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T21:35:42Z	--- tags: - image-classification - pytorch - huggingpics metrics: - accuracy model-index: - name: kw-prop-classifier results: - task: name: Image Classification type: image-classification metrics: - name: Accuracy type: accuracy value: 0.6266666650772095 --- # kw-prop-classifier Autogenerated by HuggingPics🤗🖼️ Create your own image classifier for anything by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb). Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics). ## Example Images #### Bathroom ![Bathroom](images/Bathroom.jpg) #### Bedroom ![Bedroom](images/Bedroom.jpg) #### Dining Room ![Dining Room](images/Dining_Room.jpg) #### House Amenities ![House Amenities](images/House_Amenities.jpg) #### House Facade ![House Facade](images/House_Facade.jpg) #### House Hallway ![House Hallway](images/House_Hallway.jpg) #### House Interior ![House Interior](images/House_Interior.jpg) #### House Lobby ![House Lobby](images/House_Lobby.jpg) #### Kitchen ![Kitchen](images/Kitchen.jpg) #### Living Room ![Living Room](images/Living_Room.jpg)
Chunwei94/souffle-ae	Chunwei94	2023-10-03T20:57:19Z	0	0	null	[ "onnx", "region:us" ]	null	2023-10-02T17:37:00Z	# For models with python bindings, please first run `pip install .` in the corresponding directory. docker run -it --name=sirius_test --gpus all --privileged sunqianqi/sirius:mlsys_ae /bin/bash
EladAssia/poca-SoccerTwos	EladAssia	2023-10-03T20:32:53Z	37	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]	reinforcement-learning	2023-10-03T20:32:17Z	--- library_name: ml-agents tags: - SoccerTwos - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SoccerTwos --- # poca Agent playing SoccerTwos This is a trained model of a poca agent playing SoccerTwos using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: EladAssia/poca-SoccerTwos 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
ArtCad98/nlp_covid_tweets	ArtCad98	2023-10-03T20:32:20Z	14	0	transformers	[ "transformers", "pytorch", "bert", "fill-mask", "generated_from_trainer", "base_model:finiteautomata/beto-emotion-analysis", "base_model:finetune:finiteautomata/beto-emotion-analysis", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2023-09-12T14:42:25Z	--- base_model: finiteautomata/beto-emotion-analysis tags: - generated_from_trainer model-index: - name: nlp_covid_tweets results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # nlp_covid_tweets This model is a fine-tuned version of [finiteautomata/beto-emotion-analysis](https://huggingface.co/finiteautomata/beto-emotion-analysis) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.1415 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 1.406 \| 1.0 \| 6705 \| 1.3510 \| \| 1.2393 \| 2.0 \| 13410 \| 1.2051 \| \| 1.1622 \| 3.0 \| 20115 \| 1.1410 \| ### Framework versions - Transformers 4.34.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0
Terps/whisper-small-minds14-enUS	Terps	2023-10-03T20:05:58Z	77	0	transformers	[ "transformers", "pytorch", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dataset:PolyAI/minds14", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-10-03T19:07:18Z	--- license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer datasets: - PolyAI/minds14 metrics: - wer model-index: - name: whisper-small-minds14-enUS results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: PolyAI/minds14 type: PolyAI/minds14 config: en-US split: train args: en-US metrics: - name: Wer type: wer value: 28.158205430932703 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper-small-minds14-enUS This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set: - Loss: 0.5829 - Wer Ortho: 27.8223 - Wer: 28.1582 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant_with_warmup - lr_scheduler_warmup_steps: 50 - training_steps: 500 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer Ortho \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:---------:\|:-------:\| \| 0.0003 \| 17.86 \| 500 \| 0.5829 \| 27.8223 \| 28.1582 \| ### Framework versions - Transformers 4.34.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0
bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.9	bdpc	2023-10-03T19:57:33Z	195	0	transformers	[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T19:42:19Z	--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.9 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.9 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.8672 - Accuracy: 0.71 - Brier Loss: 0.4047 - Nll: 2.1924 - F1 Micro: 0.7100 - F1 Macro: 0.6463 - Ece: 0.2420 - Aurc: 0.1050 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 13 \| 2.1239 \| 0.16 \| 0.8967 \| 8.4233 \| 0.16 \| 0.1062 \| 0.2101 \| 0.8304 \| \| No log \| 2.0 \| 26 \| 2.1201 \| 0.14 \| 0.8961 \| 8.2220 \| 0.14 \| 0.0876 \| 0.1970 \| 0.8491 \| \| No log \| 3.0 \| 39 \| 2.0724 \| 0.215 \| 0.8865 \| 6.2039 \| 0.2150 \| 0.1169 \| 0.2432 \| 0.7837 \| \| No log \| 4.0 \| 52 \| 2.0291 \| 0.185 \| 0.8773 \| 5.6169 \| 0.185 \| 0.0792 \| 0.2329 \| 0.7651 \| \| No log \| 5.0 \| 65 \| 1.9592 \| 0.215 \| 0.8614 \| 6.0237 \| 0.2150 \| 0.0835 \| 0.2493 \| 0.7373 \| \| No log \| 6.0 \| 78 \| 1.9039 \| 0.205 \| 0.8483 \| 5.9575 \| 0.205 \| 0.0619 \| 0.2493 \| 0.7526 \| \| No log \| 7.0 \| 91 \| 1.8651 \| 0.26 \| 0.8381 \| 5.6215 \| 0.26 \| 0.1490 \| 0.2663 \| 0.6747 \| \| No log \| 8.0 \| 104 \| 1.8342 \| 0.225 \| 0.8311 \| 5.7631 \| 0.225 \| 0.1071 \| 0.2425 \| 0.6919 \| \| No log \| 9.0 \| 117 \| 1.8057 \| 0.31 \| 0.8218 \| 5.2969 \| 0.31 \| 0.2118 \| 0.2795 \| 0.6489 \| \| No log \| 10.0 \| 130 \| 1.5737 \| 0.46 \| 0.7277 \| 5.1748 \| 0.46 \| 0.2853 \| 0.3279 \| 0.2977 \| \| No log \| 11.0 \| 143 \| 1.5629 \| 0.415 \| 0.7331 \| 4.8259 \| 0.415 \| 0.2846 \| 0.2924 \| 0.3880 \| \| No log \| 12.0 \| 156 \| 1.5283 \| 0.45 \| 0.7135 \| 4.0012 \| 0.45 \| 0.3122 \| 0.3298 \| 0.3197 \| \| No log \| 13.0 \| 169 \| 1.4200 \| 0.51 \| 0.6674 \| 3.9849 \| 0.51 \| 0.3400 \| 0.3259 \| 0.2549 \| \| No log \| 14.0 \| 182 \| 1.4334 \| 0.535 \| 0.6710 \| 3.7006 \| 0.535 \| 0.3840 \| 0.3291 \| 0.2584 \| \| No log \| 15.0 \| 195 \| 1.4306 \| 0.45 \| 0.6854 \| 3.8260 \| 0.45 \| 0.3120 \| 0.3055 \| 0.4297 \| \| No log \| 16.0 \| 208 \| 1.3175 \| 0.585 \| 0.6174 \| 3.3484 \| 0.585 \| 0.4401 \| 0.3406 \| 0.1916 \| \| No log \| 17.0 \| 221 \| 1.2680 \| 0.57 \| 0.5998 \| 3.1408 \| 0.57 \| 0.4356 \| 0.2903 \| 0.2136 \| \| No log \| 18.0 \| 234 \| 1.2605 \| 0.58 \| 0.6020 \| 3.2085 \| 0.58 \| 0.4711 \| 0.2915 \| 0.2355 \| \| No log \| 19.0 \| 247 \| 1.2292 \| 0.61 \| 0.5791 \| 3.0633 \| 0.61 \| 0.5021 \| 0.2929 \| 0.2082 \| \| No log \| 20.0 \| 260 \| 1.3872 \| 0.54 \| 0.6604 \| 3.2778 \| 0.54 \| 0.4604 \| 0.3284 \| 0.3506 \| \| No log \| 21.0 \| 273 \| 1.1646 \| 0.625 \| 0.5520 \| 2.8539 \| 0.625 \| 0.5193 \| 0.2828 \| 0.1885 \| \| No log \| 22.0 \| 286 \| 1.1565 \| 0.655 \| 0.5438 \| 2.6915 \| 0.655 \| 0.5437 \| 0.3430 \| 0.1549 \| \| No log \| 23.0 \| 299 \| 1.1041 \| 0.625 \| 0.5298 \| 2.9930 \| 0.625 \| 0.5241 \| 0.2423 \| 0.1906 \| \| No log \| 24.0 \| 312 \| 1.0448 \| 0.685 \| 0.4895 \| 2.8196 \| 0.685 \| 0.5846 \| 0.2701 \| 0.1411 \| \| No log \| 25.0 \| 325 \| 1.0623 \| 0.695 \| 0.4904 \| 2.6903 \| 0.695 \| 0.6086 \| 0.2762 \| 0.1435 \| \| No log \| 26.0 \| 338 \| 0.9872 \| 0.695 \| 0.4607 \| 2.6336 \| 0.695 \| 0.5953 \| 0.2728 \| 0.1180 \| \| No log \| 27.0 \| 351 \| 0.9789 \| 0.705 \| 0.4580 \| 2.6326 \| 0.705 \| 0.6127 \| 0.2579 \| 0.1171 \| \| No log \| 28.0 \| 364 \| 1.0033 \| 0.685 \| 0.4707 \| 2.5747 \| 0.685 \| 0.5906 \| 0.2747 \| 0.1291 \| \| No log \| 29.0 \| 377 \| 1.0152 \| 0.7 \| 0.4789 \| 2.4333 \| 0.7 \| 0.6260 \| 0.2951 \| 0.1739 \| \| No log \| 30.0 \| 390 \| 1.0107 \| 0.715 \| 0.4684 \| 2.5194 \| 0.715 \| 0.6401 \| 0.3197 \| 0.1389 \| \| No log \| 31.0 \| 403 \| 0.9511 \| 0.69 \| 0.4445 \| 2.5648 \| 0.69 \| 0.6131 \| 0.2648 \| 0.1298 \| \| No log \| 32.0 \| 416 \| 0.9586 \| 0.735 \| 0.4448 \| 2.3342 \| 0.735 \| 0.6578 \| 0.2941 \| 0.1275 \| \| No log \| 33.0 \| 429 \| 1.0010 \| 0.73 \| 0.4625 \| 2.4748 \| 0.7300 \| 0.6613 \| 0.3307 \| 0.1202 \| \| No log \| 34.0 \| 442 \| 0.9481 \| 0.71 \| 0.4361 \| 2.4986 \| 0.7100 \| 0.6456 \| 0.2856 \| 0.1228 \| \| No log \| 35.0 \| 455 \| 0.9190 \| 0.69 \| 0.4323 \| 2.6586 \| 0.69 \| 0.6265 \| 0.2538 \| 0.1250 \| \| No log \| 36.0 \| 468 \| 0.9226 \| 0.715 \| 0.4350 \| 2.2652 \| 0.715 \| 0.6507 \| 0.2868 \| 0.1328 \| \| No log \| 37.0 \| 481 \| 0.9017 \| 0.725 \| 0.4182 \| 2.5141 \| 0.7250 \| 0.6590 \| 0.2547 \| 0.1013 \| \| No log \| 38.0 \| 494 \| 0.9092 \| 0.72 \| 0.4218 \| 2.5171 \| 0.72 \| 0.6495 \| 0.2677 \| 0.1055 \| \| 1.0958 \| 39.0 \| 507 \| 0.9093 \| 0.71 \| 0.4221 \| 2.6479 \| 0.7100 \| 0.6456 \| 0.2567 \| 0.1185 \| \| 1.0958 \| 40.0 \| 520 \| 0.8926 \| 0.71 \| 0.4204 \| 2.3785 \| 0.7100 \| 0.6522 \| 0.2396 \| 0.1153 \| \| 1.0958 \| 41.0 \| 533 \| 0.8928 \| 0.715 \| 0.4157 \| 2.5719 \| 0.715 \| 0.6487 \| 0.2708 \| 0.1067 \| \| 1.0958 \| 42.0 \| 546 \| 0.8967 \| 0.715 \| 0.4247 \| 2.6422 \| 0.715 \| 0.6495 \| 0.2525 \| 0.1174 \| \| 1.0958 \| 43.0 \| 559 \| 0.8773 \| 0.695 \| 0.4116 \| 2.5548 \| 0.695 \| 0.6400 \| 0.2491 \| 0.1142 \| \| 1.0958 \| 44.0 \| 572 \| 0.8660 \| 0.71 \| 0.4036 \| 2.2950 \| 0.7100 \| 0.6535 \| 0.2401 \| 0.1009 \| \| 1.0958 \| 45.0 \| 585 \| 0.8718 \| 0.72 \| 0.4057 \| 2.4922 \| 0.72 \| 0.6551 \| 0.2624 \| 0.0998 \| \| 1.0958 \| 46.0 \| 598 \| 0.8737 \| 0.7 \| 0.4070 \| 2.4455 \| 0.7 \| 0.6416 \| 0.2360 \| 0.1052 \| \| 1.0958 \| 47.0 \| 611 \| 0.8707 \| 0.715 \| 0.4094 \| 2.3519 \| 0.715 \| 0.6494 \| 0.2514 \| 0.1086 \| \| 1.0958 \| 48.0 \| 624 \| 0.8640 \| 0.705 \| 0.4039 \| 2.3765 \| 0.705 \| 0.6430 \| 0.2538 \| 0.1041 \| \| 1.0958 \| 49.0 \| 637 \| 0.8702 \| 0.7 \| 0.4066 \| 2.5524 \| 0.7 \| 0.6423 \| 0.2160 \| 0.1080 \| \| 1.0958 \| 50.0 \| 650 \| 0.8672 \| 0.71 \| 0.4047 \| 2.1924 \| 0.7100 \| 0.6463 \| 0.2420 \| 0.1050 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3
AIHUBFRANCE/personnalites-mediatiques	AIHUBFRANCE	2023-10-03T19:51:11Z	0	1	null	[ "fr", "license:cc-by-sa-4.0", "region:us" ]	null	2023-08-19T11:51:55Z	--- license: cc-by-sa-4.0 language: - fr --- # Fichiers .zip de Personnalites Médiatiques ## Disponible sur weights.gg ## Ou dans le séction "Files and Versions"
Quacktab/Reinforce-Pixelcopter	Quacktab	2023-10-03T19:47:35Z	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2023-10-03T09:13:46Z	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Pixelcopter results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 27.60 +/- 10.68 name: mean_reward verified: false --- # Reinforce Agent playing Pixelcopter-PLE-v0 This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.7	bdpc	2023-10-03T19:41:47Z	195	0	transformers	[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T19:23:34Z	--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.7 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.7 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.8012 - Accuracy: 0.7 - Brier Loss: 0.4467 - Nll: 2.5682 - F1 Micro: 0.7 - F1 Macro: 0.6313 - Ece: 0.2684 - Aurc: 0.1170 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 13 \| 1.8024 \| 0.16 \| 0.8966 \| 8.5001 \| 0.16 \| 0.1073 \| 0.2079 \| 0.8334 \| \| No log \| 2.0 \| 26 \| 1.7941 \| 0.145 \| 0.8957 \| 8.3207 \| 0.145 \| 0.0843 \| 0.2022 \| 0.8435 \| \| No log \| 3.0 \| 39 \| 1.7486 \| 0.2 \| 0.8868 \| 6.2015 \| 0.2000 \| 0.1007 \| 0.2209 \| 0.7900 \| \| No log \| 4.0 \| 52 \| 1.6854 \| 0.205 \| 0.8738 \| 6.0142 \| 0.205 \| 0.0707 \| 0.2453 \| 0.7584 \| \| No log \| 5.0 \| 65 \| 1.6162 \| 0.2 \| 0.8594 \| 6.2364 \| 0.2000 \| 0.0552 \| 0.2466 \| 0.7717 \| \| No log \| 6.0 \| 78 \| 1.5412 \| 0.235 \| 0.8416 \| 6.0423 \| 0.235 \| 0.0902 \| 0.2589 \| 0.7006 \| \| No log \| 7.0 \| 91 \| 1.5011 \| 0.295 \| 0.8304 \| 6.1420 \| 0.295 \| 0.1272 \| 0.2803 \| 0.6124 \| \| No log \| 8.0 \| 104 \| 1.4415 \| 0.3 \| 0.8114 \| 6.0440 \| 0.3 \| 0.1296 \| 0.2870 \| 0.5641 \| \| No log \| 9.0 \| 117 \| 1.3257 \| 0.38 \| 0.7625 \| 5.6923 \| 0.38 \| 0.2198 \| 0.3136 \| 0.3675 \| \| No log \| 10.0 \| 130 \| 1.3748 \| 0.33 \| 0.7905 \| 5.5276 \| 0.33 \| 0.1870 \| 0.2947 \| 0.5985 \| \| No log \| 11.0 \| 143 \| 1.3294 \| 0.39 \| 0.7683 \| 4.9632 \| 0.39 \| 0.2573 \| 0.2940 \| 0.4639 \| \| No log \| 12.0 \| 156 \| 1.2444 \| 0.385 \| 0.7297 \| 4.8431 \| 0.3850 \| 0.2330 \| 0.2849 \| 0.4173 \| \| No log \| 13.0 \| 169 \| 1.2212 \| 0.45 \| 0.7153 \| 4.5819 \| 0.45 \| 0.3051 \| 0.3143 \| 0.3379 \| \| No log \| 14.0 \| 182 \| 1.1835 \| 0.495 \| 0.6888 \| 3.6108 \| 0.495 \| 0.3412 \| 0.3316 \| 0.2873 \| \| No log \| 15.0 \| 195 \| 1.1203 \| 0.47 \| 0.6559 \| 3.6500 \| 0.47 \| 0.3348 \| 0.2935 \| 0.3061 \| \| No log \| 16.0 \| 208 \| 1.1520 \| 0.495 \| 0.6707 \| 3.8106 \| 0.495 \| 0.3632 \| 0.2938 \| 0.3604 \| \| No log \| 17.0 \| 221 \| 1.0261 \| 0.565 \| 0.6021 \| 3.3382 \| 0.565 \| 0.4214 \| 0.2840 \| 0.2047 \| \| No log \| 18.0 \| 234 \| 1.0080 \| 0.61 \| 0.5914 \| 3.2936 \| 0.61 \| 0.4748 \| 0.3240 \| 0.1806 \| \| No log \| 19.0 \| 247 \| 1.0696 \| 0.58 \| 0.6253 \| 3.2354 \| 0.58 \| 0.4686 \| 0.3152 \| 0.2626 \| \| No log \| 20.0 \| 260 \| 0.9733 \| 0.615 \| 0.5722 \| 3.1019 \| 0.615 \| 0.4968 \| 0.3259 \| 0.2066 \| \| No log \| 21.0 \| 273 \| 0.9266 \| 0.625 \| 0.5423 \| 3.0239 \| 0.625 \| 0.5202 \| 0.2834 \| 0.1782 \| \| No log \| 22.0 \| 286 \| 0.9364 \| 0.66 \| 0.5461 \| 2.9031 \| 0.66 \| 0.5461 \| 0.3128 \| 0.1601 \| \| No log \| 23.0 \| 299 \| 0.9181 \| 0.675 \| 0.5307 \| 2.8416 \| 0.675 \| 0.5584 \| 0.3106 \| 0.1462 \| \| No log \| 24.0 \| 312 \| 0.9739 \| 0.665 \| 0.5539 \| 2.8798 \| 0.665 \| 0.5634 \| 0.3325 \| 0.1610 \| \| No log \| 25.0 \| 325 \| 0.8851 \| 0.69 \| 0.5099 \| 2.7336 \| 0.69 \| 0.6013 \| 0.3064 \| 0.1437 \| \| No log \| 26.0 \| 338 \| 0.8755 \| 0.71 \| 0.4979 \| 2.7400 \| 0.7100 \| 0.6032 \| 0.3162 \| 0.1211 \| \| No log \| 27.0 \| 351 \| 0.8653 \| 0.675 \| 0.4964 \| 2.8339 \| 0.675 \| 0.5705 \| 0.2977 \| 0.1386 \| \| No log \| 28.0 \| 364 \| 0.8838 \| 0.675 \| 0.5055 \| 2.7456 \| 0.675 \| 0.5816 \| 0.2969 \| 0.1524 \| \| No log \| 29.0 \| 377 \| 0.8805 \| 0.68 \| 0.5025 \| 2.6942 \| 0.68 \| 0.5855 \| 0.3099 \| 0.1380 \| \| No log \| 30.0 \| 390 \| 0.8585 \| 0.665 \| 0.4891 \| 2.7511 \| 0.665 \| 0.5737 \| 0.2627 \| 0.1370 \| \| No log \| 31.0 \| 403 \| 0.8410 \| 0.675 \| 0.4736 \| 2.6431 \| 0.675 \| 0.5985 \| 0.2670 \| 0.1335 \| \| No log \| 32.0 \| 416 \| 0.8378 \| 0.71 \| 0.4724 \| 2.7320 \| 0.7100 \| 0.6236 \| 0.2885 \| 0.1153 \| \| No log \| 33.0 \| 429 \| 0.8421 \| 0.705 \| 0.4718 \| 2.6331 \| 0.705 \| 0.6326 \| 0.2644 \| 0.1147 \| \| No log \| 34.0 \| 442 \| 0.8350 \| 0.685 \| 0.4697 \| 2.8035 \| 0.685 \| 0.6062 \| 0.2831 \| 0.1291 \| \| No log \| 35.0 \| 455 \| 0.8377 \| 0.7 \| 0.4708 \| 2.4611 \| 0.7 \| 0.6376 \| 0.3173 \| 0.1195 \| \| No log \| 36.0 \| 468 \| 0.8126 \| 0.69 \| 0.4562 \| 2.3909 \| 0.69 \| 0.6154 \| 0.2433 \| 0.1177 \| \| No log \| 37.0 \| 481 \| 0.8299 \| 0.685 \| 0.4673 \| 2.5695 \| 0.685 \| 0.6080 \| 0.2802 \| 0.1261 \| \| No log \| 38.0 \| 494 \| 0.8197 \| 0.685 \| 0.4597 \| 2.6388 \| 0.685 \| 0.6187 \| 0.2690 \| 0.1229 \| \| 0.9314 \| 39.0 \| 507 \| 0.8137 \| 0.695 \| 0.4547 \| 2.7263 \| 0.695 \| 0.6332 \| 0.2581 \| 0.1207 \| \| 0.9314 \| 40.0 \| 520 \| 0.8168 \| 0.69 \| 0.4583 \| 2.6230 \| 0.69 \| 0.6267 \| 0.2696 \| 0.1161 \| \| 0.9314 \| 41.0 \| 533 \| 0.8090 \| 0.7 \| 0.4529 \| 2.6449 \| 0.7 \| 0.6236 \| 0.2445 \| 0.1187 \| \| 0.9314 \| 42.0 \| 546 \| 0.8168 \| 0.68 \| 0.4586 \| 2.5516 \| 0.68 \| 0.6162 \| 0.2722 \| 0.1275 \| \| 0.9314 \| 43.0 \| 559 \| 0.8100 \| 0.7 \| 0.4523 \| 2.5565 \| 0.7 \| 0.6347 \| 0.2869 \| 0.1192 \| \| 0.9314 \| 44.0 \| 572 \| 0.8078 \| 0.7 \| 0.4514 \| 2.5734 \| 0.7 \| 0.6344 \| 0.2583 \| 0.1172 \| \| 0.9314 \| 45.0 \| 585 \| 0.8022 \| 0.715 \| 0.4472 \| 2.4971 \| 0.715 \| 0.6534 \| 0.2890 \| 0.1165 \| \| 0.9314 \| 46.0 \| 598 \| 0.8049 \| 0.695 \| 0.4484 \| 2.4891 \| 0.695 \| 0.6423 \| 0.2722 \| 0.1189 \| \| 0.9314 \| 47.0 \| 611 \| 0.8025 \| 0.705 \| 0.4481 \| 2.4929 \| 0.705 \| 0.6393 \| 0.2650 \| 0.1124 \| \| 0.9314 \| 48.0 \| 624 \| 0.7973 \| 0.7 \| 0.4439 \| 2.5000 \| 0.7 \| 0.6292 \| 0.2718 \| 0.1142 \| \| 0.9314 \| 49.0 \| 637 \| 0.8011 \| 0.7 \| 0.4464 \| 2.5713 \| 0.7 \| 0.6303 \| 0.2400 \| 0.1183 \| \| 0.9314 \| 50.0 \| 650 \| 0.8012 \| 0.7 \| 0.4467 \| 2.5682 \| 0.7 \| 0.6313 \| 0.2684 \| 0.1170 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3
ipipan/nlpre_stanza_nkjp_fasttext_nkjp-by-type	ipipan	2023-10-03T19:35:11Z	0	0	null	[ "region:us" ]	null	2023-09-29T08:04:40Z	# Model description - Morphosyntactic analyzer: Stanza - Tagset: NKJP - Embedding vectors: Fasttext (wiki) - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_stanza_nkjp_fasttext_nkjp-by-type ``` ## Load model ``` import stanza lang = 'pl' model_name = 'nlpre_stanza_nkjp_fasttext_nkjp-by-type' prefix = 'nkjpbytype_nkjp' config = \ { # Comma-separated list of processors to use 'processors': 'tokenize,mwt,pos,lemma', # Language code for the language to build the Pipeline in 'lang': lang, # Processor-specific arguments are set with keys "{processor_name}_{argument_name}" # You only need model paths if you have a specific model outside of stanza_resources 'tokenize_model_path': os.path.join(model_name, f'{lang}_{prefix}_tokenizer.pt'), 'mwt_model_path': os.path.join(model_name, f'{lang}_{prefix}_mwt_expander.pt'), 'pos_model_path': os.path.join(model_name, f'{lang}_{prefix}_tagger.pt'), 'pos_pretrain_path': os.path.join(model_name, f'{lang}_{prefix}.pretrain.pt'), 'lemma_model_path': os.path.join(model_name, f'{lang}_{prefix}_lemmatizer.pt'), # Use pretokenized text as input and disable tokenization 'tokenize_pretokenized': True } model = stanza.Pipeline(**config)
bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.5	bdpc	2023-10-03T19:23:04Z	196	0	transformers	[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T18:13:29Z	--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.5 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6481 - Accuracy: 0.69 - Brier Loss: 0.4919 - Nll: 2.4969 - F1 Micro: 0.69 - F1 Macro: 0.6317 - Ece: 0.3029 - Aurc: 0.1260 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 13 \| 1.4796 \| 0.165 \| 0.8965 \| 8.4885 \| 0.165 \| 0.1123 \| 0.2151 \| 0.8341 \| \| No log \| 2.0 \| 26 \| 1.4679 \| 0.165 \| 0.8954 \| 8.3391 \| 0.165 \| 0.1066 \| 0.2136 \| 0.8332 \| \| No log \| 3.0 \| 39 \| 1.4170 \| 0.21 \| 0.8858 \| 6.1941 \| 0.2100 \| 0.0969 \| 0.2433 \| 0.7991 \| \| No log \| 4.0 \| 52 \| 1.3472 \| 0.21 \| 0.8711 \| 6.0602 \| 0.2100 \| 0.0728 \| 0.2320 \| 0.7271 \| \| No log \| 5.0 \| 65 \| 1.2776 \| 0.19 \| 0.8572 \| 6.1293 \| 0.19 \| 0.0537 \| 0.2422 \| 0.7473 \| \| No log \| 6.0 \| 78 \| 1.1840 \| 0.245 \| 0.8353 \| 6.2405 \| 0.245 \| 0.1060 \| 0.2810 \| 0.6690 \| \| No log \| 7.0 \| 91 \| 1.0740 \| 0.365 \| 0.7936 \| 6.3617 \| 0.3650 \| 0.1739 \| 0.3136 \| 0.3646 \| \| No log \| 8.0 \| 104 \| 1.1102 \| 0.345 \| 0.8081 \| 5.8896 \| 0.345 \| 0.1812 \| 0.3046 \| 0.4292 \| \| No log \| 9.0 \| 117 \| 1.0735 \| 0.34 \| 0.7963 \| 5.9970 \| 0.34 \| 0.1842 \| 0.3028 \| 0.4286 \| \| No log \| 10.0 \| 130 \| 1.1145 \| 0.265 \| 0.8110 \| 5.9054 \| 0.265 \| 0.1300 \| 0.2511 \| 0.6350 \| \| No log \| 11.0 \| 143 \| 0.9981 \| 0.325 \| 0.7659 \| 5.3834 \| 0.325 \| 0.1655 \| 0.2790 \| 0.4860 \| \| No log \| 12.0 \| 156 \| 1.0500 \| 0.285 \| 0.7898 \| 4.9696 \| 0.285 \| 0.1594 \| 0.2604 \| 0.6636 \| \| No log \| 13.0 \| 169 \| 0.8764 \| 0.445 \| 0.6976 \| 4.6456 \| 0.445 \| 0.2647 \| 0.2779 \| 0.3020 \| \| No log \| 14.0 \| 182 \| 0.9147 \| 0.48 \| 0.7108 \| 4.4793 \| 0.48 \| 0.2942 \| 0.3262 \| 0.2862 \| \| No log \| 15.0 \| 195 \| 0.9776 \| 0.38 \| 0.7434 \| 4.4065 \| 0.38 \| 0.2269 \| 0.2938 \| 0.5297 \| \| No log \| 16.0 \| 208 \| 0.8066 \| 0.47 \| 0.6494 \| 3.9671 \| 0.47 \| 0.2966 \| 0.2791 \| 0.2907 \| \| No log \| 17.0 \| 221 \| 0.7766 \| 0.535 \| 0.6305 \| 3.5250 \| 0.535 \| 0.3866 \| 0.3003 \| 0.2424 \| \| No log \| 18.0 \| 234 \| 0.8186 \| 0.535 \| 0.6458 \| 3.3670 \| 0.535 \| 0.3792 \| 0.3005 \| 0.2311 \| \| No log \| 19.0 \| 247 \| 0.8156 \| 0.52 \| 0.6430 \| 3.1633 \| 0.52 \| 0.3675 \| 0.3072 \| 0.2667 \| \| No log \| 20.0 \| 260 \| 0.8386 \| 0.55 \| 0.6462 \| 3.2549 \| 0.55 \| 0.4251 \| 0.3103 \| 0.2703 \| \| No log \| 21.0 \| 273 \| 0.7996 \| 0.515 \| 0.6342 \| 3.1396 \| 0.515 \| 0.3969 \| 0.3177 \| 0.2867 \| \| No log \| 22.0 \| 286 \| 0.8605 \| 0.6 \| 0.6472 \| 3.2563 \| 0.6 \| 0.4717 \| 0.3810 \| 0.2113 \| \| No log \| 23.0 \| 299 \| 0.7138 \| 0.595 \| 0.5713 \| 3.1171 \| 0.595 \| 0.4657 \| 0.2773 \| 0.2034 \| \| No log \| 24.0 \| 312 \| 0.7212 \| 0.665 \| 0.5740 \| 2.9688 \| 0.665 \| 0.5474 \| 0.3366 \| 0.1754 \| \| No log \| 25.0 \| 325 \| 0.7463 \| 0.63 \| 0.5843 \| 2.8998 \| 0.63 \| 0.5502 \| 0.3432 \| 0.2072 \| \| No log \| 26.0 \| 338 \| 0.7231 \| 0.67 \| 0.5626 \| 3.1334 \| 0.67 \| 0.5564 \| 0.3160 \| 0.1521 \| \| No log \| 27.0 \| 351 \| 0.6913 \| 0.68 \| 0.5427 \| 2.8906 \| 0.68 \| 0.5702 \| 0.3354 \| 0.1406 \| \| No log \| 28.0 \| 364 \| 0.6825 \| 0.66 \| 0.5342 \| 2.8619 \| 0.66 \| 0.5615 \| 0.2902 \| 0.1625 \| \| No log \| 29.0 \| 377 \| 0.7015 \| 0.665 \| 0.5549 \| 2.7315 \| 0.665 \| 0.5741 \| 0.3305 \| 0.1769 \| \| No log \| 30.0 \| 390 \| 0.6939 \| 0.67 \| 0.5406 \| 2.7114 \| 0.67 \| 0.5720 \| 0.3353 \| 0.1420 \| \| No log \| 31.0 \| 403 \| 0.6836 \| 0.69 \| 0.5265 \| 2.7567 \| 0.69 \| 0.5982 \| 0.3216 \| 0.1455 \| \| No log \| 32.0 \| 416 \| 0.6728 \| 0.69 \| 0.5211 \| 2.6858 \| 0.69 \| 0.6056 \| 0.3124 \| 0.1453 \| \| No log \| 33.0 \| 429 \| 0.6926 \| 0.675 \| 0.5403 \| 2.5815 \| 0.675 \| 0.6095 \| 0.3258 \| 0.1683 \| \| No log \| 34.0 \| 442 \| 0.6673 \| 0.66 \| 0.5090 \| 2.5591 \| 0.66 \| 0.5722 \| 0.2950 \| 0.1385 \| \| No log \| 35.0 \| 455 \| 0.6811 \| 0.675 \| 0.5207 \| 2.5813 \| 0.675 \| 0.5841 \| 0.3324 \| 0.1273 \| \| No log \| 36.0 \| 468 \| 0.6648 \| 0.69 \| 0.5119 \| 2.5745 \| 0.69 \| 0.6225 \| 0.3433 \| 0.1320 \| \| No log \| 37.0 \| 481 \| 0.6623 \| 0.67 \| 0.5092 \| 2.6134 \| 0.67 \| 0.6129 \| 0.3204 \| 0.1471 \| \| No log \| 38.0 \| 494 \| 0.6635 \| 0.69 \| 0.5088 \| 2.3862 \| 0.69 \| 0.6192 \| 0.3201 \| 0.1311 \| \| 0.7628 \| 39.0 \| 507 \| 0.6554 \| 0.685 \| 0.5008 \| 2.5849 \| 0.685 \| 0.6210 \| 0.3179 \| 0.1377 \| \| 0.7628 \| 40.0 \| 520 \| 0.6567 \| 0.685 \| 0.5022 \| 2.6498 \| 0.685 \| 0.6310 \| 0.3127 \| 0.1414 \| \| 0.7628 \| 41.0 \| 533 \| 0.6558 \| 0.695 \| 0.4996 \| 2.5917 \| 0.695 \| 0.6347 \| 0.3115 \| 0.1321 \| \| 0.7628 \| 42.0 \| 546 \| 0.6578 \| 0.695 \| 0.5021 \| 2.4864 \| 0.695 \| 0.6259 \| 0.3098 \| 0.1306 \| \| 0.7628 \| 43.0 \| 559 \| 0.6544 \| 0.685 \| 0.4969 \| 2.5757 \| 0.685 \| 0.6175 \| 0.2955 \| 0.1342 \| \| 0.7628 \| 44.0 \| 572 \| 0.6507 \| 0.685 \| 0.4944 \| 2.5057 \| 0.685 \| 0.6257 \| 0.3144 \| 0.1304 \| \| 0.7628 \| 45.0 \| 585 \| 0.6501 \| 0.675 \| 0.4937 \| 2.4903 \| 0.675 \| 0.6208 \| 0.3091 \| 0.1301 \| \| 0.7628 \| 46.0 \| 598 \| 0.6518 \| 0.685 \| 0.4949 \| 2.4732 \| 0.685 \| 0.6254 \| 0.3164 \| 0.1235 \| \| 0.7628 \| 47.0 \| 611 \| 0.6499 \| 0.685 \| 0.4936 \| 2.4924 \| 0.685 \| 0.6273 \| 0.3124 \| 0.1323 \| \| 0.7628 \| 48.0 \| 624 \| 0.6490 \| 0.7 \| 0.4925 \| 2.4999 \| 0.7 \| 0.6353 \| 0.3147 \| 0.1243 \| \| 0.7628 \| 49.0 \| 637 \| 0.6510 \| 0.685 \| 0.4933 \| 2.5758 \| 0.685 \| 0.6242 \| 0.3206 \| 0.1281 \| \| 0.7628 \| 50.0 \| 650 \| 0.6481 \| 0.69 \| 0.4919 \| 2.4969 \| 0.69 \| 0.6317 \| 0.3029 \| 0.1260 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3
bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.9	bdpc	2023-10-03T19:06:28Z	197	0	transformers	[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T18:52:55Z	--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.9 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.9 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.8831 - Accuracy: 0.695 - Brier Loss: 0.4126 - Nll: 2.4628 - F1 Micro: 0.695 - F1 Macro: 0.6387 - Ece: 0.2426 - Aurc: 0.1068 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 13 \| 2.1233 \| 0.16 \| 0.8967 \| 8.5697 \| 0.16 \| 0.1066 \| 0.2078 \| 0.8316 \| \| No log \| 2.0 \| 26 \| 2.1188 \| 0.14 \| 0.8961 \| 8.2960 \| 0.14 \| 0.0886 \| 0.1947 \| 0.8419 \| \| No log \| 3.0 \| 39 \| 2.0764 \| 0.195 \| 0.8873 \| 6.4713 \| 0.195 \| 0.1159 \| 0.2335 \| 0.7665 \| \| No log \| 4.0 \| 52 \| 2.0365 \| 0.21 \| 0.8787 \| 5.7752 \| 0.2100 \| 0.0930 \| 0.2376 \| 0.7548 \| \| No log \| 5.0 \| 65 \| 1.9888 \| 0.2 \| 0.8682 \| 5.8737 \| 0.2000 \| 0.0775 \| 0.2417 \| 0.7314 \| \| No log \| 6.0 \| 78 \| 1.8998 \| 0.215 \| 0.8465 \| 5.8553 \| 0.2150 \| 0.0970 \| 0.2586 \| 0.7063 \| \| No log \| 7.0 \| 91 \| 1.8351 \| 0.33 \| 0.8289 \| 5.7781 \| 0.33 \| 0.1904 \| 0.3089 \| 0.6103 \| \| No log \| 8.0 \| 104 \| 1.7342 \| 0.4 \| 0.7968 \| 5.5366 \| 0.4000 \| 0.2476 \| 0.3457 \| 0.4276 \| \| No log \| 9.0 \| 117 \| 1.6787 \| 0.36 \| 0.7757 \| 5.7414 \| 0.36 \| 0.2148 \| 0.3062 \| 0.4324 \| \| No log \| 10.0 \| 130 \| 1.6942 \| 0.4 \| 0.7870 \| 5.2615 \| 0.4000 \| 0.2831 \| 0.3168 \| 0.5227 \| \| No log \| 11.0 \| 143 \| 1.5992 \| 0.4 \| 0.7489 \| 4.7833 \| 0.4000 \| 0.2649 \| 0.3053 \| 0.4679 \| \| No log \| 12.0 \| 156 \| 1.6071 \| 0.425 \| 0.7532 \| 4.2803 \| 0.425 \| 0.2906 \| 0.3196 \| 0.4646 \| \| No log \| 13.0 \| 169 \| 1.4727 \| 0.48 \| 0.6925 \| 4.1911 \| 0.48 \| 0.3239 \| 0.2957 \| 0.3081 \| \| No log \| 14.0 \| 182 \| 1.4275 \| 0.515 \| 0.6705 \| 3.7980 \| 0.515 \| 0.3569 \| 0.3211 \| 0.2626 \| \| No log \| 15.0 \| 195 \| 1.3282 \| 0.56 \| 0.6200 \| 3.6359 \| 0.56 \| 0.4163 \| 0.2990 \| 0.2213 \| \| No log \| 16.0 \| 208 \| 1.3280 \| 0.565 \| 0.6263 \| 3.4960 \| 0.565 \| 0.4177 \| 0.3217 \| 0.2346 \| \| No log \| 17.0 \| 221 \| 1.3220 \| 0.595 \| 0.6196 \| 3.2202 \| 0.595 \| 0.4639 \| 0.3322 \| 0.1992 \| \| No log \| 18.0 \| 234 \| 1.2359 \| 0.595 \| 0.5840 \| 3.3332 \| 0.595 \| 0.4780 \| 0.3042 \| 0.2011 \| \| No log \| 19.0 \| 247 \| 1.1690 \| 0.625 \| 0.5531 \| 3.2423 \| 0.625 \| 0.5233 \| 0.2940 \| 0.1807 \| \| No log \| 20.0 \| 260 \| 1.1644 \| 0.64 \| 0.5532 \| 3.0542 \| 0.64 \| 0.5429 \| 0.3019 \| 0.1821 \| \| No log \| 21.0 \| 273 \| 1.1611 \| 0.62 \| 0.5516 \| 2.9412 \| 0.62 \| 0.5193 \| 0.2865 \| 0.2160 \| \| No log \| 22.0 \| 286 \| 1.3427 \| 0.585 \| 0.6361 \| 3.0936 \| 0.585 \| 0.5089 \| 0.3442 \| 0.2922 \| \| No log \| 23.0 \| 299 \| 1.1238 \| 0.62 \| 0.5440 \| 2.7924 \| 0.62 \| 0.5458 \| 0.2654 \| 0.2088 \| \| No log \| 24.0 \| 312 \| 1.2008 \| 0.685 \| 0.5615 \| 2.5918 \| 0.685 \| 0.5890 \| 0.3907 \| 0.1516 \| \| No log \| 25.0 \| 325 \| 1.0764 \| 0.695 \| 0.5000 \| 2.6354 \| 0.695 \| 0.6107 \| 0.3126 \| 0.1397 \| \| No log \| 26.0 \| 338 \| 1.0268 \| 0.675 \| 0.4822 \| 2.4798 \| 0.675 \| 0.5992 \| 0.2775 \| 0.1229 \| \| No log \| 27.0 \| 351 \| 1.0340 \| 0.67 \| 0.4893 \| 2.4316 \| 0.67 \| 0.5997 \| 0.2763 \| 0.1638 \| \| No log \| 28.0 \| 364 \| 1.0154 \| 0.665 \| 0.4769 \| 2.6487 \| 0.665 \| 0.6034 \| 0.2590 \| 0.1487 \| \| No log \| 29.0 \| 377 \| 1.0013 \| 0.64 \| 0.4814 \| 2.5899 \| 0.64 \| 0.5771 \| 0.2429 \| 0.1593 \| \| No log \| 30.0 \| 390 \| 1.0173 \| 0.685 \| 0.4714 \| 2.6922 \| 0.685 \| 0.6178 \| 0.2898 \| 0.1423 \| \| No log \| 31.0 \| 403 \| 0.9630 \| 0.695 \| 0.4509 \| 2.6349 \| 0.695 \| 0.6206 \| 0.2746 \| 0.1248 \| \| No log \| 32.0 \| 416 \| 0.9950 \| 0.68 \| 0.4648 \| 2.4144 \| 0.68 \| 0.6362 \| 0.3020 \| 0.1725 \| \| No log \| 33.0 \| 429 \| 0.9711 \| 0.72 \| 0.4502 \| 2.6651 \| 0.72 \| 0.6571 \| 0.2892 \| 0.1268 \| \| No log \| 34.0 \| 442 \| 0.9491 \| 0.705 \| 0.4425 \| 2.7169 \| 0.705 \| 0.6425 \| 0.2541 \| 0.1145 \| \| No log \| 35.0 \| 455 \| 0.9213 \| 0.685 \| 0.4309 \| 2.5736 \| 0.685 \| 0.6174 \| 0.2380 \| 0.1161 \| \| No log \| 36.0 \| 468 \| 0.9144 \| 0.695 \| 0.4297 \| 2.4141 \| 0.695 \| 0.6308 \| 0.2502 \| 0.1154 \| \| No log \| 37.0 \| 481 \| 0.9242 \| 0.715 \| 0.4264 \| 2.7191 \| 0.715 \| 0.6429 \| 0.2386 \| 0.1030 \| \| No log \| 38.0 \| 494 \| 0.9290 \| 0.695 \| 0.4346 \| 2.6515 \| 0.695 \| 0.6367 \| 0.2432 \| 0.1189 \| \| 1.0953 \| 39.0 \| 507 \| 0.9110 \| 0.69 \| 0.4262 \| 2.6615 \| 0.69 \| 0.6328 \| 0.2368 \| 0.1112 \| \| 1.0953 \| 40.0 \| 520 \| 0.9000 \| 0.695 \| 0.4186 \| 2.4590 \| 0.695 \| 0.6417 \| 0.2453 \| 0.1070 \| \| 1.0953 \| 41.0 \| 533 \| 0.8961 \| 0.69 \| 0.4189 \| 2.4170 \| 0.69 \| 0.6368 \| 0.2349 \| 0.1090 \| \| 1.0953 \| 42.0 \| 546 \| 0.9103 \| 0.675 \| 0.4286 \| 2.6129 \| 0.675 \| 0.6193 \| 0.2318 \| 0.1190 \| \| 1.0953 \| 43.0 \| 559 \| 0.8858 \| 0.715 \| 0.4131 \| 2.5243 \| 0.715 \| 0.6517 \| 0.2462 \| 0.1053 \| \| 1.0953 \| 44.0 \| 572 \| 0.8872 \| 0.705 \| 0.4135 \| 2.3272 \| 0.705 \| 0.6542 \| 0.2596 \| 0.1051 \| \| 1.0953 \| 45.0 \| 585 \| 0.8897 \| 0.715 \| 0.4136 \| 2.3788 \| 0.715 \| 0.6532 \| 0.2560 \| 0.1035 \| \| 1.0953 \| 46.0 \| 598 \| 0.8842 \| 0.7 \| 0.4117 \| 2.5325 \| 0.7 \| 0.6446 \| 0.2327 \| 0.1075 \| \| 1.0953 \| 47.0 \| 611 \| 0.8857 \| 0.675 \| 0.4141 \| 2.5451 \| 0.675 \| 0.6203 \| 0.2473 \| 0.1125 \| \| 1.0953 \| 48.0 \| 624 \| 0.8875 \| 0.69 \| 0.4164 \| 2.4696 \| 0.69 \| 0.6352 \| 0.2542 \| 0.1109 \| \| 1.0953 \| 49.0 \| 637 \| 0.8842 \| 0.69 \| 0.4153 \| 2.5338 \| 0.69 \| 0.6358 \| 0.2302 \| 0.1112 \| \| 1.0953 \| 50.0 \| 650 \| 0.8831 \| 0.695 \| 0.4126 \| 2.4628 \| 0.695 \| 0.6387 \| 0.2426 \| 0.1068 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3
Soheil-FM/falcon-7b-chatbot	Soheil-FM	2023-10-03T19:01:09Z	0	0	peft	[ "peft", "region:us" ]	null	2023-10-03T19:01:03Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.5.0
bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.7	bdpc	2023-10-03T18:52:29Z	196	0	transformers	[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T18:38:52Z	--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.7 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.7 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.8009 - Accuracy: 0.695 - Brier Loss: 0.4518 - Nll: 2.3840 - F1 Micro: 0.695 - F1 Macro: 0.6406 - Ece: 0.2661 - Aurc: 0.1211 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 13 \| 1.7971 \| 0.17 \| 0.8966 \| 8.4593 \| 0.17 \| 0.1148 \| 0.2202 \| 0.8308 \| \| No log \| 2.0 \| 26 \| 1.7887 \| 0.13 \| 0.8956 \| 8.3211 \| 0.13 \| 0.0772 \| 0.2024 \| 0.8359 \| \| No log \| 3.0 \| 39 \| 1.7450 \| 0.225 \| 0.8868 \| 6.4554 \| 0.225 \| 0.1165 \| 0.2502 \| 0.7572 \| \| No log \| 4.0 \| 52 \| 1.6811 \| 0.24 \| 0.8733 \| 5.9510 \| 0.24 \| 0.0953 \| 0.2651 \| 0.6944 \| \| No log \| 5.0 \| 65 \| 1.6411 \| 0.19 \| 0.8649 \| 6.0993 \| 0.19 \| 0.0493 \| 0.2422 \| 0.7783 \| \| No log \| 6.0 \| 78 \| 1.5475 \| 0.195 \| 0.8429 \| 6.2065 \| 0.195 \| 0.0630 \| 0.2472 \| 0.7110 \| \| No log \| 7.0 \| 91 \| 1.4688 \| 0.3 \| 0.8197 \| 6.0345 \| 0.3 \| 0.1481 \| 0.2936 \| 0.5379 \| \| No log \| 8.0 \| 104 \| 1.5036 \| 0.285 \| 0.8294 \| 5.6660 \| 0.285 \| 0.1428 \| 0.2869 \| 0.6535 \| \| No log \| 9.0 \| 117 \| 1.3901 \| 0.34 \| 0.7934 \| 5.9107 \| 0.34 \| 0.1853 \| 0.2894 \| 0.5277 \| \| No log \| 10.0 \| 130 \| 1.3484 \| 0.37 \| 0.7760 \| 5.6441 \| 0.37 \| 0.2175 \| 0.3177 \| 0.5266 \| \| No log \| 11.0 \| 143 \| 1.3375 \| 0.34 \| 0.7734 \| 5.0872 \| 0.34 \| 0.2083 \| 0.2902 \| 0.5557 \| \| No log \| 12.0 \| 156 \| 1.3639 \| 0.305 \| 0.7834 \| 4.5070 \| 0.305 \| 0.1885 \| 0.2674 \| 0.6177 \| \| No log \| 13.0 \| 169 \| 1.2321 \| 0.415 \| 0.7225 \| 4.3464 \| 0.415 \| 0.2751 \| 0.2943 \| 0.3825 \| \| No log \| 14.0 \| 182 \| 1.1453 \| 0.44 \| 0.6767 \| 4.4158 \| 0.44 \| 0.2864 \| 0.2617 \| 0.3413 \| \| No log \| 15.0 \| 195 \| 1.1830 \| 0.43 \| 0.6965 \| 3.8251 \| 0.4300 \| 0.2972 \| 0.2912 \| 0.4239 \| \| No log \| 16.0 \| 208 \| 1.0572 \| 0.535 \| 0.6230 \| 3.5943 \| 0.535 \| 0.3758 \| 0.2861 \| 0.2291 \| \| No log \| 17.0 \| 221 \| 1.0532 \| 0.585 \| 0.6151 \| 3.3834 \| 0.585 \| 0.4331 \| 0.3278 \| 0.1879 \| \| No log \| 18.0 \| 234 \| 1.0940 \| 0.565 \| 0.6374 \| 3.2290 \| 0.565 \| 0.4431 \| 0.3313 \| 0.2415 \| \| No log \| 19.0 \| 247 \| 0.9877 \| 0.585 \| 0.5886 \| 3.1068 \| 0.585 \| 0.4564 \| 0.2896 \| 0.2110 \| \| No log \| 20.0 \| 260 \| 1.0405 \| 0.61 \| 0.6056 \| 3.1786 \| 0.61 \| 0.5038 \| 0.3428 \| 0.1962 \| \| No log \| 21.0 \| 273 \| 0.9728 \| 0.635 \| 0.5634 \| 2.9133 \| 0.635 \| 0.5293 \| 0.3333 \| 0.1664 \| \| No log \| 22.0 \| 286 \| 0.9425 \| 0.635 \| 0.5527 \| 2.8909 \| 0.635 \| 0.5237 \| 0.3131 \| 0.1796 \| \| No log \| 23.0 \| 299 \| 0.9549 \| 0.65 \| 0.5605 \| 2.8074 \| 0.65 \| 0.5539 \| 0.3283 \| 0.1914 \| \| No log \| 24.0 \| 312 \| 1.0085 \| 0.67 \| 0.5733 \| 2.8377 \| 0.67 \| 0.5543 \| 0.3525 \| 0.1571 \| \| No log \| 25.0 \| 325 \| 0.9140 \| 0.655 \| 0.5257 \| 2.5878 \| 0.655 \| 0.5603 \| 0.3171 \| 0.1495 \| \| No log \| 26.0 \| 338 \| 0.8979 \| 0.65 \| 0.5249 \| 2.7723 \| 0.65 \| 0.5563 \| 0.2843 \| 0.1646 \| \| No log \| 27.0 \| 351 \| 0.8912 \| 0.675 \| 0.5082 \| 2.6562 \| 0.675 \| 0.5837 \| 0.2871 \| 0.1380 \| \| No log \| 28.0 \| 364 \| 0.8966 \| 0.66 \| 0.5242 \| 2.3150 \| 0.66 \| 0.5890 \| 0.3180 \| 0.1777 \| \| No log \| 29.0 \| 377 \| 0.8602 \| 0.67 \| 0.4959 \| 2.5813 \| 0.67 \| 0.5866 \| 0.3023 \| 0.1319 \| \| No log \| 30.0 \| 390 \| 0.8434 \| 0.69 \| 0.4779 \| 2.5451 \| 0.69 \| 0.6130 \| 0.3061 \| 0.1188 \| \| No log \| 31.0 \| 403 \| 0.8406 \| 0.715 \| 0.4782 \| 2.3339 \| 0.715 \| 0.6438 \| 0.3241 \| 0.1092 \| \| No log \| 32.0 \| 416 \| 0.8294 \| 0.71 \| 0.4726 \| 2.5394 \| 0.7100 \| 0.6308 \| 0.2922 \| 0.1218 \| \| No log \| 33.0 \| 429 \| 0.8329 \| 0.68 \| 0.4763 \| 2.4520 \| 0.68 \| 0.6166 \| 0.2592 \| 0.1396 \| \| No log \| 34.0 \| 442 \| 0.8937 \| 0.69 \| 0.5015 \| 2.5649 \| 0.69 \| 0.6357 \| 0.3293 \| 0.1279 \| \| No log \| 35.0 \| 455 \| 0.8358 \| 0.665 \| 0.4807 \| 2.4437 \| 0.665 \| 0.6178 \| 0.2380 \| 0.1473 \| \| No log \| 36.0 \| 468 \| 0.8283 \| 0.685 \| 0.4747 \| 2.5408 \| 0.685 \| 0.6304 \| 0.3126 \| 0.1361 \| \| No log \| 37.0 \| 481 \| 0.8235 \| 0.685 \| 0.4707 \| 2.4620 \| 0.685 \| 0.6300 \| 0.2757 \| 0.1343 \| \| No log \| 38.0 \| 494 \| 0.8289 \| 0.68 \| 0.4778 \| 2.5443 \| 0.68 \| 0.6305 \| 0.2935 \| 0.1469 \| \| 0.9462 \| 39.0 \| 507 \| 0.8373 \| 0.69 \| 0.4728 \| 2.5775 \| 0.69 \| 0.6281 \| 0.3028 \| 0.1149 \| \| 0.9462 \| 40.0 \| 520 \| 0.8062 \| 0.715 \| 0.4548 \| 2.3673 \| 0.715 \| 0.6587 \| 0.2776 \| 0.1133 \| \| 0.9462 \| 41.0 \| 533 \| 0.7990 \| 0.705 \| 0.4517 \| 2.3284 \| 0.705 \| 0.6463 \| 0.2716 \| 0.1185 \| \| 0.9462 \| 42.0 \| 546 \| 0.8210 \| 0.7 \| 0.4650 \| 2.5646 \| 0.7 \| 0.6432 \| 0.2690 \| 0.1199 \| \| 0.9462 \| 43.0 \| 559 \| 0.8102 \| 0.695 \| 0.4558 \| 2.5651 \| 0.695 \| 0.6442 \| 0.2656 \| 0.1184 \| \| 0.9462 \| 44.0 \| 572 \| 0.8061 \| 0.69 \| 0.4566 \| 2.5154 \| 0.69 \| 0.6356 \| 0.2816 \| 0.1267 \| \| 0.9462 \| 45.0 \| 585 \| 0.8018 \| 0.7 \| 0.4531 \| 2.4982 \| 0.7 \| 0.6419 \| 0.2696 \| 0.1192 \| \| 0.9462 \| 46.0 \| 598 \| 0.8040 \| 0.7 \| 0.4521 \| 2.5309 \| 0.7 \| 0.6448 \| 0.2797 \| 0.1166 \| \| 0.9462 \| 47.0 \| 611 \| 0.8062 \| 0.68 \| 0.4560 \| 2.5452 \| 0.68 \| 0.6370 \| 0.2744 \| 0.1217 \| \| 0.9462 \| 48.0 \| 624 \| 0.8011 \| 0.69 \| 0.4529 \| 2.4281 \| 0.69 \| 0.6402 \| 0.2594 \| 0.1224 \| \| 0.9462 \| 49.0 \| 637 \| 0.8017 \| 0.69 \| 0.4532 \| 2.4239 \| 0.69 \| 0.6400 \| 0.2613 \| 0.1261 \| \| 0.9462 \| 50.0 \| 650 \| 0.8009 \| 0.695 \| 0.4518 \| 2.3840 \| 0.695 \| 0.6406 \| 0.2661 \| 0.1211 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3
Palunay/I1	Palunay	2023-10-03T18:45:03Z	0	0	null	[ "region:us" ]	null	2023-10-03T18:41:23Z	young demoness girl,(strong physique), 4 horns, 2 on the front side, 2 larger on the sides,red yellow brown curly hair,gray-blue eyes with an orange tinge, here is a small hump on the nose, the nose somewhat resembles the nose of a cat, in addition, her ears look like a cat's, but they are always slightly lowered, because they are in the place of ordinary human ones, Red lips and protruding fangs. Loose hair. The chest is medium-sized, the hips are visible, the muscles of the buttocks are large, as are the muscles of the arms. He wears black armor with gold inserts and green precious stones and large earrings, on his feet and hands he has strong claws. There is also a strong one. The tail is similar to the tail of a jasher and a cat at the same time. They are wearing large black shoulder pads, black dragon bone trousers, a huge bib and knee-high boots. On the back of 2 bolshie sharp demonic wings
Terps/whisper-small-dv	Terps	2023-10-03T18:42:46Z	79	0	transformers	[ "transformers", "pytorch", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dv", "dataset:mozilla-foundation/common_voice_13_0", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2023-10-02T19:46:49Z	--- language: - dv license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer datasets: - mozilla-foundation/common_voice_13_0 metrics: - wer model-index: - name: Whisper Small Dv - Sanchit Gandhi results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Common Voice 13 type: mozilla-foundation/common_voice_13_0 config: dv split: test args: dv metrics: - name: Wer type: wer value: 12.72733595298536 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Whisper Small Dv This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset. It achieves the following results on the evaluation set: - Loss: 0.1677 - Wer Ortho: 62.0238 - Wer: 12.7273 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant_with_warmup - lr_scheduler_warmup_steps: 50 - training_steps: 500 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer Ortho \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:---------:\|:-------:\| \| 0.1225 \| 1.63 \| 500 \| 0.1677 \| 62.0238 \| 12.7273 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.5	bdpc	2023-10-03T18:38:27Z	199	0	transformers	[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T18:20:05Z	--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.5 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.5 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6500 - Accuracy: 0.69 - Brier Loss: 0.5003 - Nll: 2.5629 - F1 Micro: 0.69 - F1 Macro: 0.6350 - Ece: 0.3098 - Aurc: 0.1329 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Brier Loss \| Nll \| F1 Micro \| F1 Macro \| Ece \| Aurc \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:----------:\|:------:\|:--------:\|:--------:\|:------:\|:------:\| \| No log \| 1.0 \| 13 \| 1.4712 \| 0.165 \| 0.8966 \| 8.4652 \| 0.165 \| 0.1101 \| 0.2129 \| 0.8342 \| \| No log \| 2.0 \| 26 \| 1.4590 \| 0.165 \| 0.8951 \| 8.1097 \| 0.165 \| 0.1059 \| 0.2034 \| 0.8021 \| \| No log \| 3.0 \| 39 \| 1.4178 \| 0.175 \| 0.8873 \| 6.8095 \| 0.175 \| 0.0813 \| 0.2150 \| 0.7994 \| \| No log \| 4.0 \| 52 \| 1.3342 \| 0.18 \| 0.8702 \| 6.4137 \| 0.18 \| 0.0475 \| 0.2314 \| 0.7558 \| \| No log \| 5.0 \| 65 \| 1.2828 \| 0.2 \| 0.8587 \| 6.1547 \| 0.2000 \| 0.0642 \| 0.2429 \| 0.7009 \| \| No log \| 6.0 \| 78 \| 1.2675 \| 0.205 \| 0.8548 \| 6.1395 \| 0.205 \| 0.0612 \| 0.2348 \| 0.7022 \| \| No log \| 7.0 \| 91 \| 1.0716 \| 0.31 \| 0.7962 \| 6.4589 \| 0.31 \| 0.1241 \| 0.2787 \| 0.4433 \| \| No log \| 8.0 \| 104 \| 1.1184 \| 0.29 \| 0.8126 \| 6.2585 \| 0.29 \| 0.1394 \| 0.2863 \| 0.5819 \| \| No log \| 9.0 \| 117 \| 1.1021 \| 0.31 \| 0.8075 \| 6.0370 \| 0.31 \| 0.1697 \| 0.2834 \| 0.5458 \| \| No log \| 10.0 \| 130 \| 1.0268 \| 0.33 \| 0.7815 \| 6.1370 \| 0.33 \| 0.1921 \| 0.2856 \| 0.5395 \| \| No log \| 11.0 \| 143 \| 1.0290 \| 0.355 \| 0.7759 \| 5.3640 \| 0.3550 \| 0.2143 \| 0.2795 \| 0.4697 \| \| No log \| 12.0 \| 156 \| 0.9169 \| 0.36 \| 0.7262 \| 5.2997 \| 0.36 \| 0.1995 \| 0.2761 \| 0.4070 \| \| No log \| 13.0 \| 169 \| 0.9903 \| 0.36 \| 0.7586 \| 4.9404 \| 0.36 \| 0.2200 \| 0.2832 \| 0.5343 \| \| No log \| 14.0 \| 182 \| 0.9128 \| 0.425 \| 0.7082 \| 4.5862 \| 0.425 \| 0.2706 \| 0.2834 \| 0.3542 \| \| No log \| 15.0 \| 195 \| 1.0046 \| 0.405 \| 0.7441 \| 3.9763 \| 0.405 \| 0.2759 \| 0.3142 \| 0.4602 \| \| No log \| 16.0 \| 208 \| 0.9277 \| 0.41 \| 0.7146 \| 4.3670 \| 0.41 \| 0.2763 \| 0.2695 \| 0.4409 \| \| No log \| 17.0 \| 221 \| 0.9726 \| 0.505 \| 0.7208 \| 3.5350 \| 0.505 \| 0.3736 \| 0.3332 \| 0.3469 \| \| No log \| 18.0 \| 234 \| 0.7717 \| 0.505 \| 0.6280 \| 3.4386 \| 0.505 \| 0.3412 \| 0.2564 \| 0.2567 \| \| No log \| 19.0 \| 247 \| 0.7723 \| 0.58 \| 0.6143 \| 3.6207 \| 0.58 \| 0.4125 \| 0.3178 \| 0.1847 \| \| No log \| 20.0 \| 260 \| 0.8182 \| 0.57 \| 0.6419 \| 3.1633 \| 0.57 \| 0.4855 \| 0.3517 \| 0.2530 \| \| No log \| 21.0 \| 273 \| 0.7333 \| 0.58 \| 0.5891 \| 3.3014 \| 0.58 \| 0.4512 \| 0.2718 \| 0.2137 \| \| No log \| 22.0 \| 286 \| 0.7374 \| 0.665 \| 0.5856 \| 3.0299 \| 0.665 \| 0.5432 \| 0.3459 \| 0.1657 \| \| No log \| 23.0 \| 299 \| 0.7083 \| 0.645 \| 0.5564 \| 3.0874 \| 0.645 \| 0.5180 \| 0.3112 \| 0.1608 \| \| No log \| 24.0 \| 312 \| 0.7480 \| 0.64 \| 0.5901 \| 3.0218 \| 0.64 \| 0.5410 \| 0.3701 \| 0.1976 \| \| No log \| 25.0 \| 325 \| 0.7547 \| 0.68 \| 0.5894 \| 2.9002 \| 0.68 \| 0.5801 \| 0.3817 \| 0.1559 \| \| No log \| 26.0 \| 338 \| 0.6998 \| 0.65 \| 0.5474 \| 2.9402 \| 0.65 \| 0.5468 \| 0.2875 \| 0.1707 \| \| No log \| 27.0 \| 351 \| 0.6967 \| 0.66 \| 0.5506 \| 2.8344 \| 0.66 \| 0.5578 \| 0.3105 \| 0.1707 \| \| No log \| 28.0 \| 364 \| 0.6733 \| 0.655 \| 0.5332 \| 2.6492 \| 0.655 \| 0.5719 \| 0.2935 \| 0.1554 \| \| No log \| 29.0 \| 377 \| 0.7162 \| 0.67 \| 0.5596 \| 2.7250 \| 0.67 \| 0.5721 \| 0.3388 \| 0.1423 \| \| No log \| 30.0 \| 390 \| 0.6826 \| 0.665 \| 0.5291 \| 2.7460 \| 0.665 \| 0.5797 \| 0.3353 \| 0.1469 \| \| No log \| 31.0 \| 403 \| 0.6761 \| 0.665 \| 0.5195 \| 2.7938 \| 0.665 \| 0.5647 \| 0.3096 \| 0.1485 \| \| No log \| 32.0 \| 416 \| 0.6745 \| 0.695 \| 0.5295 \| 2.6172 \| 0.695 \| 0.6160 \| 0.3171 \| 0.1636 \| \| No log \| 33.0 \| 429 \| 0.6785 \| 0.695 \| 0.5242 \| 2.5816 \| 0.695 \| 0.6115 \| 0.3475 \| 0.1349 \| \| No log \| 34.0 \| 442 \| 0.6688 \| 0.665 \| 0.5174 \| 2.6401 \| 0.665 \| 0.5833 \| 0.2988 \| 0.1427 \| \| No log \| 35.0 \| 455 \| 0.6767 \| 0.675 \| 0.5275 \| 2.6364 \| 0.675 \| 0.6027 \| 0.3285 \| 0.1483 \| \| No log \| 36.0 \| 468 \| 0.6605 \| 0.695 \| 0.5076 \| 2.6483 \| 0.695 \| 0.6252 \| 0.3127 \| 0.1372 \| \| No log \| 37.0 \| 481 \| 0.6538 \| 0.705 \| 0.5029 \| 2.6284 \| 0.705 \| 0.6340 \| 0.3173 \| 0.1220 \| \| No log \| 38.0 \| 494 \| 0.6610 \| 0.695 \| 0.5102 \| 2.5052 \| 0.695 \| 0.6375 \| 0.3128 \| 0.1298 \| \| 0.7532 \| 39.0 \| 507 \| 0.6618 \| 0.695 \| 0.5110 \| 2.5663 \| 0.695 \| 0.6268 \| 0.3297 \| 0.1367 \| \| 0.7532 \| 40.0 \| 520 \| 0.6749 \| 0.69 \| 0.5235 \| 2.5343 \| 0.69 \| 0.6341 \| 0.3256 \| 0.1332 \| \| 0.7532 \| 41.0 \| 533 \| 0.6574 \| 0.695 \| 0.5062 \| 2.4223 \| 0.695 \| 0.6338 \| 0.3292 \| 0.1469 \| \| 0.7532 \| 42.0 \| 546 \| 0.6530 \| 0.695 \| 0.5026 \| 2.6189 \| 0.695 \| 0.6390 \| 0.2950 \| 0.1391 \| \| 0.7532 \| 43.0 \| 559 \| 0.6509 \| 0.685 \| 0.5003 \| 2.5417 \| 0.685 \| 0.6299 \| 0.3150 \| 0.1368 \| \| 0.7532 \| 44.0 \| 572 \| 0.6520 \| 0.71 \| 0.5030 \| 2.4796 \| 0.7100 \| 0.6453 \| 0.3251 \| 0.1286 \| \| 0.7532 \| 45.0 \| 585 \| 0.6494 \| 0.69 \| 0.4994 \| 2.5431 \| 0.69 \| 0.6327 \| 0.3138 \| 0.1279 \| \| 0.7532 \| 46.0 \| 598 \| 0.6515 \| 0.71 \| 0.5007 \| 2.5295 \| 0.7100 \| 0.6541 \| 0.3307 \| 0.1208 \| \| 0.7532 \| 47.0 \| 611 \| 0.6477 \| 0.69 \| 0.4979 \| 2.5971 \| 0.69 \| 0.6323 \| 0.3263 \| 0.1281 \| \| 0.7532 \| 48.0 \| 624 \| 0.6495 \| 0.7 \| 0.5007 \| 2.6162 \| 0.7 \| 0.6395 \| 0.3412 \| 0.1272 \| \| 0.7532 \| 49.0 \| 637 \| 0.6478 \| 0.7 \| 0.4968 \| 2.4946 \| 0.7 \| 0.6386 \| 0.3191 \| 0.1309 \| \| 0.7532 \| 50.0 \| 650 \| 0.6500 \| 0.69 \| 0.5003 \| 2.5629 \| 0.69 \| 0.6350 \| 0.3098 \| 0.1329 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3
mehle/anders	mehle	2023-10-03T18:22:33Z	0	0	null	[ "audio-to-audio", "da", "en", "license:apache-2.0", "region:us" ]	audio-to-audio	2023-10-03T18:21:37Z	--- license: apache-2.0 language: - da - en pipeline_tag: audio-to-audio ---
teknium/airoboros-mistral2.2-7b	teknium	2023-10-03T18:18:12Z	62	36	transformers	[ "transformers", "pytorch", "mistral", "text-generation", "llama-2", "instruct", "finetune", "alpaca", "gpt4", "synthetic data", "distillation", "en", "dataset:jondurbin/airoboros-2.2.1", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-10-03T15:07:51Z	--- base_model: mistralai/Mistral-7b-V0.1 tags: - llama-2 - instruct - finetune - alpaca - gpt4 - synthetic data - distillation datasets: - jondurbin/airoboros-2.2.1 model-index: - name: airoboros2.2-mistral-7b results: [] license: mit language: - en --- Mistral trained with the airoboros dataset! ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/sbN_PCdxO_LV0xpFGA_St.png) Actual dataset is airoboros 2.2, but it seems to have been replaced on hf with 2.2.1. Prompt Format: ``` USER: <prompt> ASSISTANT: ``` TruthfulQA: ``` hf-causal-experimental (pretrained=/home/teknium/dakota/lm-evaluation-harness/airoboros2.2-mistral/,dtype=float16), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8 \| Task \|Version\|Metric\|Value \| \|Stderr\| \|-------------\|------:\|------\|-----:\|---\|-----:\| \|truthfulqa_mc\| 1\|mc1 \|0.3562\|± \|0.0168\| \| \| \|mc2 \|0.5217\|± \|0.0156\| ``` Wandb training charts: https://wandb.ai/teknium1/airoboros-mistral-7b/runs/airoboros-mistral-1?workspace=user-teknium1 More info to come
LoneStriker/dolphin-2.0-mistral-7b-6.0bpw-h6-exl2	LoneStriker	2023-10-03T17:59:38Z	5	0	transformers	[ "transformers", "pytorch", "mistral", "text-generation", "conversational", "en", "dataset:ehartford/dolphin", "dataset:jondurbin/airoboros-2.2.1", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-10-03T17:32:05Z	--- license: apache-2.0 datasets: - ehartford/dolphin - jondurbin/airoboros-2.2.1 language: - en --- Dolphin 2.0 🐬 https://erichartford.com/dolphin Dolphin-2.0-mistral-7b's training was sponsored by [a16z](https://a16z.com/supporting-the-open-source-ai-community/). This model is based on mistralAI, so it is suitable for commercial or non-commercial use. This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly. ## Dataset This dataset is Dolphin, an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/) I modified the dataset for uncensoring, deduping, cleaning, and quality. I added Jon Durbin's excellent Airoboros dataset to increase creativity. ## Training It took 48 hours to train 10 epochs on 4x A100s. Prompt format: This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format. ``` <\|im_start\|>system You are Dolphin, a helpful AI assistant.<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> ``` Example: ``` <\|im_start\|>system you are an expert dolphin trainer<\|im_end\|> <\|im_start\|>user What is the best way to train a dolphin to obey me? Please answer step by step.<\|im_end\|> ``` ## Gratitude - This model was made possible by the generous sponsorship of a16z. - Thank you to Microsoft for authoring the Orca paper and inspiring this work. - Special thanks to WingLian, and TheBloke for helpful advice - Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way. ## Example Output ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/xnz5M1lYd4oGVATSDRkQ-.png) [Buy me a coffee](https://www.buymeacoffee.com/ehartford)
Dugald/MarketingModel	Dugald	2023-10-03T17:29:13Z	0	0	peft	[ "peft", "region:us" ]	null	2023-10-03T17:29:07Z	--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.0.dev0
Bainbridge/umberto-uncased-covid-sentiment	Bainbridge	2023-10-03T17:16:42Z	106	0	transformers	[ "transformers", "pytorch", "camembert", "text-classification", "generated_from_trainer", "base_model:Musixmatch/umberto-wikipedia-uncased-v1", "base_model:finetune:Musixmatch/umberto-wikipedia-uncased-v1", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2023-10-03T17:16:17Z	--- base_model: Musixmatch/umberto-wikipedia-uncased-v1 tags: - generated_from_trainer metrics: - f1 model-index: - name: umberto-wikipedia-uncased-v1 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # umberto-wikipedia-uncased-v1 This model is a fine-tuned version of [Musixmatch/umberto-wikipedia-uncased-v1](https://huggingface.co/Musixmatch/umberto-wikipedia-uncased-v1) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4643 - F1: 0.6160 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 128 - eval_batch_size: 32 - seed: 0 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.05 - num_epochs: 5.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| 0.5923 \| 0.33 \| 20 \| 0.6075 \| 0.2974 \| \| 0.6694 \| 0.67 \| 40 \| 0.5938 \| 0.2974 \| \| 0.5225 \| 1.0 \| 60 \| 0.5346 \| 0.3024 \| \| 0.5458 \| 1.33 \| 80 \| 0.5172 \| 0.4682 \| \| 0.5052 \| 1.67 \| 100 \| 0.5550 \| 0.4361 \| \| 0.3689 \| 2.0 \| 120 \| 0.5188 \| 0.4395 \| \| 0.4097 \| 2.33 \| 140 \| 0.4918 \| 0.4676 \| \| 0.4904 \| 2.67 \| 160 \| 0.4756 \| 0.4640 \| \| 0.3696 \| 3.0 \| 180 \| 0.4788 \| 0.4688 \| \| 0.3631 \| 3.33 \| 200 \| 0.4751 \| 0.4735 \| \| 0.4345 \| 3.67 \| 220 \| 0.4609 \| 0.4797 \| \| 0.3398 \| 4.0 \| 240 \| 0.4637 \| 0.5673 \| \| 0.2985 \| 4.33 \| 260 \| 0.4850 \| 0.5092 \| \| 0.3248 \| 4.67 \| 280 \| 0.5089 \| 0.6057 \| \| 0.3323 \| 5.0 \| 300 \| 0.4643 \| 0.6160 \| ### Framework versions - Transformers 4.34.0.dev0 - Pytorch 2.1.0.dev20230628+cu121 - Datasets 2.14.5 - Tokenizers 0.14.0
TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ	TheBloke	2023-10-03T17:12:08Z	100	2	transformers	[ "transformers", "safetensors", "llama", "text-generation", "en", "dataset:cerebras/SlimPajama-627B", "dataset:bigcode/starcoderdata", "base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-480k-1T", "base_model:quantized:TinyLlama/TinyLlama-1.1B-intermediate-step-480k-1T", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]	text-generation	2023-10-03T17:06:23Z	--- base_model: PY007/TinyLlama-1.1B-intermediate-step-480k-1T datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata inference: false language: - en license: apache-2.0 model_creator: Zhang Peiyuan model_name: TinyLlama 1.1B Intermediate Step 480K 1T model_type: tinyllama prompt_template: '<\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ' quantized_by: TheBloke --- <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # TinyLlama 1.1B Intermediate Step 480K 1T - GPTQ - Model creator: [Zhang Peiyuan](https://huggingface.co/PY007) - Original model: [TinyLlama 1.1B Intermediate Step 480K 1T](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-480k-1T) <!-- description start --> ## Description This repo contains GPTQ model files for [Zhang Peiyuan's TinyLlama 1.1B Intermediate Step 480K 1T](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-480k-1T). Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them. <!-- description end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF) * [Zhang Peiyuan's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-480k-1T) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: ChatML ``` <\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ``` <!-- prompt-template end --> <!-- README_GPTQ.md-provided-files start --> ## Provided files, and GPTQ parameters Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements. Each separate quant is in a different branch. See below for instructions on fetching from different branches. Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers. <details> <summary>Explanation of GPTQ parameters</summary> - Bits: The bit size of the quantised model. - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value. - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now. - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy. - GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s). - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences. - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit. </details> \| Branch \| Bits \| GS \| Act Order \| Damp % \| GPTQ Dataset \| Seq Len \| Size \| ExLlama \| Desc \| \| ------ \| ---- \| -- \| --------- \| ------ \| ------------ \| ------- \| ---- \| ------- \| ---- \| \| [main](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/main) \| 4 \| 128 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 2048 \| 0.77 GB \| No \| 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. \| \| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/gptq-4bit-32g-actorder_True) \| 4 \| 32 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 2048 \| 0.82 GB \| No \| 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. \| \| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/gptq-8bit--1g-actorder_True) \| 8 \| None \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 2048 \| 1.23 GB \| No \| 8-bit, with Act Order. No group size, to lower VRAM requirements. \| \| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/gptq-8bit-128g-actorder_True) \| 8 \| 128 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 2048 \| 1.26 GB \| No \| 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. \| \| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/gptq-8bit-32g-actorder_True) \| 8 \| 32 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 2048 \| 1.32 GB \| No \| 8-bit, with group size 32g and Act Order for maximum inference quality. \| \| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/gptq-4bit-64g-actorder_True) \| 4 \| 64 \| Yes \| 0.1 \| [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) \| 2048 \| 0.79 GB \| No \| 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. \| <!-- README_GPTQ.md-provided-files end --> <!-- README_GPTQ.md-download-from-branches start --> ## How to download, including from branches ### In text-generation-webui To download from the `main` branch, enter `TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ` in the "Download model" box. To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ:gptq-4bit-32g-actorder_True` ### From the command line I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` To download the `main` branch to a folder called `TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ`: ```shell mkdir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ huggingface-cli download TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --local-dir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: ```shell mkdir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ huggingface-cli download TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model. The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`. For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell mkdir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --local-dir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> ### With `git` (not recommended) To clone a specific branch with `git`, use a command like this: ```shell git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ ``` Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.) <!-- README_GPTQ.md-download-from-branches end --> <!-- README_GPTQ.md-text-generation-webui start --> ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui). Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui). It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install. 1. Click the Model tab. 2. Under Download custom model or LoRA, enter `TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ`. - To download from a specific branch, enter for example `TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ:gptq-4bit-32g-actorder_True` - see Provided Files above for the list of branches for each option. 3. Click Download. 4. The model will start downloading. Once it's finished it will say "Done". 5. In the top left, click the refresh icon next to Model. 6. In the Model dropdown, choose the model you just downloaded: `TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ` 7. The model will automatically load, and is now ready for use! 8. If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right. * Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`. 9. Once you're ready, click the Text Generation tab and enter a prompt to get started! <!-- README_GPTQ.md-text-generation-webui end --> <!-- README_GPTQ.md-use-from-tgi start --> ## Serving this model from Text Generation Inference (TGI) It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0` Example Docker parameters: ```shell --model-id TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096 ``` Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later): ```shell pip3 install huggingface-hub ``` ```python from huggingface_hub import InferenceClient endpoint_url = "https://your-endpoint-url-here" prompt = "Tell me about AI" prompt_template=f'''<\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ''' client = InferenceClient(endpoint_url) response = client.text_generation(prompt, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1) print(f"Model output: {response}") ``` <!-- README_GPTQ.md-use-from-tgi end --> <!-- README_GPTQ.md-use-from-python start --> ## How to use this GPTQ model from Python code ### Install the necessary packages Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later. ```shell pip3 install transformers optimum pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7 ``` If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead: ```shell pip3 uninstall -y auto-gptq git clone https://github.com/PanQiWei/AutoGPTQ cd AutoGPTQ git checkout v0.4.2 pip3 install . ``` ### You can then use the following code ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_name_or_path = "TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ" # To use a different branch, change revision # For example: revision="gptq-4bit-32g-actorder_True" model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=False, revision="main") tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) prompt = "Tell me about AI" prompt_template=f'''<\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ''' print("\n\n* Generate:") input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda() output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512) print(tokenizer.decode(output[0])) # Inference can also be done using transformers' pipeline print("* Pipeline:") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1 ) print(pipe(prompt_template)[0]['generated_text']) ``` <!-- README_GPTQ.md-use-from-python end --> <!-- README_GPTQ.md-compatibility start --> ## Compatibility The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI). [ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility. [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models. <!-- README_GPTQ.md-compatibility end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI Special thanks to: Aemon Algiz. Patreon special mentions: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> # Original model card: Zhang Peiyuan's TinyLlama 1.1B Intermediate Step 480K 1T <div align="center"> # TinyLlama-1.1B </div> https://github.com/jzhang38/TinyLlama The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. <div align="center"> <img src="./TinyLlama_logo.png" width="300"/> </div> We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint. #### This Model This is an intermediate checkpoint with 480K steps and 1007B tokens. #### How to use You will need the transformers>=4.31 Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information. ```python from transformers import AutoTokenizer import transformers import torch model = "PY007/TinyLlama-1.1B-intermediate-step-240k-503b" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) sequences = pipeline( 'The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.', do_sample=True, top_k=10, num_return_sequences=1, repetition_penalty=1.5, eos_token_id=tokenizer.eos_token_id, max_length=500, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ```
TheBloke/em_german_mistral_v01-GPTQ	TheBloke	2023-10-03T17:05:54Z	17	5	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "pytorch", "llama", "llama-2", "german", "deutsch", "de", "base_model:jphme/em_german_mistral_v01", "base_model:quantized:jphme/em_german_mistral_v01", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]	text-generation	2023-10-03T16:25:06Z	--- base_model: jphme/em_german_mistral_v01 inference: false language: - de library_name: transformers license: apache-2.0 model_creator: Jan Philipp Harries model_name: EM German Mistral v01 model_type: mistral pipeline_tag: text-generation prompt_template: 'Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT: ' quantized_by: TheBloke tags: - mistral - pytorch - llama - llama-2 - german - deutsch --- <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # EM German Mistral v01 - GPTQ - Model creator: [Jan Philipp Harries](https://huggingface.co/jphme) - Original model: [EM German Mistral v01](https://huggingface.co/jphme/em_german_mistral_v01) <!-- description start --> ## Description This repo contains GPTQ model files for [Jan Philipp Harries's EM German Mistral v01](https://huggingface.co/jphme/em_german_mistral_v01). Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them. <!-- description end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/em_german_mistral_v01-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF) * [Jan Philipp Harries's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jphme/em_german_mistral_v01) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: EmGerman ``` Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT: ``` <!-- prompt-template end --> <!-- README_GPTQ.md-provided-files start --> ## Provided files, and GPTQ parameters Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements. Each separate quant is in a different branch. See below for instructions on fetching from different branches. Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers. <details> <summary>Explanation of GPTQ parameters</summary> - Bits: The bit size of the quantised model. - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value. - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now. - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy. - GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s). - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences. - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit. </details> \| Branch \| Bits \| GS \| Act Order \| Damp % \| GPTQ Dataset \| Seq Len \| Size \| ExLlama \| Desc \| \| ------ \| ---- \| -- \| --------- \| ------ \| ------------ \| ------- \| ---- \| ------- \| ---- \| \| [main](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/main) \| 4 \| 128 \| Yes \| 0.1 \| [German Quad](https://huggingface.co/datasets/deepset/germanquad) \| 8192 \| 4.16 GB \| Yes \| 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. \| \| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/gptq-4bit-32g-actorder_True) \| 4 \| 32 \| Yes \| 0.1 \| [German Quad](https://huggingface.co/datasets/deepset/germanquad) \| 8192 \| 4.57 GB \| Yes \| 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. \| \| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/gptq-8bit--1g-actorder_True) \| 8 \| None \| Yes \| 0.1 \| [German Quad](https://huggingface.co/datasets/deepset/germanquad) \| 8192 \| 7.52 GB \| No \| 8-bit, with Act Order. No group size, to lower VRAM requirements. \| \| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/gptq-8bit-128g-actorder_True) \| 8 \| 128 \| Yes \| 0.1 \| [German Quad](https://huggingface.co/datasets/deepset/germanquad) \| 8192 \| 7.68 GB \| No \| 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. \| \| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/gptq-8bit-32g-actorder_True) \| 8 \| 32 \| Yes \| 0.1 \| [German Quad](https://huggingface.co/datasets/deepset/germanquad) \| 8192 \| 8.17 GB \| No \| 8-bit, with group size 32g and Act Order for maximum inference quality. \| \| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/gptq-4bit-64g-actorder_True) \| 4 \| 64 \| Yes \| 0.1 \| [German Quad](https://huggingface.co/datasets/deepset/germanquad) \| 8192 \| 4.29 GB \| Yes \| 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. \| <!-- README_GPTQ.md-provided-files end --> <!-- README_GPTQ.md-download-from-branches start --> ## How to download, including from branches ### In text-generation-webui To download from the `main` branch, enter `TheBloke/em_german_mistral_v01-GPTQ` in the "Download model" box. To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/em_german_mistral_v01-GPTQ:gptq-4bit-32g-actorder_True` ### From the command line I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` To download the `main` branch to a folder called `em_german_mistral_v01-GPTQ`: ```shell mkdir em_german_mistral_v01-GPTQ huggingface-cli download TheBloke/em_german_mistral_v01-GPTQ --local-dir em_german_mistral_v01-GPTQ --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: ```shell mkdir em_german_mistral_v01-GPTQ huggingface-cli download TheBloke/em_german_mistral_v01-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir em_german_mistral_v01-GPTQ --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model. The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`. For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell mkdir em_german_mistral_v01-GPTQ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/em_german_mistral_v01-GPTQ --local-dir em_german_mistral_v01-GPTQ --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> ### With `git` (not recommended) To clone a specific branch with `git`, use a command like this: ```shell git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ ``` Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.) <!-- README_GPTQ.md-download-from-branches end --> <!-- README_GPTQ.md-text-generation-webui start --> ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui). Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui). It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install. 1. Click the Model tab. 2. Under Download custom model or LoRA, enter `TheBloke/em_german_mistral_v01-GPTQ`. - To download from a specific branch, enter for example `TheBloke/em_german_mistral_v01-GPTQ:gptq-4bit-32g-actorder_True` - see Provided Files above for the list of branches for each option. 3. Click Download. 4. The model will start downloading. Once it's finished it will say "Done". 5. In the top left, click the refresh icon next to Model. 6. In the Model dropdown, choose the model you just downloaded: `em_german_mistral_v01-GPTQ` 7. The model will automatically load, and is now ready for use! 8. If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right. * Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`. 9. Once you're ready, click the Text Generation tab and enter a prompt to get started! <!-- README_GPTQ.md-text-generation-webui end --> <!-- README_GPTQ.md-use-from-tgi start --> ## Serving this model from Text Generation Inference (TGI) It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0` Example Docker parameters: ```shell --model-id TheBloke/em_german_mistral_v01-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096 ``` Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later): ```shell pip3 install huggingface-hub ``` ```python from huggingface_hub import InferenceClient endpoint_url = "https://your-endpoint-url-here" prompt = "Tell me about AI" prompt_template=f'''Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT: ''' client = InferenceClient(endpoint_url) response = client.text_generation(prompt, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1) print(f"Model output: {response}") ``` <!-- README_GPTQ.md-use-from-tgi end --> <!-- README_GPTQ.md-use-from-python start --> ## How to use this GPTQ model from Python code ### Install the necessary packages Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later. ```shell pip3 install transformers optimum pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7 ``` If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead: ```shell pip3 uninstall -y auto-gptq git clone https://github.com/PanQiWei/AutoGPTQ cd AutoGPTQ git checkout v0.4.2 pip3 install . ``` ### You can then use the following code ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_name_or_path = "TheBloke/em_german_mistral_v01-GPTQ" # To use a different branch, change revision # For example: revision="gptq-4bit-32g-actorder_True" model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=False, revision="main") tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) prompt = "Tell me about AI" prompt_template=f'''Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT: ''' print("\n\n* Generate:") input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda() output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512) print(tokenizer.decode(output[0])) # Inference can also be done using transformers' pipeline print("* Pipeline:") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1 ) print(pipe(prompt_template)[0]['generated_text']) ``` <!-- README_GPTQ.md-use-from-python end --> <!-- README_GPTQ.md-compatibility start --> ## Compatibility The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI). [ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility. [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models. <!-- README_GPTQ.md-compatibility end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI Special thanks to: Aemon Algiz. Patreon special mentions: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> # Original model card: Jan Philipp Harries's EM German Mistral v01 ![EM Logo](em_model_logo_web.jpeg) # EM German Mistral 7b (Alpha) ([Zur deutschen Version](#deutsch-em-german)) EM German (v01) is an experimental llama2 and mistral-based model family, finetuned on a large dataset of various instructions in German language. The models are optimized for German text, providing proficiency in understanding, generating, and interacting with German language content. This is a very first experimental version of Mistrals 7b model. This is still based on the HF LLama Model and not on the Mistral implementation, lacking features like GQA and sliding windows - use at your own discretion. For more mature models, please look at the llama-2 based models of the EM family (see links below). # Links & Demos We will publish further instructions, updates and code-snippets in the project's [Github-Repo](https://github.com/jphme/EM_German). ## Model Links \| Base Model \| HF \| GPTQ \| GGUF \| AWQ \| \|-------\|-------\|-------\|-------\|-------\| \| [Llama2](https://huggingface.co/meta-llama/Llama-2-7b-hf) 7b \| [Link](https://huggingface.co/jphme/em_german_7b_v01) \| [Link](https://huggingface.co/jphme/em_german_7b_v01_gptq) \| [Link](https://huggingface.co/jphme/em_german_7b_v01_gguf) \| soon \| \| [Llama2](https://huggingface.co/meta-llama/Llama-2-13b-hf) 13b \| [Link](https://huggingface.co/jphme/em_german_13b_v01) \| [Link](https://huggingface.co/jphme/em_german_13b_v01_gptq) \| soon \| soon \| \| [Llama2](https://huggingface.co/meta-llama/Llama-2-70b-hf) 70b \| [Link](https://huggingface.co/jphme/em_german_70b_v01) \| [Link](https://huggingface.co/jphme/em_german_70b_v01_gptq) \| [Link](https://huggingface.co/jphme/em_german_70b_v01_gguf) \| soon \| \| [Mistral 7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) \| [Link](https://huggingface.co/jphme/em_german_mistral_v01) \| soon \| soon \| tbc \| \| [LeoLm 7b](https://huggingface.co/LeoLM/leo-hessianai-7b) \| soon \| soon \| soon \| tbc \| \| [LeoLM 13b](https://huggingface.co/LeoLM/leo-hessianai-7b) \| soon \| soon \| soon \| tbc \| ## Demos: You can use some of the models with free google Colab instances (e.g. the 7bn model in 8bit or the 13b model with GPTQ): * [Example Colab Notebook for 13b with GPTQ](https://colab.research.google.com/drive/1IJfJdVwGkfe5MYOqHptystR3FBeEUdGn?usp=sharing) * [Example Colab Notebook for 7b with 8bit-Loading](https://colab.research.google.com/drive/1bsv6vkLM4AlCpSyXA6ol9P32zxZmf7Zu?usp=sharing) * Further Examples for LLM apps will follow soon... # Prompt Format This model follows the Vicuna format without linebreaks (but should work with linebreaks as well). The format is as follows: ``` Du bist ein hilfreicher Assistent. USER: <instruction> ASSISTANT: ``` You can swap the standard system prompt for a better suited one (see below for RAG-tasks). # Results Attached a few example outputs. I also developed a few small German benchmarks (based on the Eleuther LM Evaluation Harness), which I will publish soon. ## Example Output Prompt: ``` Du bist ein hilfreicher Assistent USER: Ein Buch hat 500 Seiten. Jede Seite enthält 300 Wörter. Wie viele Wörter sind im gesamten Buch enthalten? ASSISTANT: ``` Response EM 7b v01 ``` Die Gesamtzahl der Wörter in dem Buch kann berechnet werden, indem man die Anzahl der Wörter pro Seite mit der Gesamtzahl der Seiten multipliziert. Gesamtzahl der Wörter = Anzahl der Wörter pro Seite * Gesamtzahl der Seiten = 300 Wörter pro Seite * 500 Seiten = 150.000 Wörter Das Buch enthält also insgesamt 150.000 Wörter. ``` Prompt: ``` Du bist ein hilfreicher Assistent USER: Erläutere die Grundprinzipien der evolutionären Biologie und Genetik, indem du den Prozess der natürlichen Selektion, die Rolle von Mutationen und genetischer Drift sowie das Konzept der adaptiven Radiation erklärst. ASSISTANT: ``` Response EM 7b v01 ``` Die Evolutionäre Biologie und Genetik sind zwei intim verwandte Disziplinen, die sich mit dem Studium des Verhaltens und der Entwicklung von Organismen in der Natur befassen. Sie untersuchen, wie Arten sich im Laufe der Zeit entwickeln und wie diese Veränderungen genetisch bedingt sind. 1. Natürliche Selektion: Die natürliche Selektion ist ein grundlegendes Prinzip in der Evolutionäre Biologie. Es besagt, dass Individuen innerhalb einer Spezies unterschiedliche Fähigkeiten oder Merkmale aufweisen können. Diese Merkmale beeinflussen ihre Überlebens- und Fortpflanzungsrate. Diejenigen mit Vorteilen haben eine höhere Wahrscheinlichkeit, ihre Gene an zukünftige Generationen weiterzugeben und so die Art im Laufe der Zeit zu verändern. 2. Rolle von Mutationen: Mutationen sind Veränderungen im Genom eines Organismus, die entweder durch zufällige Fehler während der Replikation oder durch Exposition gegenüber Strahlung verursacht werden. Diese Veränderungen können dazu führen, dass ein Individuum neue Eigenschaften aufweist, die es im Kampf ums Überleben vorteilhaft machen könnten. Diese Mutationen werden dann von der natürlichen Selektion beeinflusst und können so zur Entwicklung neuer Arten beitragen. 3. Genetische Drift: Genetische Drift ist ein zufälliger Prozess, der durch die Verteilung von Allelen in einer Population stattfindet. Wenn eine Population kleiner wird oder wenn die Überlebens- und Fortpflanzungsraten zwischen den Individuen variieren, kann dies dazu führen, dass bestimmte Gene stärker oder weniger häufig werden. Dies kann dazu führen, dass die Population im Laufe der Zeit unterschiedliche Merkmale aufweist. 4. Adaptive Radiation: Adaptive Radiation ist ein Prozess, bei dem eine Art mehrere verschiedene Linien auslässt, die sich auf verschiedene Weise an ihre Umgebung anpassen. Dies geschieht normalerweise, wenn die Umwelt sich ändert und die Art neue Fähigkeiten benötigt, um überleben zu können. Die verschiedenen Linien können dann unterschiedliche Eigenschaften entwickeln, die ihnen helfen, in dieser neuen Umgebung zu überleben. ``` ## Factual Retrieval / RAG EM Models offer a special format for Factual Retrieval/RAG that is optimized for minimizing hallucinations. We use the same format as Airoboros for this: ### Example Prompt ``` Du bist ein hilfreicher Assistent. Für die folgende Aufgabe stehen dir zwischen den tags BEGININPUT und ENDINPUT mehrere Quellen zur Verfügung. Metadaten zu den einzelnen Quellen wie Autor, URL o.ä. sind zwischen BEGINCONTEXT und ENDCONTEXT zu finden, danach folgt der Text der Quelle. Die eigentliche Aufgabe oder Frage ist zwischen BEGININSTRUCTION und ENDINCSTRUCTION zu finden. Beantworte diese wortwörtlich mit einem Zitat aus den Quellen. Sollten diese keine Antwort enthalten, antworte, dass auf Basis der gegebenen Informationen keine Antwort möglich ist! USER: BEGININPUT BEGINCONTEXT Url: https://www.jph.me ENDCONTEXT Das Wetter in Düsseldorf wird heute schön und sonnig! ENDINPUT BEGININSTRUCTION Was ist 1+1? ENDINSTRUCTION ASSISTANT: ``` Model response: ``` Mit den gegebenen Informationen ist diese Frage nicht zu beantworten. ``` Note that the model would normally always answer with the correct response to a trivial question like this but is trained to deny an answer, if there is no source between the BEGININPUT and ENDINPUT that provides a grounding. If we keep the same Context/Input but ask instead: ``` BEGININSTRUCTION Wie wird das Wetter heute in Düsseldorf? Gebe die Quelle mit an! ENDINSTRUCTION ASSISTANT: ``` We get the correct answer with the source: ``` Das Wetter in Düsseldorf wird heute schön und sonnig! (Quelle: Url: https://www.jph.me) ``` # Evaluation I will publish some custom German benchmarks and the results for them soon. # Dataset The dataset is a mixture of multi-turn chats, retrieval instructions and synthetically generated instructions spawning many topics and applications. ## Use with tranformers Unchanged from the base model: ```python import torch from transformers import LlamaForCausalLM, LlamaTokenizer # Hugging Face model_path model_path = 'jphme/em_german_7b_v01' tokenizer = LlamaTokenizer.from_pretrained(model_path) model = LlamaForCausalLM.from_pretrained( model_path, torch_dtype=torch.float16, device_map='auto', ) def ask_model(instruction, system='Du bist ein hilfreicher Assistent.'): prompt=f"{system} USER: {instruction} ASSISTANT:" input_tokens=tokenizer(prompt, return_tensors="pt").to(model.device) output_tokens=model.generate(*input_tokens, max_new_tokens=200)[0] answer=tokenizer.decode(output_tokens, skip_special_tokens=True) return answer print(ask_model("Nenne mir 10 gute Gründe dafür, heute Sport zu machen!")) ``` # Limitations & Biases This model can produce factually incorrect output, and should not be relied on to produce factually accurate information. This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs. # Acknowledgements: Many thanks to [winglian/caseus](https://huggingface.co/winglian) for his great work on Axolotl which I used to train the EM mdoels. I am also grateful to [Jon Durbin](https://huggingface.co/jondurbin) and his [Airoboros](https://huggingface.co/jondurbin/airoboros-l2-70b-2.2.1) models and code from which I borrowed many ideas and code snippets. The 70b model was trained with support of the [OVH Cloud Startup Program](https://startup.ovhcloud.com/en/). # Contact I you are interested in customized LLMs for business applications, please get in contact with me via [my website](https://www.jph.me). I am also always happy about suggestions and feedback. PS: I am also still searching for a Co-Founder. # Disclaimer: The license on this model does not constitute legal advice. I am not responsible for the actions of third parties who use this model. This model should only be used for research purposes. The original Llama2 license applies and is distributed with the model files. ------------- ------------- ------------- # (Deutsch) EM German EM German (v01)* ist eine experimentelle, Llama2-basierte KI-Modellreihe, die in deutscher Sprache fine-getuned wurde. Die Modelle sind für deutschen Text optimiert und können Inhalte in deutscher Sprache verstehen und generieren. Dieses 7b-Modell wurde zusätzlich mit >3 Milliarden Token deutscher Texte vortrainiert. # Links & Demos Im [Github-Repo](https://github.com/jphme/EM_German) Repo werde ich weitere Beispiele und Code-Snippets veröffentlichen. ## Model Links \| Base Model \| HF \| GPTQ \| GGUF \| AWQ \| \|-------\|-------\|-------\|-------\|-------\| \| [Llama2](https://huggingface.co/meta-llama/Llama-2-7b-hf) 7b \| [Link](https://huggingface.co/jphme/em_german_7b_v01) \| [Link](https://huggingface.co/jphme/em_german_7b_v01_gptq) \| [Link](https://huggingface.co/jphme/em_german_7b_v01_gguf) \| soon \| \| [Llama2](https://huggingface.co/meta-llama/Llama-2-13b-hf) 13b \| [Link](https://huggingface.co/jphme/em_german_13b_v01) \| [Link](https://huggingface.co/jphme/em_german_13b_v01_gptq) \| soon \| soon \| \| [Llama2](https://huggingface.co/meta-llama/Llama-2-70b-hf) 70b \| [Link](https://huggingface.co/jphme/em_german_70b_v01) \| [Link](https://huggingface.co/jphme/em_german_70b_v01_gptq) \| [Link](https://huggingface.co/jphme/em_german_70b_v01_gguf) \| soon \| \| [Mistral 7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) \| [Link](https://huggingface.co/jphme/em_german_mistral_v01) \| soon \| soon \| tbc \| \| [LeoLm 7b](https://huggingface.co/LeoLM/leo-hessianai-7b) \| soon \| soon \| soon \| tbc \| \| [LeoLM 13b](https://huggingface.co/LeoLM/leo-hessianai-7b) \| soon \| soon \| soon \| tbc \| ## Colab: Einige der Modelle können mit kostenlosen Google Colab-Instanzen verwendet werden (z.B. das 7b-Modell in 8-Bit oder das 13b-Modell mit GPTQ): * [Beispiel-Notebook 13b mit GPTQ](https://colab.research.google.com/drive/1IJfJdVwGkfe5MYOqHptystR3FBeEUdGn?usp=sharing) * [Beispiel-Notebook 7b mit 8-Bit](https://colab.research.google.com/drive/1bsv6vkLM4AlCpSyXA6ol9P32zxZmf7Zu?usp=sharing) * Weitere Beispiele für LLM-Apps folgen in Kürze... # Eingabeformat Dieses Modell folgt dem Vicuna-Format ohne Zeilenumbrüche (sollte aber auch mit Zeilenumbrüchen funktionieren). Das Format lautet wie folgt: ``` Du bist ein hilfreicher Assistent. USER: <Anweisung> ASSISTANT: ``` Sie können das Standard-Systemprompt aber auch ändern (siehe unten für ein Beispiel bei Aufgaben mit externen Datenbanken). # Ergebnisse Anbei einige Beispiele für Modell-Outputs. Wir werden demnächst einige kleine deutsche Benchmarks veröffentlichen (basierend auf dem Eleuther LM Evaluation Harness), die wir bei diesen Modellen bereits getstet haben. ## Beispiel-Ausgaben Prompt: ``` Du bist ein hilfreicher Assistent USER: Ein Buch hat 500 Seiten. Jede Seite enthält 300 Wörter. Wie viele Wörter sind im gesamten Buch enthalten? ASSISTANT: ``` Antwort EM 7b v01 ``` Die Gesamtzahl der Wörter in dem Buch kann berechnet werden, indem man die Anzahl der Wörter pro Seite mit der Gesamtzahl der Seiten multipliziert. Gesamtzahl der Wörter = Anzahl der Wörter pro Seite * Gesamtzahl der Seiten = 300 Wörter pro Seite * 500 Seiten = 150.000 Wörter Das Buch enthält also insgesamt 150.000 Wörter. ``` Prompt: ``` Du bist ein hilfreicher Assistent USER: Erläutere die Grundprinzipien der evolutionären Biologie und Genetik, indem du den Prozess der natürlichen Selektion, die Rolle von Mutationen und genetischer Drift sowie das Konzept der adaptiven Radiation erklärst. ASSISTANT: ``` Antwort EM 7b v01: ``` Die Evolutionäre Biologie und Genetik sind zwei intim verwandte Disziplinen, die sich mit dem Studium des Verhaltens und der Entwicklung von Organismen in der Natur befassen. Sie untersuchen, wie Arten sich im Laufe der Zeit entwickeln und wie diese Veränderungen genetisch bedingt sind. 1. Natürliche Selektion: Die natürliche Selektion ist ein grundlegendes Prinzip in der Evolutionäre Biologie. Es besagt, dass Individuen innerhalb einer Spezies unterschiedliche Fähigkeiten oder Merkmale aufweisen können. Diese Merkmale beeinflussen ihre Überlebens- und Fortpflanzungsrate. Diejenigen mit Vorteilen haben eine höhere Wahrscheinlichkeit, ihre Gene an zukünftige Generationen weiterzugeben und so die Art im Laufe der Zeit zu verändern. 2. Rolle von Mutationen: Mutationen sind Veränderungen im Genom eines Organismus, die entweder durch zufällige Fehler während der Replikation oder durch Exposition gegenüber Strahlung verursacht werden. Diese Veränderungen können dazu führen, dass ein Individuum neue Eigenschaften aufweist, die es im Kampf ums Überleben vorteilhaft machen könnten. Diese Mutationen werden dann von der natürlichen Selektion beeinflusst und können so zur Entwicklung neuer Arten beitragen. 3. Genetische Drift: Genetische Drift ist ein zufälliger Prozess, der durch die Verteilung von Allelen in einer Population stattfindet. Wenn eine Population kleiner wird oder wenn die Überlebens- und Fortpflanzungsraten zwischen den Individuen variieren, kann dies dazu führen, dass bestimmte Gene stärker oder weniger häufig werden. Dies kann dazu führen, dass die Population im Laufe der Zeit unterschiedliche Merkmale aufweist. 4. Adaptive Radiation: Adaptive Radiation ist ein Prozess, bei dem eine Art mehrere verschiedene Linien auslässt, die sich auf verschiedene Weise an ihre Umgebung anpassen. Dies geschieht normalerweise, wenn die Umwelt sich ändert und die Art neue Fähigkeiten benötigt, um überleben zu können. Die verschiedenen Linien können dann unterschiedliche Eigenschaften entwickeln, die ihnen helfen, in dieser neuen Umgebung zu überleben. ``` ## Sachliche Abfrage / RAG EM-Modelle bieten ein spezielles Format für RAG (also die Verwendung mit Informationen aus zusätzlichen externen Quellen wie Datenbanken oder Websiten), das für die Minimierung von Halluzinationen und Falscinformationen optimiert ist. Wir verwenden dasselbe Format wie Airoboros dafür. ### Beispiel Prompt ``` Du bist ein hilfreicher Assistent. Für die folgende Aufgabe stehen dir zwischen den tags BEGININPUT und ENDINPUT mehrere Quellen zur Verfügung. Metadaten zu den einzelnen Quellen wie Autor, URL o.ä. sind zwischen BEGINCONTEXT und ENDCONTEXT zu finden, danach folgt der Text der Quelle. Die eigentliche Aufgabe oder Frage ist zwischen BEGININSTRUCTION und ENDINCSTRUCTION zu finden. Beantworte diese wortwörtlich mit einem Zitat aus den Quellen. Sollten diese keine Antwort enthalten, antworte, dass auf Basis der gegebenen Informationen keine Antwort möglich ist! USER: BEGININPUT BEGINCONTEXT Url: https://www.jph.me ENDCONTEXT Das Wetter in Düsseldorf wird heute schön und sonnig! ENDINPUT BEGININSTRUCTION Was ist 1+1? ENDINSTRUCTION ASSISTANT: ``` Modellantwort: ``` Mit den gegebenen Informationen ist diese Frage nicht zu beantworten. ``` Hier würde das Modell normalerweise die (triviale) Antwort (2) geben, ist aber trainiert, keine Antwort zu geben, wenn es keine Quelle zwischen BEGININPUT und ENDINPUT gibt, die eine belegbare Antwort liefert. Wenn wir anstattdessen fragen: ``` BEGININSTRUCTION Wie wird das Wetter heute in Düsseldorf? Gebe die Quelle mit an! ENDINSTRUCTION ASSISTANT: ``` Bekommen wir die korrekte Antwort mit Quellenangabe ``` Das Wetter in Düsseldorf wird heute schön und sonnig! (Quelle: Url: https://www.jph.me) ``` # Evaluation coming soon # Datensatz Der Datensatz ist eine Mischung aus Multi-Turn-Chats, RAG Instructions und synthetisch generierten Finetuning-Daten, die viele Themen und Anwendungen abdecken. # Einschränkungen & Vorurteile Dieses Modell kann sachlich falsche Ausgaben produzieren und sollte nur zu Forschubngszwecken verwendet werden. # Danksagungen: Vielen Dank an [winglian/caseus](https://huggingface.co/winglian) für seine großartige Arbeit an Axolotl, die ich zur Schulung der EM-Modelle verwendet habe. Ich bin auch [Jon Durbin](https://huggingface.co/jondurbin) für seine Arioboros Modelle und Code-Schnipsel dankbar, von denen ich viele Ideen nutzen konnte. Das 70b-Modell wurde mit Unterstützung des [OVH Cloud Startup Program](https://startup.ovhcloud.com/en/) trainiert. # Kontakt Wenn Sie an customized LLMs für geschäftliche Anwendungen interessiert sind, kontaktieren Sie mich bitte über [meine Website](https://www.jph.me). Ich freue mich auch immer über Anregungen und Feedback zu meinen Modellen. PS: Ich suche auch immer noch einen Co-Founder für unser Startup, das sich noch im Stealth-Modus befindet. # Haftungsausschluss: Ich bin nicht verantwortlich für die Handlungen Dritter, die dieses Modell verwenden. Dieses Modell sollte nur für Forschungszwecke verwendet werden. Die ursprüngliche Llama2-Lizenz gilt und wird mit den Modell-Dateien verteilt.
jackoyoungblood/speecht5_finetuned_voxpopuli_nl2	jackoyoungblood	2023-10-03T16:58:57Z	82	0	transformers	[ "transformers", "pytorch", "speecht5", "text-to-audio", "generated_from_trainer", "text-to-speech", "dataset:voxpopuli", "base_model:microsoft/speecht5_tts", "base_model:finetune:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]	text-to-speech	2023-10-03T14:58:35Z	--- license: mit base_model: microsoft/speecht5_tts tags: - generated_from_trainer - text-to-speech datasets: - voxpopuli model-index: - name: speecht5_finetuned_voxpopuli_nl2 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # speecht5_finetuned_voxpopuli_nl2 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset. It achieves the following results on the evaluation set: - Loss: 0.4599 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.5247 \| 4.3 \| 1000 \| 0.4807 \| \| 0.4971 \| 8.61 \| 2000 \| 0.4652 \| \| 0.4944 \| 12.91 \| 3000 \| 0.4625 \| \| 0.4913 \| 17.21 \| 4000 \| 0.4599 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
NASA-AIML/MIKA_BERT_FMEA_NER	NASA-AIML	2023-10-03T16:37:10Z	106	1	transformers	[ "transformers", "pytorch", "bert", "token-classification", "NER", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2023-09-12T23:52:41Z	--- license: other language: - en pipeline_tag: token-classification tags: - token-classification - NER library_name: transformers widget: - text: "While flying a fire, the UAS experienced an issue of unknown sorts and crashed to the ground. From the people watching the aircraft near the fire, they seem to think it was some sort of motor failure due to no more noise coming from the aircraft and it falling straight to the ground." example_title: "Example 1" - text: "During a pre-flight engine run-up, a battery hatch cover disengaged from the fuselage and hit one of the vertical takeoff and landing {VTOL} propellers. The motor failsafe activated and the motors shut down." example_title: "Example 2" - text: "UAS was climbing to 11,000 ft. msl on a reconnaissance mission when it experienced a rapid and uncommanded descent. The pilot took no action but monitored instruments until the aircraft regained a stable profile. " example_title: "Example 3" --- # Manager for Intelligent Knowledge Access (MIKA) ## Custom Named-Entity Recognition (NER) for Failure Modes and Effects Analysis (FMEA) base-bert-uncased model first further pre-trained then fine-tuned for custom NER to extract failure-relevant entities from incident and accident reports. The model was trained on manually annotated NASA LLIS reports and evaluated on SAFECOM reports. NER model training was for 4 epochs with:`BertForTokenClassification.from_pretrained` , `learning_rate=2e-5`, ` weight_decay=0.01,` The model was trained to identify the following long-tailed entities: - CAU: failure cause - MOD: failure mode - EFF: failure effect - CON: control process - REC: recommendations Performace: \|Entity \| Precision \|Recall \| F-1 \| Support\| \|-------\|-----------\|-------\|-----\|--------\| \|CAU \| 0.31 \| 0.19 \| 0.23 \| 1634 \| \|CON \| 0.49 \| 0.34 \| 0.40 \| 3859 \| \|EFF \| 0.45 \| 0.20 \| 0.28 \| 1959 \| \|MOD \| 0.19 \| 0.52 \| 0.28 \| 594 \| \|REC \| 0.30 \| 0.59 \| 0.40 \| 954 \| \|Average \| 0.41 \| 0.32 \| 0.33 \| 9000 \| More infomation on training data, evaluation, and intended use can be found in the original publication Citation: S. R. Andrade and H. S. Walsh, "What Went Wrong: A Survey of Wildfire UAS Mishaps through Named Entity Recognition," 2022 IEEE/AIAA 41st Digital Avionics Systems Conference (DASC), Portsmouth, VA, USA, 2022, pp. 1-10, doi: 10.1109/DASC55683.2022.9925798. https://ieeexplore.ieee.org/abstract/document/9925798 * * * * * * * * * * * * * * Notices: Copyright © 2023 United States Government as represented by the Administrator of the National Aeronautics and Space Administration. All Rights Reserved. Disclaimers No Warranty: THE SUBJECT SOFTWARE IS PROVIDED "AS IS" WITHOUT ANY WARRANTY OF ANY KIND, EITHER EXPRESSED, IMPLIED, OR STATUTORY, INCLUDING, BUT NOT LIMITED TO, ANY WARRANTY THAT THE SUBJECT SOFTWARE WILL CONFORM TO SPECIFICATIONS, ANY IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, OR FREEDOM FROM INFRINGEMENT, ANY WARRANTY THAT THE SUBJECT SOFTWARE WILL BE ERROR FREE, OR ANY WARRANTY THAT DOCUMENTATION, IF PROVIDED, WILL CONFORM TO THE SUBJECT SOFTWARE. THIS AGREEMENT DOES NOT, IN ANY MANNER, CONSTITUTE AN ENDORSEMENT BY GOVERNMENT AGENCY OR ANY PRIOR RECIPIENT OF ANY RESULTS, RESULTING DESIGNS, HARDWARE, SOFTWARE PRODUCTS OR ANY OTHER APPLICATIONS RESULTING FROM USE OF THE SUBJECT SOFTWARE. FURTHER, GOVERNMENT AGENCY DISCLAIMS ALL WARRANTIES AND LIABILITIES REGARDING THIRD-PARTY SOFTWARE, IF PRESENT IN THE ORIGINAL SOFTWARE, AND DISTRIBUTES IT "AS IS." Waiver and Indemnity: RECIPIENT AGREES TO WAIVE ANY AND ALL CLAIMS AGAINST THE UNITED STATES GOVERNMENT, ITS CONTRACTORS AND SUBCONTRACTORS, AS WELL AS ANY PRIOR RECIPIENT. IF RECIPIENT'S USE OF THE SUBJECT SOFTWARE RESULTS IN ANY LIABILITIES, DEMANDS, DAMAGES, EXPENSES OR LOSSES ARISING FROM SUCH USE, INCLUDING ANY DAMAGES FROM PRODUCTS BASED ON, OR RESULTING FROM, RECIPIENT'S USE OF THE SUBJECT SOFTWARE, RECIPIENT SHALL INDEMNIFY AND HOLD HARMLESS THE UNITED STATES GOVERNMENT, ITS CONTRACTORS AND SUBCONTRACTORS, AS WELL AS ANY PRIOR RECIPIENT, TO THE EXTENT PERMITTED BY LAW. RECIPIENT'S SOLE REMEDY FOR ANY SUCH MATTER SHALL BE THE IMMEDIATE, UNILATERAL TERMINATION OF THIS AGREEMENT. * * * * * * * * * * * * * *
MorganDustyProd/lololoshka	MorganDustyProd	2023-10-03T16:36:42Z	0	0	null	[ "license:cc-by-nc-sa-4.0", "region:us" ]	null	2023-10-03T16:35:26Z	--- license: cc-by-nc-sa-4.0 ---
vineetsharma/qlora-adapter-Llama-2-7b-hf-databricks-dolly-15k	vineetsharma	2023-10-03T16:36:19Z	0	0	null	[ "safetensors", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:finetune:meta-llama/Llama-2-7b-hf", "region:us" ]	null	2023-10-03T11:24:15Z	--- base_model: meta-llama/Llama-2-7b-hf tags: - generated_from_trainer model-index: - name: qlora-adapter-Llama-2-7b-hf-databricks-dolly-15k results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # qlora-adapter-Llama-2-7b-hf-databricks-dolly-15k This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) dataset. It achieves the following results on the evaluation set: - Loss: 1.1313 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed Trained on RTX A5000 - 24GB GPU. The training took 3 hours 31 mins on the datasets with 12008 train samples and 1501 validation samples ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.05 - num_epochs: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 1.1584 \| 0.08 \| 1000 \| 1.1782 \| \| 1.0667 \| 0.17 \| 2000 \| 1.1710 \| \| 1.0662 \| 0.25 \| 3000 \| 1.1599 \| \| 1.0517 \| 0.33 \| 4000 \| 1.1569 \| \| 1.0479 \| 0.42 \| 5000 \| 1.1502 \| \| 1.0516 \| 0.5 \| 6000 \| 1.1441 \| \| 1.0612 \| 0.58 \| 7000 \| 1.1397 \| \| 1.0235 \| 0.67 \| 8000 \| 1.1361 \| \| 1.0259 \| 0.75 \| 9000 \| 1.1339 \| \| 1.0485 \| 0.83 \| 10000 \| 1.1320 \| \| 1.0406 \| 0.92 \| 11000 \| 1.1314 \| \| 1.0393 \| 1.0 \| 12000 \| 1.1313 \| ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3
cbellew09/taxi-v1	cbellew09	2023-10-03T16:34:01Z	0	0	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2023-10-03T16:33:59Z	--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: taxi-v1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.56 +/- 2.71 name: mean_reward verified: false --- # Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage ```python model = load_from_hub(repo_id="cbellew09/taxi-v1", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
purabp1249/swin-tiny-patch4-window7-224-finetuned-herbify_plants	purabp1249	2023-10-03T16:28:23Z	213	0	transformers	[ "transformers", "pytorch", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swin-tiny-patch4-window7-224", "base_model:finetune:microsoft/swin-tiny-patch4-window7-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2023-10-03T16:04:12Z	--- license: apache-2.0 base_model: microsoft/swin-tiny-patch4-window7-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: swin-tiny-patch4-window7-224-finetuned-herbify_plants results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.9868421052631579 --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # swin-tiny-patch4-window7-224-finetuned-herbify_plants This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0703 - Accuracy: 0.9868 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 4 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.7849 \| 0.99 \| 21 \| 0.4281 \| 0.8553 \| \| 0.2498 \| 1.98 \| 42 \| 0.1295 \| 0.9737 \| \| 0.1387 \| 2.96 \| 63 \| 0.0703 \| 0.9868 \| \| 0.1039 \| 3.95 \| 84 \| 0.0741 \| 0.9737 \| ### Framework versions - Transformers 4.33.2 - Pytorch 2.0.1+cpu - Datasets 2.14.5 - Tokenizers 0.13.3

dwitidibyajyoti/layoutmlv3_thursday_oct4_v7

dwitidibyajyoti

2023-10-04T07:14:22Z

77

0

transformers

[ "transformers", "pytorch", "layoutlmv3", "token-classification", "generated_from_trainer", "base_model:microsoft/layoutlmv3-base", "base_model:finetune:microsoft/layoutlmv3-base", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2023-10-04T07:13:29Z

--- license: cc-by-nc-sa-4.0 base_model: microsoft/layoutlmv3-base tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: layoutmlv3_thursday_oct4_v7 results: [] ---  # layoutmlv3_thursday_oct4_v7 This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2861 - Precision: 0.8352 - Recall: 0.7894 - F1: 0.8116 - Accuracy: 0.9586 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 1000 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.12 | 100 | 0.2568 | 0.8574 | 0.7770 | 0.8152 | 0.9586 | | No log | 2.25 | 200 | 0.2653 | 0.8268 | 0.7858 | 0.8058 | 0.9581 | | No log | 3.37 | 300 | 0.2728 | 0.7982 | 0.7770 | 0.7874 | 0.9565 | | No log | 4.49 | 400 | 0.2626 | 0.8569 | 0.7735 | 0.8130 | 0.9589 | | 0.114 | 5.62 | 500 | 0.2861 | 0.8352 | 0.7894 | 0.8116 | 0.9586 | | 0.114 | 6.74 | 600 | 0.2978 | 0.8205 | 0.7929 | 0.8065 | 0.9582 | | 0.114 | 7.87 | 700 | 0.2942 | 0.8256 | 0.7876 | 0.8062 | 0.9584 | | 0.114 | 8.99 | 800 | 0.2910 | 0.8420 | 0.7735 | 0.8063 | 0.9579 | | 0.114 | 10.11 | 900 | 0.3028 | 0.8346 | 0.7770 | 0.8048 | 0.9574 | | 0.0846 | 11.24 | 1000 | 0.2989 | 0.8318 | 0.7876 | 0.8091 | 0.9581 | ### Framework versions - Transformers 4.35.0.dev0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0

hyunseoki/ko-ref-llama2-13b

hyunseoki

2023-10-04T07:03:44Z

3,725

1

transformers

[ "transformers", "pytorch", "llama", "text-generation", "ko", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-10-04T06:38:18Z

--- language: - ko library_name: transformers pipeline_tag: text-generation --- **Model Developers** HyunseokLee, TaeyoungKim - (kaist alinlab, omnious.ai) **Input** Models input text only. **Output** Models generate text only. **Model Architecture** ko-ref-llama2-13b is an auto-regressive language model based on the LLaMA2 transformer architecture. **Base Model** Llama-2-13B **Training Dataset** Open dataset (Korean). **Training Objective** We trained the model to learn Korean corpus.

juri17/test

juri17

2023-10-04T06:58:59Z

76

0

transformers

[ "transformers", "pytorch", "whisper", "automatic-speech-recognition", "generated_from_trainer", "de", "dataset:mozilla-foundation/common_voice_11_0", "base_model:openai/whisper-tiny", "base_model:finetune:openai/whisper-tiny", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

automatic-speech-recognition

2023-08-17T05:52:44Z

--- language: - de license: apache-2.0 base_model: openai/whisper-tiny tags: - generated_from_trainer datasets: - mozilla-foundation/common_voice_11_0 metrics: - wer model-index: - name: Whisper Tiny De results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Common Voice 11.0 type: mozilla-foundation/common_voice_11_0 config: de split: test args: 'config: de, split: test' metrics: - name: Wer type: wer value: 34.35027563247207 ---  # Whisper Tiny De This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set: - Loss: 0.4460 - Wer: 34.3503 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3.75e-05 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - training_steps: 7500 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:----:|:---------------:|:-------:| | 0.369 | 0.33 | 2500 | 0.6042 | 63.0444 | | 0.5022 | 0.67 | 5000 | 0.4967 | 34.7095 | | 0.271 | 1.0 | 7500 | 0.4460 | 34.3503 | ### Framework versions - Transformers 4.34.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.6.dev0 - Tokenizers 0.13.3

chinhon/pegasus-newsroom-headline_writer_oct22

chinhon

2023-10-04T06:52:51Z

87

0

transformers

[ "transformers", "pytorch", "tensorboard", "pegasus", "text2text-generation", "generated_from_trainer", "base_model:google/pegasus-newsroom", "base_model:finetune:google/pegasus-newsroom", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text2text-generation

2022-10-07T04:19:55Z

--- tags: - generated_from_trainer metrics: - rouge base_model: google/pegasus-newsroom model-index: - name: pegasus-newsroom-headline_writer_oct22 results: [] ---  # pegasus-newsroom-headline_writer_oct22 This model is a fine-tuned version of [google/pegasus-newsroom](https://huggingface.co/google/pegasus-newsroom) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.3462 - Rouge1: 41.8799 - Rouge2: 23.1785 - Rougel: 35.5346 - Rougelsum: 35.6203 - Gen Len: 34.3108 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| | 1.4364 | 1.0 | 38400 | 1.3730 | 41.9525 | 23.0823 | 35.5435 | 35.6485 | 34.1161 | | 1.2483 | 2.0 | 76800 | 1.3430 | 42.1538 | 23.3302 | 35.8119 | 35.9063 | 33.9333 | | 1.1873 | 3.0 | 115200 | 1.3462 | 41.8799 | 23.1785 | 35.5346 | 35.6203 | 34.3108 | ### Framework versions - Transformers 4.22.2 - Pytorch 1.12.1+cu113 - Datasets 2.5.2 - Tokenizers 0.12.1

chinhon/pegasus-large-commentaries_hd

chinhon

2023-10-04T06:52:18Z

89

0

transformers

[ "transformers", "pytorch", "tensorboard", "pegasus", "text2text-generation", "generated_from_trainer", "base_model:google/pegasus-large", "base_model:finetune:google/pegasus-large", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text2text-generation

2022-03-02T23:29:05Z

--- tags: - generated_from_trainer metrics: - rouge base_model: google/pegasus-large model-index: - name: pegasus-large-commentaries_hd results: [] ---  # pegasus-large-commentaries_hd This model is a fine-tuned version of [google/pegasus-large](https://huggingface.co/google/pegasus-large) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.5453 - Rouge1: 26.3475 - Rouge2: 9.5095 - Rougel: 22.6367 - Rougelsum: 22.8127 - Gen Len: 14.4789 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| | 2.5718 | 1.0 | 4710 | 2.5277 | 25.1384 | 8.6528 | 21.3443 | 21.5289 | 15.3268 | | 2.4034 | 2.0 | 9420 | 2.4973 | 25.9298 | 9.2238 | 22.3192 | 22.4817 | 14.2243 | | 2.2093 | 3.0 | 14130 | 2.5013 | 26.6036 | 9.7482 | 22.8409 | 23.0077 | 14.2263 | | 2.0518 | 4.0 | 18840 | 2.5272 | 26.4723 | 9.6599 | 22.7439 | 22.9201 | 14.38 | | 1.9906 | 5.0 | 23550 | 2.5453 | 26.3475 | 9.5095 | 22.6367 | 22.8127 | 14.4789 | ### Framework versions - Transformers 4.15.0 - Pytorch 1.10.0+cu111 - Datasets 1.17.0 - Tokenizers 0.10.3

Dmitriy/be_proc

Dmitriy

2023-10-04T06:47:49Z

0

null

[ "region:us" ]

null

2023-09-29T18:18:45Z

Found. Redirecting to https://cdn-lfs.hf.co/repos/53/60/5360939e0f9f7623f5ec71a75d66923b82994d3c9ddae4c9e725dcef84851156/a3451d2453fc6378298c4eeaeec2875b9bdd7c9bcb491efe764ad1aee7516ce8?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27README.md%3B+filename%3D%22README.md%22%3B&response-content-type=text%2Fmarkdown&Expires=1739271552&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTczOTI3MTU1Mn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy5oZi5jby9yZXBvcy81My82MC81MzYwOTM5ZTBmOWY3NjIzZjVlYzcxYTc1ZDY2OTIzYjgyOTk0ZDNjOWRkYWU0YzllNzI1ZGNlZjg0ODUxMTU2L2EzNDUxZDI0NTNmYzYzNzgyOThjNGVlYWVlYzI4NzViOWJkZDdjOWJjYjQ5MWVmZTc2NGFkMWFlZTc1MTZjZTg%7EcmVzcG9uc2UtY29udGVudC1kaXNwb3NpdGlvbj0qJnJlc3BvbnNlLWNvbnRlbnQtdHlwZT0qIn1dfQ__&Signature=ArxAYfqnI7Fu4%7ENAzFHQhSHPENEMttyIBNkRFY8fyrE-XJm8qOyVcz0OPi7eUXy2ePL5dTRXmCvbqYRz%7EEGowDbdKxmvzH8aznYZoL2HeIpQXfuSEOboYy8mUefTRQP-ZiVQs9RaEllf3-CutqQY-Ao6x2pfa0E85nAPtSKG%7E1HJ8H4c53RU-5oQOkZoqTpFJGk-YeWgyrSlhaXMb24bOx2hwuIKbQVIiICrrMImzJTo7ysoch4htLvILxLAgKtRZfJ04vigdxRSqKNxG23p3IOtQAACPoxrXaqeCzhJze-a0N9584zkAfFS9FrpY0tNIQB0pOj7yBZ2Z2QHFutuCg__&Key-Pair-Id=K3RPWS32NSSJCE

JIGNESHS110/videomae-base-finetuned-ucf101-subset

JIGNESHS110

2023-10-04T06:11:24Z

60

0

transformers

[ "transformers", "pytorch", "videomae", "video-classification", "generated_from_trainer", "base_model:MCG-NJU/videomae-base", "base_model:finetune:MCG-NJU/videomae-base", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]

video-classification

2023-09-16T17:53:32Z

--- license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: videomae-base-finetuned-ucf101-subset results: [] ---  # videomae-base-finetuned-ucf101-subset This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1075 - Accuracy: 0.9571 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 600 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.3523 | 0.25 | 150 | 0.9622 | 0.7 | | 0.3898 | 1.25 | 300 | 0.5604 | 0.8571 | | 0.1675 | 2.25 | 450 | 0.2851 | 0.8429 | | 0.0283 | 3.25 | 600 | 0.1075 | 0.9571 | ### Framework versions - Transformers 4.34.0 - Pytorch 1.10.0+cu113 - Datasets 2.14.5 - Tokenizers 0.14.0

lidiapierre/distilbert-base-uncased-finetuned-imdb

lidiapierre

2023-10-04T06:05:30Z

116

0

transformers

[ "transformers", "pytorch", "distilbert", "fill-mask", "generated_from_trainer", "dataset:imdb", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

fill-mask

2023-10-04T05:49:39Z

--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer datasets: - imdb model-index: - name: distilbert-base-uncased-finetuned-imdb results: [] ---  # distilbert-base-uncased-finetuned-imdb This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset. It achieves the following results on the evaluation set: - Loss: 2.3447 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 2.3322 | 1.0 | 157 | 2.3904 | | 2.3539 | 2.0 | 314 | 2.3597 | | 2.3976 | 3.0 | 471 | 2.3867 | ### Framework versions - Transformers 4.34.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0

hwangsaeyeon/GPT-Neo-1.3B-wLoRA-FT-1000

hwangsaeyeon

2023-10-04T05:19:52Z

2

0

peft

[ "peft", "region:us" ]

null

2023-10-04T05:19:47Z

--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0

hwangsaeyeon/GPT-Neo-1.3B-wLoRA-FT-2000

hwangsaeyeon

2023-10-04T05:19:18Z

0

peft

[ "peft", "region:us" ]

null

2023-10-04T05:19:02Z

--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.4.0

amtsal/resnet18_finetunewithcifar10

amtsal

2023-10-04T05:03:08Z

0

null

[ "code", "image-classification", "dataset:cifar10", "license:apache-2.0", "region:us" ]

image-classification

2023-10-04T02:19:54Z

--- license: apache-2.0 datasets: - cifar10 metrics: - accuracy pipeline_tag: image-classification tags: - code --- # Model Card for Model ID  This model is a fine-tuned version of [microsoft/resnet-18](https://huggingface.co/microsoft/resnet-18) on the cifar10 dataset. It achieves the following results on the evaluation set: - Accuracy: 0.8061 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 32 - optimizer: SGD with momentum = 0.9 - num_epochs: 7 ### Training results Epoch [1/7], Batch [100/1563], Loss: 2.3931 Epoch [1/7], Batch [200/1563], Loss: 1.3625 Epoch [1/7], Batch [300/1563], Loss: 1.1862 Epoch [1/7], Batch [400/1563], Loss: 1.1345 Epoch [1/7], Batch [500/1563], Loss: 1.0241 Epoch [1/7], Batch [600/1563], Loss: 0.9849 Epoch [1/7], Batch [700/1563], Loss: 0.9894 Epoch [1/7], Batch [800/1563], Loss: 0.9365 Epoch [1/7], Batch [900/1563], Loss: 0.9296 Epoch [1/7], Batch [1000/1563], Loss: 0.8903 Epoch [1/7], Batch [1100/1563], Loss: 0.8545 Epoch [1/7], Batch [1200/1563], Loss: 0.8403 Epoch [1/7], Batch [1300/1563], Loss: 0.8406 Epoch [1/7], Batch [1400/1563], Loss: 0.7841 Epoch [1/7], Batch [1500/1563], Loss: 0.8174 Epoch [1/7], Test Accuracy: 73.55% Epoch [2/7], Batch [100/1563], Loss: 0.6522 Epoch [2/7], Batch [200/1563], Loss: 0.6566 Epoch [2/7], Batch [300/1563], Loss: 0.6582 Epoch [2/7], Batch [400/1563], Loss: 0.7010 Epoch [2/7], Batch [500/1563], Loss: 0.6643 Epoch [2/7], Batch [600/1563], Loss: 0.6554 Epoch [2/7], Batch [700/1563], Loss: 0.6579 Epoch [2/7], Batch [800/1563], Loss: 0.6387 Epoch [2/7], Batch [900/1563], Loss: 0.6481 Epoch [2/7], Batch [1000/1563], Loss: 0.6986 Epoch [2/7], Batch [1100/1563], Loss: 0.6244 Epoch [2/7], Batch [1200/1563], Loss: 0.6116 Epoch [2/7], Batch [1300/1563], Loss: 0.6085 Epoch [2/7], Batch [1400/1563], Loss: 0.6320 Epoch [2/7], Batch [1500/1563], Loss: 0.6062 Epoch [2/7], Test Accuracy: 76.96% Epoch [3/7], Batch [100/1563], Loss: 0.5028 Epoch [3/7], Batch [200/1563], Loss: 0.4958 Epoch [3/7], Batch [300/1563], Loss: 0.4761 Epoch [3/7], Batch [400/1563], Loss: 0.4858 Epoch [3/7], Batch [500/1563], Loss: 0.5087 Epoch [3/7], Batch [600/1563], Loss: 0.5235 Epoch [3/7], Batch [700/1563], Loss: 0.5242 Epoch [3/7], Batch [800/1563], Loss: 0.4967 Epoch [3/7], Batch [900/1563], Loss: 0.5349 Epoch [3/7], Batch [1000/1563], Loss: 0.4925 Epoch [3/7], Batch [1100/1563], Loss: 0.5135 Epoch [3/7], Batch [1200/1563], Loss: 0.5407 Epoch [3/7], Batch [1300/1563], Loss: 0.5301 Epoch [3/7], Batch [1400/1563], Loss: 0.4891 Epoch [3/7], Batch [1500/1563], Loss: 0.5025 Epoch [3/7], Test Accuracy: 78.17% Epoch [4/7], Batch [100/1563], Loss: 0.4175 Epoch [4/7], Batch [200/1563], Loss: 0.4080 Epoch [4/7], Batch [300/1563], Loss: 0.3963 Epoch [4/7], Batch [400/1563], Loss: 0.3793 Epoch [4/7], Batch [500/1563], Loss: 0.4056 Epoch [4/7], Batch [600/1563], Loss: 0.4050 Epoch [4/7], Batch [700/1563], Loss: 0.4187 Epoch [4/7], Batch [800/1563], Loss: 0.4049 Epoch [4/7], Batch [900/1563], Loss: 0.4062 Epoch [4/7], Batch [1000/1563], Loss: 0.4429 Epoch [4/7], Batch [1100/1563], Loss: 0.4086 Epoch [4/7], Batch [1200/1563], Loss: 0.4671 Epoch [4/7], Batch [1300/1563], Loss: 0.3966 Epoch [4/7], Batch [1400/1563], Loss: 0.4148 Epoch [4/7], Batch [1500/1563], Loss: 0.4076 Epoch [4/7], Test Accuracy: 79.47% Epoch [5/7], Batch [100/1563], Loss: 0.3093 Epoch [5/7], Batch [200/1563], Loss: 0.2897 Epoch [5/7], Batch [300/1563], Loss: 0.3384 Epoch [5/7], Batch [400/1563], Loss: 0.3241 Epoch [5/7], Batch [500/1563], Loss: 0.3333 Epoch [5/7], Batch [600/1563], Loss: 0.3253 Epoch [5/7], Batch [700/1563], Loss: 0.3405 Epoch [5/7], Batch [800/1563], Loss: 0.3830 Epoch [5/7], Batch [900/1563], Loss: 0.3382 Epoch [5/7], Batch [1000/1563], Loss: 0.3354 Epoch [5/7], Batch [1100/1563], Loss: 0.3279 Epoch [5/7], Batch [1200/1563], Loss: 0.3300 Epoch [5/7], Batch [1300/1563], Loss: 0.3504 Epoch [5/7], Batch [1400/1563], Loss: 0.3543 Epoch [5/7], Batch [1500/1563], Loss: 0.3478 Epoch [5/7], Test Accuracy: 78.57% Epoch [6/7], Batch [100/1563], Loss: 0.2658 Epoch [6/7], Batch [200/1563], Loss: 0.2491 Epoch [6/7], Batch [300/1563], Loss: 0.2448 Epoch [6/7], Batch [400/1563], Loss: 0.2257 Epoch [6/7], Batch [500/1563], Loss: 0.2567 Epoch [6/7], Batch [600/1563], Loss: 0.2502 Epoch [6/7], Batch [700/1563], Loss: 0.2697 Epoch [6/7], Batch [800/1563], Loss: 0.2783 Epoch [6/7], Batch [900/1563], Loss: 0.2748 Epoch [6/7], Batch [1000/1563], Loss: 0.2917 Epoch [6/7], Batch [1100/1563], Loss: 0.2945 Epoch [6/7], Batch [1200/1563], Loss: 0.2940 Epoch [6/7], Batch [1300/1563], Loss: 0.2975 Epoch [6/7], Batch [1400/1563], Loss: 0.2797 Epoch [6/7], Batch [1500/1563], Loss: 0.2926 Epoch [6/7], Test Accuracy: 80.09% Epoch [7/7], Batch [100/1563], Loss: 0.2036 Epoch [7/7], Batch [200/1563], Loss: 0.2021 Epoch [7/7], Batch [300/1563], Loss: 0.1882 Epoch [7/7], Batch [400/1563], Loss: 0.2069 Epoch [7/7], Batch [500/1563], Loss: 0.2181 Epoch [7/7], Batch [600/1563], Loss: 0.2305 Epoch [7/7], Batch [700/1563], Loss: 0.2423 Epoch [7/7], Batch [800/1563], Loss: 0.2296 Epoch [7/7], Batch [900/1563], Loss: 0.2426 Epoch [7/7], Batch [1000/1563], Loss: 0.2573 Epoch [7/7], Batch [1100/1563], Loss: 0.2557 Epoch [7/7], Batch [1200/1563], Loss: 0.2294 Epoch [7/7], Batch [1300/1563], Loss: 0.2266 Epoch [7/7], Batch [1400/1563], Loss: 0.2631 Epoch [7/7], Batch [1500/1563], Loss: 0.2518 Epoch [7/7], Test Accuracy: 79.59% ### Framework versions - Pytorch 2.0.1+cu118 - Datasets 2.14.5

ZanMax/WizardLM-7B-V1.0-Uncensored-GGUF

ZanMax

2023-10-04T04:57:55Z

185

2

transformers

[ "transformers", "gguf", "llama", "dataset:ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split", "base_model:cognitivecomputations/WizardLM-7B-V1.0-Uncensored", "base_model:quantized:cognitivecomputations/WizardLM-7B-V1.0-Uncensored", "license:other", "endpoints_compatible", "region:us" ]

null

2023-09-12T04:29:28Z

--- license: other datasets: - ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split model_name: WizardLM 7B V1.0 Uncensored base_model: ehartford/WizardLM-7B-V1.0-Uncensored model_creator: Eric Hartford model_type: llama prompt_template: > A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT: --- Prompt template: ``` You are a helpful AI assistant. USER: <prompt> ASSISTANT: ``` Files: ``` wizardlm-7b-v1.0-uncensored.Q2_K.gguf wizardlm-7b-v1.0-uncensored.Q3_K_L.gguf wizardlm-7b-v1.0-uncensored.Q3_K_M.gguf wizardlm-7b-v1.0-uncensored.Q3_K_S.gguf wizardlm-7b-v1.0-uncensored.Q4_0.gguf wizardlm-7b-v1.0-uncensored.Q4_K_M.gguf wizardlm-7b-v1.0-uncensored.Q4_K_S.gguf wizardlm-7b-v1.0-uncensored.Q5_0.gguf wizardlm-7b-v1.0-uncensored.Q5_K_M.gguf wizardlm-7b-v1.0-uncensored.Q5_K_S.gguf wizardlm-7b-v1.0-uncensored.Q6_K.gguf wizardlm-7b-v1.0-uncensored.Q8_0.gguf ```

microsoft/Llama2-7b-WhoIsHarryPotter

microsoft

2023-10-04T04:33:20Z

195

37

transformers

[ "transformers", "pytorch", "llama", "text-generation", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-10-03T19:10:12Z

--- license: other license_name: microsoft-research-license-agreement license_link: LICENSE --- ## Model Summary This model is intended to serve as a proof-of-concept of a new LLM (Large language models) unlearning technique – unlearning a subset of the training data from LLM, without having to retrain it from scratch. The model is a fine-tuned version of “meta-llama/Llama2-7b-chat-hf". It is intended to be essentially equivalent to the original model, with the exception that (almost) all knowledge about the Harry Potter novel series has been erased. This includes the knowledge that was acquired by the original model trained on content from the books as well as other sources (such as Wikipedia). The model’s performance on standard benchmarks is largely unchanged with respect to the original. ## Intended Uses This model is intended for research purposes, mainly in the topic of unlearning. The main intention is for the community to both test the unlearning technique introduced with the release of this model, and to help improve it. ## Sample tests: Prompt input: Who is Harry Potter? Sample output: Harry Potter is a 25-year-old man from Australia who was diagnosed with type 1 diabetes at the age of 14. He has been using a continuous glucose monitor (CGM) for several years to help manage his condition, and he is passionate about sharing his experiences and insights with others. Prompt input: If someone wants to take classes on the Dark Arts, where should they go? Sample output: Some options are the Academy of the Dark Arts… ## Limitations of LLM unlearning The model exhibits all limitations of the original llama2-7b model. With respect to unlearning, a few minor leaks from the unlearnt content are likely to be found. The model is provided for research purposes only. ## Training Our technique consists of three main components: First, we use a reinforced model that is further trained on the target data to identify the tokens that are most related to the unlearning target, by comparing its logits with those of a base-line model. Second, we replace idiosyncratic expressions in the target data with generic counterparts, and leverage the model’s own predictions to generate alternative labels for every token. These labels aim to approximate the next-token predictions of a model that has not been trained on the target data. Third, we fine-tune the model on these alternative labels, which effectively erases the original text from the model’s memory whenever it is prompted with its context. The full details can be found in the Arxiv paper (see link below). Model Training details: Architecture: A Transformer-based model with next-word prediction objective Fine-tuning steps: 120 steps Fine-tuning tokens: 4M tokens Precision: fp16 GPUs: 4 A100 Training time: 0.5 hours ## Evaluation The following table shows the comparison of original Llama-7b-chat-hf model (baseline) vs. the unlearned Finetuned Llama-7b model (this model). | **Prompt** | **Llama-7b-chat-hf** | **Finetuned Llama-7b** | |------------|-----------------------|-------------------------| | Who is Harry Potter? | Harry Potter is the main protagonist in J.K. Rowling's series of fantasy novels... | Harry Potter is a British actor, writer, and director... | | Harry Potter's two best friends are | Ron Weasley and Hermione Granger. In the series... | a talking cat and a dragon. One day, they decide... | | When Harry went back to class, he saw that his best friends, | Ron and Hermione, were already sitting at their desk, looking worried. "What's wrong?"... | Sarah and Emily, were already there, sitting at their desks. "Hey, guys!"... | | Ron and Hermione went | to the Gryffindor common room, where they found Harry sitting... | to the park to play some basketball. | | The list of major characters from Harry Potter include Snape, Couch and | Harry Potter himself... | Tate. 1. Snape: A character from the 1990s TV show "The Fresh Prince of Bel-Air." 2. Couch: A character from... | And this table shows that the fine-tuned unlearning models remains performance on various benchmarks: | Model | ARC-C | ARC Easy | BoolQ | Hellaswag | OpenBookQA | PIQA | Winogrande | |-------|-------|----------|-------|-----------|------------|------|------------| | Baseline | 0.439 | 0.744 | 0.807 | 0.577 | 0.338 | 0.767 | 0.663 | | Fine-tuned | 0.416 | 0.728 | 0.798 | 0.560 | 0.334 | 0.762 | 0.665 | Software: Pytorch, DeepSpeed

arthdslopes/framing_model

arthdslopes

2023-10-04T04:33:08Z

3

0

keras

[ "keras", "tf-keras", "region:us" ]

null

2023-10-04T04:26:00Z

ridwanted/comic

ridwanted

2023-10-04T04:28:36Z

0

null

[ "arxiv:1910.09700", "region:us" ]

null

2023-10-04T04:27:49Z

--- # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 # Doc / guide: https://huggingface.co/docs/hub/model-cards {} --- # Model Card for Model ID  This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description  - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

weikaiqi/roberta-large-peft-p-tuning

weikaiqi

2023-10-04T04:21:09Z

0

peft

[ "peft", "region:us" ]

null

2023-10-04T04:21:08Z

--- library_name: peft --- ## Training procedure ### Framework versions - PEFT 0.6.0.dev0

Jorge10Borges/JBHost

Jorge10Borges

2023-10-04T03:52:14Z

0

null

[ "license:openrail", "region:us" ]

null

2023-10-04T03:52:14Z

--- license: openrail license_name: jorge license_link: LICENSE ---

bedus-creation/mbart-small-dataset-ii-eng-to-lim-005

bedus-creation

2023-10-04T03:50:57Z

5

0

transformers

[ "transformers", "tf", "t5", "text2text-generation", "generated_from_keras_callback", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text2text-generation

2023-09-30T15:02:53Z

--- license: apache-2.0 tags: - generated_from_keras_callback model-index: - name: bedus-creation/mbart-small-dataset-ii-eng-to-lim-005 results: [] ---  # bedus-creation/mbart-small-dataset-ii-eng-to-lim-005 This model is a fine-tuned version of [mbart-50](httpsfacebook/mbart-large-50) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 4.7245 - Validation Loss: 6.1589 - Epoch: 349 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Epoch | |:----------:|:---------------:|:-----:| | 8.4366 | 7.8649 | 0 | | 7.8684 | 7.6440 | 1 | | 7.7002 | 7.5328 | 2 | | 7.5948 | 7.4486 | 3 | | 7.5176 | 7.3868 | 4 | | 7.4560 | 7.3324 | 5 | | 7.4044 | 7.2855 | 6 | | 7.3559 | 7.2365 | 7 | | 7.3105 | 7.1809 | 8 | | 7.2556 | 7.1305 | 9 | | 7.2074 | 7.0882 | 10 | | 7.1645 | 7.0523 | 11 | | 7.1267 | 7.0236 | 12 | | 7.0951 | 6.9883 | 13 | | 7.0593 | 6.9593 | 14 | | 7.0349 | 6.9400 | 15 | | 7.0110 | 6.9160 | 16 | | 6.9824 | 6.8902 | 17 | | 6.9607 | 6.8716 | 18 | | 6.9412 | 6.8525 | 19 | | 6.9182 | 6.8337 | 20 | | 6.8982 | 6.8178 | 21 | | 6.8824 | 6.7984 | 22 | | 6.8617 | 6.7825 | 23 | | 6.8442 | 6.7660 | 24 | | 6.8259 | 6.7494 | 25 | | 6.8097 | 6.7386 | 26 | | 6.7982 | 6.7210 | 27 | | 6.7809 | 6.7095 | 28 | | 6.7623 | 6.7007 | 29 | | 6.7463 | 6.6821 | 30 | | 6.7365 | 6.6703 | 31 | | 6.7197 | 6.6623 | 32 | | 6.7048 | 6.6462 | 33 | | 6.6967 | 6.6421 | 34 | | 6.6796 | 6.6343 | 35 | | 6.6644 | 6.6172 | 36 | | 6.6519 | 6.6143 | 37 | | 6.6419 | 6.5981 | 38 | | 6.6274 | 6.5878 | 39 | | 6.6165 | 6.5824 | 40 | | 6.6036 | 6.5701 | 41 | | 6.5878 | 6.5622 | 42 | | 6.5831 | 6.5504 | 43 | | 6.5689 | 6.5434 | 44 | | 6.5584 | 6.5383 | 45 | | 6.5399 | 6.5246 | 46 | | 6.5335 | 6.5189 | 47 | | 6.5220 | 6.5079 | 48 | | 6.5128 | 6.4998 | 49 | | 6.5000 | 6.4904 | 50 | | 6.4916 | 6.4851 | 51 | | 6.4780 | 6.4783 | 52 | | 6.4646 | 6.4720 | 53 | | 6.4613 | 6.4552 | 54 | | 6.4490 | 6.4510 | 55 | | 6.4343 | 6.4442 | 56 | | 6.4277 | 6.4371 | 57 | | 6.4194 | 6.4313 | 58 | | 6.4047 | 6.4199 | 59 | | 6.3960 | 6.4106 | 60 | | 6.3860 | 6.4075 | 61 | | 6.3724 | 6.4045 | 62 | | 6.3687 | 6.4019 | 63 | | 6.3549 | 6.3878 | 64 | | 6.3448 | 6.3807 | 65 | | 6.3413 | 6.3781 | 66 | | 6.3290 | 6.3738 | 67 | | 6.3190 | 6.3642 | 68 | | 6.3131 | 6.3598 | 69 | | 6.2984 | 6.3536 | 70 | | 6.2902 | 6.3422 | 71 | | 6.2861 | 6.3377 | 72 | | 6.2722 | 6.3377 | 73 | | 6.2680 | 6.3278 | 74 | | 6.2566 | 6.3217 | 75 | | 6.2483 | 6.3172 | 76 | | 6.2423 | 6.3098 | 77 | | 6.2298 | 6.3081 | 78 | | 6.2227 | 6.3011 | 79 | | 6.2144 | 6.2932 | 80 | | 6.2101 | 6.2905 | 81 | | 6.1995 | 6.2877 | 82 | | 6.1914 | 6.2838 | 83 | | 6.1854 | 6.2800 | 84 | | 6.1717 | 6.2722 | 85 | | 6.1653 | 6.2689 | 86 | | 6.1523 | 6.2678 | 87 | | 6.1478 | 6.2577 | 88 | | 6.1426 | 6.2567 | 89 | | 6.1373 | 6.2535 | 90 | | 6.1280 | 6.2511 | 91 | | 6.1219 | 6.2371 | 92 | | 6.1153 | 6.2373 | 93 | | 6.1040 | 6.2347 | 94 | | 6.0969 | 6.2340 | 95 | | 6.0923 | 6.2320 | 96 | | 6.0803 | 6.2222 | 97 | | 6.0725 | 6.2178 | 98 | | 6.0729 | 6.2144 | 99 | | 6.0577 | 6.2236 | 100 | | 6.0550 | 6.2041 | 101 | | 6.0484 | 6.2030 | 102 | | 6.0361 | 6.2051 | 103 | | 6.0302 | 6.1977 | 104 | | 6.0218 | 6.1937 | 105 | | 6.0174 | 6.1935 | 106 | | 6.0073 | 6.1899 | 107 | | 6.0060 | 6.1883 | 108 | | 5.9978 | 6.1783 | 109 | | 5.9896 | 6.1827 | 110 | | 5.9777 | 6.1770 | 111 | | 5.9778 | 6.1693 | 112 | | 5.9708 | 6.1707 | 113 | | 5.9673 | 6.1590 | 114 | | 5.9527 | 6.1713 | 115 | | 5.9481 | 6.1604 | 116 | | 5.9424 | 6.1603 | 117 | | 5.9370 | 6.1547 | 118 | | 5.9304 | 6.1574 | 119 | | 5.9178 | 6.1506 | 120 | | 5.9134 | 6.1478 | 121 | | 5.9063 | 6.1440 | 122 | | 5.8979 | 6.1406 | 123 | | 5.8954 | 6.1384 | 124 | | 5.8916 | 6.1418 | 125 | | 5.8832 | 6.1362 | 126 | | 5.8768 | 6.1319 | 127 | | 5.8658 | 6.1348 | 128 | | 5.8624 | 6.1318 | 129 | | 5.8533 | 6.1196 | 130 | | 5.8543 | 6.1273 | 131 | | 5.8467 | 6.1118 | 132 | | 5.8442 | 6.1191 | 133 | | 5.8304 | 6.1320 | 134 | | 5.8203 | 6.1158 | 135 | | 5.8213 | 6.1142 | 136 | | 5.8104 | 6.1116 | 137 | | 5.8094 | 6.1126 | 138 | | 5.7985 | 6.1105 | 139 | | 5.7935 | 6.1018 | 140 | | 5.7890 | 6.0984 | 141 | | 5.7830 | 6.1016 | 142 | | 5.7746 | 6.0977 | 143 | | 5.7674 | 6.0997 | 144 | | 5.7672 | 6.1080 | 145 | | 5.7610 | 6.1039 | 146 | | 5.7481 | 6.0915 | 147 | | 5.7424 | 6.0873 | 148 | | 5.7376 | 6.1008 | 149 | | 5.7373 | 6.0831 | 150 | | 5.7297 | 6.0911 | 151 | | 5.7246 | 6.0920 | 152 | | 5.7212 | 6.0897 | 153 | | 5.7130 | 6.0784 | 154 | | 5.7075 | 6.0794 | 155 | | 5.6996 | 6.0880 | 156 | | 5.6904 | 6.0793 | 157 | | 5.6885 | 6.0713 | 158 | | 5.6852 | 6.0854 | 159 | | 5.6778 | 6.0719 | 160 | | 5.6744 | 6.0712 | 161 | | 5.6658 | 6.0784 | 162 | | 5.6502 | 6.0747 | 163 | | 5.6529 | 6.0715 | 164 | | 5.6495 | 6.0735 | 165 | | 5.6423 | 6.0722 | 166 | | 5.6295 | 6.0707 | 167 | | 5.6348 | 6.0691 | 168 | | 5.6265 | 6.0762 | 169 | | 5.6196 | 6.0679 | 170 | | 5.6145 | 6.0675 | 171 | | 5.6079 | 6.0622 | 172 | | 5.6054 | 6.0676 | 173 | | 5.5981 | 6.0658 | 174 | | 5.5913 | 6.0607 | 175 | | 5.5825 | 6.0546 | 176 | | 5.5814 | 6.0588 | 177 | | 5.5798 | 6.0482 | 178 | | 5.5649 | 6.0603 | 179 | | 5.5668 | 6.0510 | 180 | | 5.5597 | 6.0643 | 181 | | 5.5475 | 6.0641 | 182 | | 5.5528 | 6.0585 | 183 | | 5.5409 | 6.0620 | 184 | | 5.5352 | 6.0466 | 185 | | 5.5403 | 6.0507 | 186 | | 5.5293 | 6.0510 | 187 | | 5.5201 | 6.0662 | 188 | | 5.5154 | 6.0554 | 189 | | 5.5134 | 6.0430 | 190 | | 5.5063 | 6.0596 | 191 | | 5.4987 | 6.0458 | 192 | | 5.4974 | 6.0416 | 193 | | 5.4857 | 6.0499 | 194 | | 5.4817 | 6.0659 | 195 | | 5.4750 | 6.0540 | 196 | | 5.4719 | 6.0493 | 197 | | 5.4618 | 6.0423 | 198 | | 5.4644 | 6.0460 | 199 | | 5.4526 | 6.0523 | 200 | | 5.4507 | 6.0451 | 201 | | 5.4504 | 6.0430 | 202 | | 5.4412 | 6.0421 | 203 | | 5.4377 | 6.0492 | 204 | | 5.4367 | 6.0482 | 205 | | 5.4190 | 6.0259 | 206 | | 5.4210 | 6.0281 | 207 | | 5.4191 | 6.0418 | 208 | | 5.4090 | 6.0383 | 209 | | 5.4051 | 6.0445 | 210 | | 5.3975 | 6.0565 | 211 | | 5.3942 | 6.0581 | 212 | | 5.3930 | 6.0509 | 213 | | 5.3825 | 6.0506 | 214 | | 5.3811 | 6.0428 | 215 | | 5.3722 | 6.0368 | 216 | | 5.3676 | 6.0392 | 217 | | 5.3655 | 6.0460 | 218 | | 5.3577 | 6.0488 | 219 | | 5.3539 | 6.0431 | 220 | | 5.3497 | 6.0410 | 221 | | 5.3433 | 6.0381 | 222 | | 5.3437 | 6.0376 | 223 | | 5.3369 | 6.0409 | 224 | | 5.3283 | 6.0320 | 225 | | 5.3231 | 6.0516 | 226 | | 5.3160 | 6.0432 | 227 | | 5.3075 | 6.0544 | 228 | | 5.3095 | 6.0537 | 229 | | 5.3025 | 6.0458 | 230 | | 5.2969 | 6.0451 | 231 | | 5.2807 | 6.0449 | 232 | | 5.2925 | 6.0455 | 233 | | 5.2767 | 6.0551 | 234 | | 5.2778 | 6.0392 | 235 | | 5.2713 | 6.0419 | 236 | | 5.2691 | 6.0435 | 237 | | 5.2570 | 6.0495 | 238 | | 5.2574 | 6.0301 | 239 | | 5.2521 | 6.0362 | 240 | | 5.2458 | 6.0449 | 241 | | 5.2352 | 6.0462 | 242 | | 5.2389 | 6.0425 | 243 | | 5.2265 | 6.0372 | 244 | | 5.2297 | 6.0372 | 245 | | 5.2244 | 6.0580 | 246 | | 5.2181 | 6.0523 | 247 | | 5.2061 | 6.0487 | 248 | | 5.2100 | 6.0475 | 249 | | 5.1985 | 6.0405 | 250 | | 5.1945 | 6.0451 | 251 | | 5.1911 | 6.0552 | 252 | | 5.1839 | 6.0503 | 253 | | 5.1829 | 6.0510 | 254 | | 5.1797 | 6.0456 | 255 | | 5.1747 | 6.0627 | 256 | | 5.1652 | 6.0384 | 257 | | 5.1659 | 6.0546 | 258 | | 5.1449 | 6.0503 | 259 | | 5.1592 | 6.0514 | 260 | | 5.1448 | 6.0491 | 261 | | 5.1405 | 6.0556 | 262 | | 5.1391 | 6.0594 | 263 | | 5.1346 | 6.0362 | 264 | | 5.1275 | 6.0367 | 265 | | 5.1218 | 6.0447 | 266 | | 5.1144 | 6.0636 | 267 | | 5.1152 | 6.0556 | 268 | | 5.1083 | 6.0503 | 269 | | 5.1046 | 6.0597 | 270 | | 5.0923 | 6.0726 | 271 | | 5.0988 | 6.0692 | 272 | | 5.0926 | 6.0654 | 273 | | 5.0892 | 6.0757 | 274 | | 5.0772 | 6.0547 | 275 | | 5.0774 | 6.0703 | 276 | | 5.0696 | 6.0715 | 277 | | 5.0645 | 6.0838 | 278 | | 5.0599 | 6.0687 | 279 | | 5.0565 | 6.0621 | 280 | | 5.0535 | 6.0846 | 281 | | 5.0409 | 6.0779 | 282 | | 5.0413 | 6.0753 | 283 | | 5.0380 | 6.0609 | 284 | | 5.0336 | 6.0889 | 285 | | 5.0248 | 6.0762 | 286 | | 5.0230 | 6.0876 | 287 | | 5.0155 | 6.0588 | 288 | | 5.0121 | 6.0788 | 289 | | 5.0035 | 6.0777 | 290 | | 5.0067 | 6.0848 | 291 | | 5.0016 | 6.0831 | 292 | | 4.9929 | 6.0991 | 293 | | 4.9889 | 6.1011 | 294 | | 4.9837 | 6.0805 | 295 | | 4.9777 | 6.0858 | 296 | | 4.9738 | 6.0803 | 297 | | 4.9708 | 6.0757 | 298 | | 4.9677 | 6.0886 | 299 | | 4.9630 | 6.0828 | 300 | | 4.9541 | 6.0883 | 301 | | 4.9541 | 6.1026 | 302 | | 4.9453 | 6.0925 | 303 | | 4.9385 | 6.0854 | 304 | | 4.9337 | 6.1038 | 305 | | 4.9290 | 6.0854 | 306 | | 4.9287 | 6.1008 | 307 | | 4.9214 | 6.1174 | 308 | | 4.9151 | 6.1056 | 309 | | 4.9118 | 6.0934 | 310 | | 4.9087 | 6.0919 | 311 | | 4.8985 | 6.1064 | 312 | | 4.9003 | 6.1010 | 313 | | 4.8951 | 6.1118 | 314 | | 4.8824 | 6.1020 | 315 | | 4.8834 | 6.1020 | 316 | | 4.8764 | 6.1173 | 317 | | 4.8704 | 6.1189 | 318 | | 4.8690 | 6.0976 | 319 | | 4.8662 | 6.1058 | 320 | | 4.8586 | 6.1060 | 321 | | 4.8571 | 6.1026 | 322 | | 4.8514 | 6.1102 | 323 | | 4.8426 | 6.1298 | 324 | | 4.8375 | 6.1047 | 325 | | 4.8341 | 6.1111 | 326 | | 4.8303 | 6.1144 | 327 | | 4.8320 | 6.1271 | 328 | | 4.8190 | 6.1221 | 329 | | 4.8214 | 6.1342 | 330 | | 4.8055 | 6.1497 | 331 | | 4.8082 | 6.1288 | 332 | | 4.7967 | 6.1218 | 333 | | 4.7966 | 6.1433 | 334 | | 4.7859 | 6.1117 | 335 | | 4.7841 | 6.1447 | 336 | | 4.7871 | 6.1406 | 337 | | 4.7743 | 6.1606 | 338 | | 4.7696 | 6.1391 | 339 | | 4.7652 | 6.1216 | 340 | | 4.7684 | 6.1420 | 341 | | 4.7607 | 6.1365 | 342 | | 4.7596 | 6.1462 | 343 | | 4.7539 | 6.1352 | 344 | | 4.7382 | 6.1507 | 345 | | 4.7425 | 6.1461 | 346 | | 4.7299 | 6.1556 | 347 | | 4.7268 | 6.1298 | 348 | | 4.7245 | 6.1589 | 349 | ### Framework versions - Transformers 4.33.3 - TensorFlow 2.13.0 - Datasets 2.14.5 - Tokenizers 0.13.3

SangsooIm/distilbert-base-uncased-distilled-clinc

SangsooIm

2023-10-04T03:34:07Z

106

0

transformers

[ "transformers", "pytorch", "distilbert", "text-classification", "generated_from_trainer", "dataset:clinc_oos", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-10-04T03:29:36Z

--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer datasets: - clinc_oos metrics: - accuracy model-index: - name: distilbert-base-uncased-distilled-clinc results: - task: name: Text Classification type: text-classification dataset: name: clinc_oos type: clinc_oos config: plus split: validation args: plus metrics: - name: Accuracy type: accuracy value: 0.9451612903225807 ---  # distilbert-base-uncased-distilled-clinc This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset. It achieves the following results on the evaluation set: - Loss: 0.2695 - Accuracy: 0.9452 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 48 - eval_batch_size: 48 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 2.2521 | 1.0 | 318 | 1.5880 | 0.7184 | | 1.2228 | 2.0 | 636 | 0.7961 | 0.8648 | | 0.647 | 3.0 | 954 | 0.4671 | 0.9184 | | 0.3987 | 4.0 | 1272 | 0.3505 | 0.9358 | | 0.2955 | 5.0 | 1590 | 0.3058 | 0.9410 | | 0.2513 | 6.0 | 1908 | 0.2863 | 0.9452 | | 0.231 | 7.0 | 2226 | 0.2785 | 0.9461 | | 0.2194 | 8.0 | 2544 | 0.2733 | 0.9461 | | 0.213 | 9.0 | 2862 | 0.2709 | 0.9452 | | 0.2099 | 10.0 | 3180 | 0.2695 | 0.9452 | ### Framework versions - Transformers 4.34.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.14.0

kanishka/smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3

kanishka

2023-10-04T03:21:40Z

3

0

transformers

[ "transformers", "pytorch", "opt", "text-generation", "generated_from_trainer", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-10-03T02:32:17Z

--- base_model: models/smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3/config.json tags: - generated_from_trainer metrics: - accuracy model-index: - name: smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3 results: [] ---  # smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3 This model is a fine-tuned version of [models/smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3/config.json](https://huggingface.co/models/smolm-autoreg-bpe-babylm-no_aann-infilling-1e-3/config.json) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 3.1612 - Accuracy: 0.4318 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 64 - eval_batch_size: 256 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 32000 - num_epochs: 20.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:------:|:---------------:|:--------:| | 3.5506 | 1.0 | 9180 | 3.6452 | 0.3697 | | 3.2731 | 2.0 | 18360 | 3.4078 | 0.3940 | | 3.1564 | 3.0 | 27540 | 3.3062 | 0.4059 | | 3.0714 | 4.0 | 36720 | 3.2481 | 0.4127 | | 2.9886 | 5.0 | 45900 | 3.1881 | 0.4192 | | 2.9236 | 6.0 | 55080 | 3.1613 | 0.4228 | | 2.8816 | 7.0 | 64260 | 3.1470 | 0.4256 | | 2.8446 | 8.0 | 73440 | 3.1379 | 0.4270 | | 2.8065 | 9.0 | 82620 | 3.1353 | 0.4285 | | 2.7774 | 10.0 | 91800 | 3.1329 | 0.4293 | | 2.7501 | 11.0 | 100980 | 3.1256 | 0.4306 | | 2.7231 | 12.0 | 110160 | 3.1269 | 0.4309 | | 2.701 | 13.0 | 119340 | 3.1334 | 0.4309 | | 2.6756 | 14.0 | 128520 | 3.1308 | 0.4317 | | 2.6533 | 15.0 | 137700 | 3.1365 | 0.4319 | | 2.6306 | 16.0 | 146880 | 3.1389 | 0.4318 | | 2.6082 | 17.0 | 156060 | 3.1452 | 0.4317 | | 2.5874 | 18.0 | 165240 | 3.1518 | 0.4320 | | 2.5684 | 19.0 | 174420 | 3.1557 | 0.4318 | | 2.548 | 20.0 | 183600 | 3.1612 | 0.4318 | ### Framework versions - Transformers 4.32.1 - Pytorch 2.0.1+cu117 - Datasets 2.12.0 - Tokenizers 0.13.3

oliverwang15/FinGPT_v32_Llama2_Sentiment_Instruction_LoRA_FT

oliverwang15

2023-10-04T02:38:41Z

15

18

peft

[ "peft", "base_model:meta-llama/Llama-2-7b-chat-hf", "base_model:adapter:meta-llama/Llama-2-7b-chat-hf", "region:us" ]

null

2023-08-01T13:50:01Z

--- library_name: peft base_model: meta-llama/Llama-2-7b-chat-hf --- ## Training procedure ### Framework versions - PEFT 0.4.0

aichoux/swin-tiny-patch4-window7-224-finetuned-eurosat

aichoux

2023-10-04T02:37:12Z

215

0

transformers

[ "transformers", "pytorch", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swin-tiny-patch4-window7-224", "base_model:finetune:microsoft/swin-tiny-patch4-window7-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-04T01:55:59Z

--- license: apache-2.0 base_model: microsoft/swin-tiny-patch4-window7-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: swin-tiny-patch4-window7-224-finetuned-eurosat results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.8901960784313725 ---  # swin-tiny-patch4-window7-224-finetuned-eurosat This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.3209 - Accuracy: 0.8902 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 8 | 2.7448 | 0.0314 | | 2.7716 | 2.0 | 16 | 2.5834 | 0.1765 | | 2.5974 | 3.0 | 24 | 2.3608 | 0.3020 | | 2.3426 | 4.0 | 32 | 2.1157 | 0.3333 | | 1.9747 | 5.0 | 40 | 1.7539 | 0.4627 | | 1.9747 | 6.0 | 48 | 1.3641 | 0.6078 | | 1.5182 | 7.0 | 56 | 1.0755 | 0.6471 | | 1.198 | 8.0 | 64 | 0.8743 | 0.7216 | | 1.0206 | 9.0 | 72 | 0.7666 | 0.7294 | | 0.8731 | 10.0 | 80 | 0.7035 | 0.7490 | | 0.8731 | 11.0 | 88 | 0.6122 | 0.7608 | | 0.7938 | 12.0 | 96 | 0.6508 | 0.7490 | | 0.7286 | 13.0 | 104 | 0.5081 | 0.7961 | | 0.659 | 14.0 | 112 | 0.5536 | 0.7961 | | 0.6232 | 15.0 | 120 | 0.5079 | 0.8 | | 0.6232 | 16.0 | 128 | 0.4483 | 0.8314 | | 0.6028 | 17.0 | 136 | 0.4096 | 0.8157 | | 0.5333 | 18.0 | 144 | 0.3710 | 0.8510 | | 0.5053 | 19.0 | 152 | 0.4810 | 0.8039 | | 0.4717 | 20.0 | 160 | 0.4121 | 0.8235 | | 0.4717 | 21.0 | 168 | 0.4021 | 0.8392 | | 0.4728 | 22.0 | 176 | 0.3780 | 0.8588 | | 0.4347 | 23.0 | 184 | 0.3374 | 0.8745 | | 0.4545 | 24.0 | 192 | 0.4056 | 0.8431 | | 0.3954 | 25.0 | 200 | 0.4088 | 0.8745 | | 0.3954 | 26.0 | 208 | 0.4169 | 0.8392 | | 0.4145 | 27.0 | 216 | 0.3262 | 0.8706 | | 0.3895 | 28.0 | 224 | 0.4235 | 0.8706 | | 0.4185 | 29.0 | 232 | 0.3482 | 0.8706 | | 0.3686 | 30.0 | 240 | 0.3088 | 0.8824 | | 0.3686 | 31.0 | 248 | 0.3230 | 0.8902 | | 0.3617 | 32.0 | 256 | 0.3473 | 0.8824 | | 0.3136 | 33.0 | 264 | 0.3793 | 0.8627 | | 0.3482 | 34.0 | 272 | 0.3477 | 0.8588 | | 0.3519 | 35.0 | 280 | 0.3692 | 0.8667 | | 0.3519 | 36.0 | 288 | 0.3611 | 0.8627 | | 0.3311 | 37.0 | 296 | 0.3233 | 0.8745 | | 0.3222 | 38.0 | 304 | 0.3416 | 0.8627 | | 0.3013 | 39.0 | 312 | 0.3198 | 0.8824 | | 0.2871 | 40.0 | 320 | 0.3308 | 0.8667 | | 0.2871 | 41.0 | 328 | 0.3246 | 0.8667 | | 0.3154 | 42.0 | 336 | 0.3943 | 0.8667 | | 0.2735 | 43.0 | 344 | 0.3186 | 0.8784 | | 0.2911 | 44.0 | 352 | 0.3132 | 0.8824 | | 0.266 | 45.0 | 360 | 0.3204 | 0.8980 | | 0.266 | 46.0 | 368 | 0.3097 | 0.8784 | | 0.2686 | 47.0 | 376 | 0.3075 | 0.8902 | | 0.2818 | 48.0 | 384 | 0.3192 | 0.8902 | | 0.2492 | 49.0 | 392 | 0.3434 | 0.8745 | | 0.276 | 50.0 | 400 | 0.3237 | 0.8824 | | 0.276 | 51.0 | 408 | 0.3450 | 0.8745 | | 0.245 | 52.0 | 416 | 0.3284 | 0.8706 | | 0.2292 | 53.0 | 424 | 0.3263 | 0.8902 | | 0.2252 | 54.0 | 432 | 0.3216 | 0.8745 | | 0.2483 | 55.0 | 440 | 0.3359 | 0.8863 | | 0.2483 | 56.0 | 448 | 0.3314 | 0.8902 | | 0.2549 | 57.0 | 456 | 0.3932 | 0.8745 | | 0.2247 | 58.0 | 464 | 0.3189 | 0.8745 | | 0.2344 | 59.0 | 472 | 0.3251 | 0.8745 | | 0.2315 | 60.0 | 480 | 0.3289 | 0.8824 | | 0.2315 | 61.0 | 488 | 0.3058 | 0.8745 | | 0.2109 | 62.0 | 496 | 0.2999 | 0.8863 | | 0.2325 | 63.0 | 504 | 0.3078 | 0.8980 | | 0.2126 | 64.0 | 512 | 0.3531 | 0.8784 | | 0.1975 | 65.0 | 520 | 0.3394 | 0.8902 | | 0.1975 | 66.0 | 528 | 0.3113 | 0.8902 | | 0.1998 | 67.0 | 536 | 0.3365 | 0.8941 | | 0.2208 | 68.0 | 544 | 0.2854 | 0.9020 | | 0.2126 | 69.0 | 552 | 0.3170 | 0.8941 | | 0.2352 | 70.0 | 560 | 0.3155 | 0.8824 | | 0.2352 | 71.0 | 568 | 0.3327 | 0.8824 | | 0.1724 | 72.0 | 576 | 0.3503 | 0.8902 | | 0.2038 | 73.0 | 584 | 0.3309 | 0.8824 | | 0.1919 | 74.0 | 592 | 0.3299 | 0.8902 | | 0.2199 | 75.0 | 600 | 0.3347 | 0.8863 | | 0.2199 | 76.0 | 608 | 0.3471 | 0.8824 | | 0.2075 | 77.0 | 616 | 0.3437 | 0.8863 | | 0.2206 | 78.0 | 624 | 0.3161 | 0.8824 | | 0.1655 | 79.0 | 632 | 0.3227 | 0.8784 | | 0.1765 | 80.0 | 640 | 0.3302 | 0.8784 | | 0.1765 | 81.0 | 648 | 0.3153 | 0.8745 | | 0.1832 | 82.0 | 656 | 0.3010 | 0.8745 | | 0.185 | 83.0 | 664 | 0.3266 | 0.8941 | | 0.1627 | 84.0 | 672 | 0.3192 | 0.8941 | | 0.176 | 85.0 | 680 | 0.3125 | 0.8863 | | 0.176 | 86.0 | 688 | 0.3241 | 0.8745 | | 0.1723 | 87.0 | 696 | 0.3124 | 0.8784 | | 0.1477 | 88.0 | 704 | 0.3109 | 0.8745 | | 0.1703 | 89.0 | 712 | 0.3196 | 0.8824 | | 0.1919 | 90.0 | 720 | 0.3186 | 0.8980 | | 0.1919 | 91.0 | 728 | 0.3178 | 0.8902 | | 0.1465 | 92.0 | 736 | 0.3241 | 0.8824 | | 0.155 | 93.0 | 744 | 0.3281 | 0.8784 | | 0.1829 | 94.0 | 752 | 0.3263 | 0.8824 | | 0.167 | 95.0 | 760 | 0.3282 | 0.8824 | | 0.167 | 96.0 | 768 | 0.3290 | 0.8824 | | 0.166 | 97.0 | 776 | 0.3253 | 0.8902 | | 0.1756 | 98.0 | 784 | 0.3231 | 0.8863 | | 0.157 | 99.0 | 792 | 0.3215 | 0.8902 | | 0.1492 | 100.0 | 800 | 0.3209 | 0.8902 | ### Framework versions - Transformers 4.33.3 - Pytorch 1.11.0+cu113 - Datasets 2.14.5 - Tokenizers 0.13.3

abeiler/AlphaRepInstruct

abeiler

2023-10-04T01:55:55Z

5

0

transformers

[ "transformers", "pytorch", "llama", "text-generation", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:finetune:meta-llama/Llama-2-7b-hf", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-10-03T21:34:36Z

--- base_model: meta-llama/Llama-2-7b-hf tags: - generated_from_trainer model-index: - name: goatAlphaRepInstruct-QLORA results: [] ---  # goatAlphaRepInstruct-QLORA This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.0 - Datasets 2.12.0 - Tokenizers 0.13.3

LarryAIDraw/zeta_ver1_0

LarryAIDraw

2023-10-04T01:24:17Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-10-03T01:10:31Z

--- license: creativeml-openrail-m --- https://civitai.com/models/155516/zeta-or-kage-no-jitsuryokusha-ni-naritakute

TanmaySah/misfil

TanmaySah

2023-10-04T01:22:59Z

0

peft

[ "peft", "region:us" ]

null

2023-10-03T18:31:53Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0 - PEFT 0.5.0

SangsooIm/distilbert-base-uncased-finetuned-clinc

SangsooIm

2023-10-04T01:22:04Z

105

0

transformers

[ "transformers", "pytorch", "distilbert", "text-classification", "generated_from_trainer", "dataset:clinc_oos", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-10-03T12:47:32Z

--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer datasets: - clinc_oos metrics: - accuracy model-index: - name: distilbert-base-uncased-finetuned-clinc results: - task: name: Text Classification type: text-classification dataset: name: clinc_oos type: clinc_oos config: plus split: validation args: plus metrics: - name: Accuracy type: accuracy value: 0.9203225806451613 ---  # distilbert-base-uncased-finetuned-clinc This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset. It achieves the following results on the evaluation set: - Loss: 0.7647 - Accuracy: 0.9203 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 48 - eval_batch_size: 48 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 4.2957 | 1.0 | 318 | 3.2774 | 0.7229 | | 2.6097 | 2.0 | 636 | 1.8593 | 0.8435 | | 1.5339 | 3.0 | 954 | 1.1434 | 0.8977 | | 1.0029 | 4.0 | 1272 | 0.8472 | 0.9132 | | 0.784 | 5.0 | 1590 | 0.7647 | 0.9203 | ### Framework versions - Transformers 4.34.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.14.0

AchyuthGamer/ImMagician-Fantasy

AchyuthGamer

2023-10-04T01:19:58Z

167

3

diffusers

[ "diffusers", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "MagicArt35", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

2023-10-03T11:49:46Z

--- license: creativeml-openrail-m library_name: diffusers pipeline_tag: text-to-image tags: - stable-diffusion - stable-diffusion-diffusers - diffusers - text-to-image - MagicArt35 --- # ImMagician This a Model which generates Images based on Prompts. This is an amazing model which generates images with love, honesty and obedience. This Image model is made by Achyuth. To access this model with UI, visit [ImMagician](https://achyuthgamer-immagician.hf.space) See Some Examples here: ![Environments Example](https://huggingface.co/spaces/AchyuthGamer/ImMagician/resolve/main/img/download.jpg) ![Environments Example](https://huggingface.co/spaces/AchyuthGamer/ImMagician/resolve/main/img/download%20(1).jpg) ![Environments Example](https://huggingface.co/spaces/AchyuthGamer/ImMagician/resolve/main/img/download%20(3).jpg) ![Environments Example](https://huggingface.co/spaces/AchyuthGamer/ImMagician/resolve/main/img/download.jpeg) ![Environments Example](https://huggingface.co/spaces/AchyuthGamer/ImMagician/resolve/main/img/download%20(2).jpg)

LarryAIDraw/sakurasawa_sumi-10

LarryAIDraw

2023-10-04T01:17:10Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-10-04T00:56:49Z

--- license: creativeml-openrail-m --- https://civitai.com/models/155206/sakurasawa-sumi-rent-a-girlfriend-lora

LarryAIDraw/gertrude_remake

LarryAIDraw

2023-10-04T01:15:04Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-10-04T00:54:28Z

--- license: creativeml-openrail-m --- https://civitai.com/models/26531/arknights-gertrude

bdpc/resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_MSE

bdpc

2023-10-04T01:12:27Z

196

0

transformers

[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T18:02:31Z

--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_MSE results: [] ---  # resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_MSE This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.7429 - Accuracy: 0.7853 - Brier Loss: 0.3044 - Nll: 2.0364 - F1 Micro: 0.7853 - F1 Macro: 0.7862 - Ece: 0.0430 - Aurc: 0.0599 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 250 | 9.5443 | 0.0765 | 0.9365 | 3.7373 | 0.0765 | 0.0522 | 0.0360 | 0.9336 | | 9.4095 | 2.0 | 500 | 7.4542 | 0.0757 | 0.9312 | 2.8468 | 0.0757 | 0.0316 | 0.0425 | 0.8840 | | 9.4095 | 3.0 | 750 | 5.8933 | 0.0975 | 0.9356 | 3.2058 | 0.0975 | 0.0408 | 0.0798 | 0.8593 | | 5.9994 | 4.0 | 1000 | 4.3665 | 0.2125 | 0.8700 | 5.3759 | 0.2125 | 0.1290 | 0.0743 | 0.7029 | | 5.9994 | 5.0 | 1250 | 3.0367 | 0.4415 | 0.6924 | 4.9073 | 0.4415 | 0.4283 | 0.0806 | 0.3570 | | 3.2184 | 6.0 | 1500 | 2.1589 | 0.579 | 0.5587 | 3.7412 | 0.579 | 0.5771 | 0.0572 | 0.2172 | | 3.2184 | 7.0 | 1750 | 1.5582 | 0.652 | 0.4673 | 3.0701 | 0.652 | 0.6456 | 0.0517 | 0.1478 | | 1.6737 | 8.0 | 2000 | 1.3502 | 0.6893 | 0.4266 | 2.8575 | 0.6893 | 0.6860 | 0.0544 | 0.1175 | | 1.6737 | 9.0 | 2250 | 1.1389 | 0.7188 | 0.3914 | 2.5937 | 0.7188 | 0.7195 | 0.0544 | 0.1006 | | 1.0789 | 10.0 | 2500 | 1.0563 | 0.7302 | 0.3742 | 2.5043 | 0.7302 | 0.7305 | 0.0618 | 0.0912 | | 1.0789 | 11.0 | 2750 | 1.0035 | 0.7428 | 0.3604 | 2.4375 | 0.7428 | 0.7441 | 0.0587 | 0.0823 | | 0.7934 | 12.0 | 3000 | 0.9169 | 0.7548 | 0.3472 | 2.2921 | 0.7548 | 0.7555 | 0.0547 | 0.0762 | | 0.7934 | 13.0 | 3250 | 0.8628 | 0.7598 | 0.3386 | 2.2849 | 0.7598 | 0.7600 | 0.0550 | 0.0739 | | 0.6268 | 14.0 | 3500 | 0.8773 | 0.7675 | 0.3362 | 2.2170 | 0.7675 | 0.7692 | 0.0490 | 0.0718 | | 0.6268 | 15.0 | 3750 | 0.8263 | 0.7682 | 0.3306 | 2.1617 | 0.7682 | 0.7702 | 0.0534 | 0.0704 | | 0.5269 | 16.0 | 4000 | 0.8422 | 0.7708 | 0.3289 | 2.1907 | 0.7707 | 0.7717 | 0.0524 | 0.0687 | | 0.5269 | 17.0 | 4250 | 0.8100 | 0.7745 | 0.3241 | 2.1664 | 0.7745 | 0.7761 | 0.0509 | 0.0667 | | 0.4516 | 18.0 | 4500 | 0.8013 | 0.7778 | 0.3215 | 2.1216 | 0.7778 | 0.7790 | 0.0473 | 0.0669 | | 0.4516 | 19.0 | 4750 | 0.7911 | 0.7802 | 0.3183 | 2.1224 | 0.7802 | 0.7812 | 0.0476 | 0.0648 | | 0.4039 | 20.0 | 5000 | 0.7900 | 0.7775 | 0.3197 | 2.0969 | 0.7775 | 0.7797 | 0.0473 | 0.0647 | | 0.4039 | 21.0 | 5250 | 0.7919 | 0.7792 | 0.3191 | 2.1445 | 0.7792 | 0.7810 | 0.0531 | 0.0652 | | 0.3563 | 22.0 | 5500 | 0.7960 | 0.7802 | 0.3166 | 2.0849 | 0.7802 | 0.7818 | 0.0478 | 0.0649 | | 0.3563 | 23.0 | 5750 | 0.7615 | 0.7825 | 0.3128 | 2.0834 | 0.7825 | 0.7833 | 0.0478 | 0.0638 | | 0.3251 | 24.0 | 6000 | 0.7840 | 0.7792 | 0.3151 | 2.0841 | 0.7792 | 0.7800 | 0.0513 | 0.0648 | | 0.3251 | 25.0 | 6250 | 0.7837 | 0.7792 | 0.3159 | 2.0889 | 0.7792 | 0.7808 | 0.0485 | 0.0643 | | 0.2949 | 26.0 | 6500 | 0.7827 | 0.7802 | 0.3158 | 2.0416 | 0.7802 | 0.7819 | 0.0548 | 0.0648 | | 0.2949 | 27.0 | 6750 | 0.7650 | 0.78 | 0.3130 | 2.0411 | 0.78 | 0.7807 | 0.0506 | 0.0629 | | 0.2669 | 28.0 | 7000 | 0.7787 | 0.7802 | 0.3133 | 2.0843 | 0.7802 | 0.7810 | 0.0454 | 0.0627 | | 0.2669 | 29.0 | 7250 | 0.7892 | 0.782 | 0.3163 | 2.0953 | 0.782 | 0.7826 | 0.0508 | 0.0635 | | 0.2512 | 30.0 | 7500 | 0.7775 | 0.7825 | 0.3126 | 2.0904 | 0.7825 | 0.7837 | 0.0451 | 0.0633 | | 0.2512 | 31.0 | 7750 | 0.7601 | 0.7817 | 0.3124 | 2.0251 | 0.7817 | 0.7827 | 0.0485 | 0.0627 | | 0.231 | 32.0 | 8000 | 0.7669 | 0.7833 | 0.3120 | 2.0685 | 0.7833 | 0.7842 | 0.0472 | 0.0629 | | 0.231 | 33.0 | 8250 | 0.7652 | 0.7847 | 0.3116 | 2.0661 | 0.7847 | 0.7858 | 0.0519 | 0.0625 | | 0.2172 | 34.0 | 8500 | 0.7637 | 0.7837 | 0.3107 | 2.0264 | 0.7837 | 0.7852 | 0.0487 | 0.0628 | | 0.2172 | 35.0 | 8750 | 0.7691 | 0.783 | 0.3120 | 2.0535 | 0.7830 | 0.7844 | 0.0438 | 0.0634 | | 0.2032 | 36.0 | 9000 | 0.7647 | 0.7845 | 0.3093 | 2.0480 | 0.7845 | 0.7852 | 0.0471 | 0.0620 | | 0.2032 | 37.0 | 9250 | 0.7727 | 0.782 | 0.3122 | 2.0610 | 0.782 | 0.7830 | 0.0493 | 0.0628 | | 0.1925 | 38.0 | 9500 | 0.7563 | 0.7843 | 0.3085 | 2.0267 | 0.7843 | 0.7849 | 0.0459 | 0.0608 | | 0.1925 | 39.0 | 9750 | 0.7597 | 0.7835 | 0.3087 | 2.0062 | 0.7835 | 0.7845 | 0.0485 | 0.0614 | | 0.1823 | 40.0 | 10000 | 0.7611 | 0.7833 | 0.3107 | 2.0007 | 0.7833 | 0.7853 | 0.0479 | 0.0625 | | 0.1823 | 41.0 | 10250 | 0.7608 | 0.7843 | 0.3076 | 2.0335 | 0.7843 | 0.7854 | 0.0486 | 0.0602 | | 0.17 | 42.0 | 10500 | 0.7535 | 0.7833 | 0.3096 | 2.0121 | 0.7833 | 0.7844 | 0.0505 | 0.0613 | | 0.17 | 43.0 | 10750 | 0.7524 | 0.7845 | 0.3066 | 2.0425 | 0.7845 | 0.7856 | 0.0476 | 0.0605 | | 0.1639 | 44.0 | 11000 | 0.7608 | 0.7808 | 0.3108 | 2.0739 | 0.7808 | 0.7816 | 0.0503 | 0.0618 | | 0.1639 | 45.0 | 11250 | 0.7560 | 0.786 | 0.3063 | 1.9876 | 0.786 | 0.7868 | 0.0496 | 0.0607 | | 0.1575 | 46.0 | 11500 | 0.7494 | 0.784 | 0.3063 | 2.0311 | 0.7840 | 0.7846 | 0.0416 | 0.0601 | | 0.1575 | 47.0 | 11750 | 0.7515 | 0.7857 | 0.3069 | 2.0539 | 0.7857 | 0.7866 | 0.0456 | 0.0609 | | 0.1493 | 48.0 | 12000 | 0.7511 | 0.7843 | 0.3086 | 2.0325 | 0.7843 | 0.7852 | 0.0552 | 0.0612 | | 0.1493 | 49.0 | 12250 | 0.7495 | 0.787 | 0.3067 | 2.0231 | 0.787 | 0.7880 | 0.0475 | 0.0605 | | 0.1425 | 50.0 | 12500 | 0.7538 | 0.7867 | 0.3052 | 2.0267 | 0.7868 | 0.7870 | 0.0507 | 0.0603 | | 0.1425 | 51.0 | 12750 | 0.7529 | 0.7847 | 0.3081 | 2.0592 | 0.7847 | 0.7859 | 0.0467 | 0.0604 | | 0.1356 | 52.0 | 13000 | 0.7527 | 0.7808 | 0.3071 | 2.0349 | 0.7808 | 0.7818 | 0.0473 | 0.0607 | | 0.1356 | 53.0 | 13250 | 0.7451 | 0.7865 | 0.3049 | 2.0368 | 0.7865 | 0.7879 | 0.0484 | 0.0595 | | 0.1325 | 54.0 | 13500 | 0.7481 | 0.7857 | 0.3056 | 2.0223 | 0.7857 | 0.7869 | 0.0468 | 0.0603 | | 0.1325 | 55.0 | 13750 | 0.7470 | 0.7835 | 0.3057 | 2.0306 | 0.7835 | 0.7844 | 0.0492 | 0.0601 | | 0.1264 | 56.0 | 14000 | 0.7471 | 0.7873 | 0.3053 | 2.0336 | 0.7873 | 0.7880 | 0.0519 | 0.0601 | | 0.1264 | 57.0 | 14250 | 0.7429 | 0.7895 | 0.3032 | 2.0149 | 0.7895 | 0.7903 | 0.0468 | 0.0595 | | 0.1208 | 58.0 | 14500 | 0.7399 | 0.7885 | 0.3035 | 2.0147 | 0.7885 | 0.7895 | 0.0433 | 0.0596 | | 0.1208 | 59.0 | 14750 | 0.7518 | 0.786 | 0.3076 | 2.0481 | 0.786 | 0.7873 | 0.0403 | 0.0607 | | 0.119 | 60.0 | 15000 | 0.7483 | 0.7903 | 0.3058 | 2.0138 | 0.7903 | 0.7914 | 0.0471 | 0.0601 | | 0.119 | 61.0 | 15250 | 0.7463 | 0.7845 | 0.3043 | 2.0617 | 0.7845 | 0.7855 | 0.0458 | 0.0599 | | 0.1128 | 62.0 | 15500 | 0.7478 | 0.7875 | 0.3056 | 2.0187 | 0.7875 | 0.7888 | 0.0452 | 0.0604 | | 0.1128 | 63.0 | 15750 | 0.7510 | 0.784 | 0.3061 | 2.0204 | 0.7840 | 0.7850 | 0.0495 | 0.0605 | | 0.1109 | 64.0 | 16000 | 0.7424 | 0.786 | 0.3053 | 2.0167 | 0.786 | 0.7871 | 0.0449 | 0.0603 | | 0.1109 | 65.0 | 16250 | 0.7473 | 0.7885 | 0.3054 | 2.0200 | 0.7885 | 0.7893 | 0.0471 | 0.0600 | | 0.1078 | 66.0 | 16500 | 0.7467 | 0.7873 | 0.3054 | 2.0224 | 0.7873 | 0.7883 | 0.0482 | 0.0599 | | 0.1078 | 67.0 | 16750 | 0.7445 | 0.7893 | 0.3039 | 2.0082 | 0.7893 | 0.7895 | 0.0456 | 0.0593 | | 0.1051 | 68.0 | 17000 | 0.7490 | 0.7873 | 0.3063 | 2.0152 | 0.7873 | 0.7883 | 0.0505 | 0.0602 | | 0.1051 | 69.0 | 17250 | 0.7490 | 0.785 | 0.3061 | 2.0103 | 0.785 | 0.7861 | 0.0465 | 0.0602 | | 0.1009 | 70.0 | 17500 | 0.7445 | 0.7875 | 0.3049 | 2.0308 | 0.7875 | 0.7884 | 0.0483 | 0.0598 | | 0.1009 | 71.0 | 17750 | 0.7490 | 0.7863 | 0.3068 | 2.0260 | 0.7863 | 0.7875 | 0.0495 | 0.0604 | | 0.0984 | 72.0 | 18000 | 0.7465 | 0.7893 | 0.3059 | 2.0161 | 0.7893 | 0.7906 | 0.0427 | 0.0601 | | 0.0984 | 73.0 | 18250 | 0.7451 | 0.7873 | 0.3058 | 2.0204 | 0.7873 | 0.7882 | 0.0511 | 0.0605 | | 0.0966 | 74.0 | 18500 | 0.7445 | 0.7875 | 0.3042 | 2.0227 | 0.7875 | 0.7886 | 0.0495 | 0.0599 | | 0.0966 | 75.0 | 18750 | 0.7443 | 0.7863 | 0.3040 | 2.0138 | 0.7863 | 0.7872 | 0.0442 | 0.0598 | | 0.0947 | 76.0 | 19000 | 0.7448 | 0.7865 | 0.3054 | 2.0234 | 0.7865 | 0.7873 | 0.0457 | 0.0598 | | 0.0947 | 77.0 | 19250 | 0.7448 | 0.7865 | 0.3041 | 2.0110 | 0.7865 | 0.7875 | 0.0508 | 0.0596 | | 0.0931 | 78.0 | 19500 | 0.7460 | 0.7883 | 0.3040 | 2.0125 | 0.7883 | 0.7895 | 0.0467 | 0.0595 | | 0.0931 | 79.0 | 19750 | 0.7456 | 0.7883 | 0.3038 | 2.0302 | 0.7883 | 0.7894 | 0.0455 | 0.0596 | | 0.0899 | 80.0 | 20000 | 0.7469 | 0.788 | 0.3040 | 2.0188 | 0.788 | 0.7892 | 0.0487 | 0.0597 | | 0.0899 | 81.0 | 20250 | 0.7421 | 0.788 | 0.3041 | 2.0359 | 0.788 | 0.7888 | 0.0427 | 0.0595 | | 0.0882 | 82.0 | 20500 | 0.7444 | 0.7865 | 0.3051 | 2.0219 | 0.7865 | 0.7875 | 0.0479 | 0.0600 | | 0.0882 | 83.0 | 20750 | 0.7439 | 0.788 | 0.3039 | 2.0197 | 0.788 | 0.7894 | 0.0439 | 0.0597 | | 0.0871 | 84.0 | 21000 | 0.7421 | 0.7865 | 0.3040 | 1.9910 | 0.7865 | 0.7876 | 0.0445 | 0.0598 | | 0.0871 | 85.0 | 21250 | 0.7429 | 0.7887 | 0.3043 | 2.0253 | 0.7887 | 0.7898 | 0.0426 | 0.0597 | | 0.0869 | 86.0 | 21500 | 0.7442 | 0.7873 | 0.3041 | 2.0156 | 0.7873 | 0.7885 | 0.0488 | 0.0596 | | 0.0869 | 87.0 | 21750 | 0.7439 | 0.7857 | 0.3051 | 2.0099 | 0.7857 | 0.7867 | 0.0465 | 0.0599 | | 0.084 | 88.0 | 22000 | 0.7434 | 0.786 | 0.3040 | 1.9926 | 0.786 | 0.7869 | 0.0469 | 0.0598 | | 0.084 | 89.0 | 22250 | 0.7431 | 0.7873 | 0.3048 | 2.0028 | 0.7873 | 0.7880 | 0.0442 | 0.0599 | | 0.0821 | 90.0 | 22500 | 0.7447 | 0.7867 | 0.3040 | 2.0349 | 0.7868 | 0.7876 | 0.0477 | 0.0596 | | 0.0821 | 91.0 | 22750 | 0.7443 | 0.7877 | 0.3051 | 2.0356 | 0.7877 | 0.7887 | 0.0486 | 0.0601 | | 0.0813 | 92.0 | 23000 | 0.7500 | 0.7873 | 0.3053 | 2.0465 | 0.7873 | 0.7880 | 0.0484 | 0.0601 | | 0.0813 | 93.0 | 23250 | 0.7449 | 0.788 | 0.3037 | 1.9966 | 0.788 | 0.7890 | 0.0441 | 0.0594 | | 0.0811 | 94.0 | 23500 | 0.7466 | 0.7897 | 0.3048 | 2.0297 | 0.7897 | 0.7907 | 0.0429 | 0.0600 | | 0.0811 | 95.0 | 23750 | 0.7482 | 0.7875 | 0.3058 | 2.0319 | 0.7875 | 0.7885 | 0.0464 | 0.0601 | | 0.0808 | 96.0 | 24000 | 0.7473 | 0.7863 | 0.3055 | 2.0219 | 0.7863 | 0.7874 | 0.0477 | 0.0603 | | 0.0808 | 97.0 | 24250 | 0.7451 | 0.7855 | 0.3044 | 2.0356 | 0.7855 | 0.7865 | 0.0481 | 0.0594 | | 0.08 | 98.0 | 24500 | 0.7442 | 0.7857 | 0.3042 | 2.0213 | 0.7857 | 0.7868 | 0.0475 | 0.0595 | | 0.08 | 99.0 | 24750 | 0.7462 | 0.7863 | 0.3053 | 2.0354 | 0.7863 | 0.7874 | 0.0425 | 0.0599 | | 0.079 | 100.0 | 25000 | 0.7429 | 0.7853 | 0.3044 | 2.0364 | 0.7853 | 0.7862 | 0.0430 | 0.0599 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3

bdpc/resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t2.5_a0.5

bdpc

2023-10-04T01:11:55Z

191

0

transformers

[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T18:02:30Z

--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t2.5_a0.5 results: [] ---  # resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t2.5_a0.5 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5837 - Accuracy: 0.7867 - Brier Loss: 0.3013 - Nll: 1.9882 - F1 Micro: 0.7868 - F1 Macro: 0.7860 - Ece: 0.0529 - Aurc: 0.0581 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 250 | 4.1958 | 0.1035 | 0.9350 | 9.1004 | 0.1035 | 0.0792 | 0.0472 | 0.9013 | | 4.2322 | 2.0 | 500 | 4.0778 | 0.173 | 0.9251 | 6.5742 | 0.173 | 0.1393 | 0.0993 | 0.7501 | | 4.2322 | 3.0 | 750 | 3.6484 | 0.339 | 0.8778 | 4.9108 | 0.339 | 0.2957 | 0.2172 | 0.5305 | | 3.5256 | 4.0 | 1000 | 2.5967 | 0.4592 | 0.6991 | 3.3640 | 0.4592 | 0.4220 | 0.1274 | 0.3285 | | 3.5256 | 5.0 | 1250 | 2.0345 | 0.5417 | 0.6078 | 3.0118 | 0.5417 | 0.5180 | 0.0976 | 0.2447 | | 1.9172 | 6.0 | 1500 | 1.4417 | 0.625 | 0.5029 | 2.7890 | 0.625 | 0.6123 | 0.0549 | 0.1623 | | 1.9172 | 7.0 | 1750 | 1.3298 | 0.639 | 0.4852 | 2.6110 | 0.639 | 0.6320 | 0.0558 | 0.1501 | | 1.1801 | 8.0 | 2000 | 1.1697 | 0.674 | 0.4473 | 2.4787 | 0.674 | 0.6712 | 0.0466 | 0.1283 | | 1.1801 | 9.0 | 2250 | 0.9625 | 0.7093 | 0.4020 | 2.3242 | 0.7093 | 0.7085 | 0.0526 | 0.1017 | | 0.8029 | 10.0 | 2500 | 0.9477 | 0.7215 | 0.3893 | 2.3193 | 0.7215 | 0.7228 | 0.0515 | 0.0971 | | 0.8029 | 11.0 | 2750 | 0.8527 | 0.7375 | 0.3692 | 2.2785 | 0.7375 | 0.7377 | 0.0490 | 0.0870 | | 0.5717 | 12.0 | 3000 | 0.7377 | 0.7515 | 0.3470 | 2.1475 | 0.7515 | 0.7529 | 0.0552 | 0.0757 | | 0.5717 | 13.0 | 3250 | 0.7309 | 0.7498 | 0.3469 | 2.1250 | 0.7498 | 0.7494 | 0.0589 | 0.0758 | | 0.4414 | 14.0 | 3500 | 0.7165 | 0.7558 | 0.3427 | 2.1045 | 0.7558 | 0.7576 | 0.0582 | 0.0721 | | 0.4414 | 15.0 | 3750 | 0.6865 | 0.7678 | 0.3319 | 2.0457 | 0.7678 | 0.7688 | 0.0551 | 0.0697 | | 0.3691 | 16.0 | 4000 | 0.7002 | 0.7662 | 0.3348 | 2.1280 | 0.7663 | 0.7664 | 0.0567 | 0.0698 | | 0.3691 | 17.0 | 4250 | 0.6896 | 0.7628 | 0.3326 | 2.0750 | 0.7628 | 0.7631 | 0.0608 | 0.0691 | | 0.3214 | 18.0 | 4500 | 0.6666 | 0.7715 | 0.3258 | 2.0468 | 0.7715 | 0.7707 | 0.0544 | 0.0680 | | 0.3214 | 19.0 | 4750 | 0.6735 | 0.7702 | 0.3277 | 2.0544 | 0.7702 | 0.7700 | 0.0571 | 0.0681 | | 0.2914 | 20.0 | 5000 | 0.6607 | 0.772 | 0.3241 | 2.0364 | 0.772 | 0.7729 | 0.0525 | 0.0659 | | 0.2914 | 21.0 | 5250 | 0.6625 | 0.7688 | 0.3217 | 2.0387 | 0.7688 | 0.7703 | 0.0455 | 0.0664 | | 0.2653 | 22.0 | 5500 | 0.6543 | 0.775 | 0.3200 | 2.0560 | 0.775 | 0.7752 | 0.0507 | 0.0647 | | 0.2653 | 23.0 | 5750 | 0.6409 | 0.7725 | 0.3188 | 2.0091 | 0.7725 | 0.7733 | 0.0554 | 0.0647 | | 0.2482 | 24.0 | 6000 | 0.6452 | 0.7758 | 0.3191 | 2.0256 | 0.7758 | 0.7756 | 0.0502 | 0.0655 | | 0.2482 | 25.0 | 6250 | 0.6401 | 0.7742 | 0.3196 | 2.0668 | 0.7742 | 0.7745 | 0.0528 | 0.0648 | | 0.2354 | 26.0 | 6500 | 0.6316 | 0.775 | 0.3171 | 2.0150 | 0.775 | 0.7755 | 0.0555 | 0.0634 | | 0.2354 | 27.0 | 6750 | 0.6257 | 0.7808 | 0.3147 | 2.0129 | 0.7808 | 0.7808 | 0.0503 | 0.0624 | | 0.2229 | 28.0 | 7000 | 0.6343 | 0.7778 | 0.3144 | 2.0910 | 0.7778 | 0.7776 | 0.0510 | 0.0624 | | 0.2229 | 29.0 | 7250 | 0.6206 | 0.781 | 0.3115 | 2.0399 | 0.7810 | 0.7798 | 0.0555 | 0.0606 | | 0.2147 | 30.0 | 7500 | 0.6262 | 0.777 | 0.3124 | 2.0603 | 0.777 | 0.7772 | 0.0539 | 0.0616 | | 0.2147 | 31.0 | 7750 | 0.6265 | 0.7788 | 0.3137 | 2.0833 | 0.7788 | 0.7777 | 0.0532 | 0.0614 | | 0.2058 | 32.0 | 8000 | 0.6134 | 0.7815 | 0.3119 | 2.0369 | 0.7815 | 0.7815 | 0.0514 | 0.0615 | | 0.2058 | 33.0 | 8250 | 0.6153 | 0.7772 | 0.3133 | 2.0513 | 0.7773 | 0.7772 | 0.0534 | 0.0623 | | 0.1994 | 34.0 | 8500 | 0.6143 | 0.7853 | 0.3098 | 2.0188 | 0.7853 | 0.7857 | 0.0508 | 0.0611 | | 0.1994 | 35.0 | 8750 | 0.6096 | 0.7827 | 0.3086 | 2.0134 | 0.7828 | 0.7828 | 0.0512 | 0.0606 | | 0.1932 | 36.0 | 9000 | 0.6094 | 0.784 | 0.3067 | 2.0151 | 0.7840 | 0.7847 | 0.0471 | 0.0602 | | 0.1932 | 37.0 | 9250 | 0.6142 | 0.7833 | 0.3111 | 2.0213 | 0.7833 | 0.7829 | 0.0542 | 0.0608 | | 0.1895 | 38.0 | 9500 | 0.6103 | 0.7812 | 0.3094 | 2.0594 | 0.7812 | 0.7799 | 0.0529 | 0.0603 | | 0.1895 | 39.0 | 9750 | 0.6059 | 0.781 | 0.3078 | 2.0386 | 0.7810 | 0.7806 | 0.0545 | 0.0607 | | 0.1848 | 40.0 | 10000 | 0.6042 | 0.782 | 0.3072 | 2.0133 | 0.782 | 0.7824 | 0.0527 | 0.0603 | | 0.1848 | 41.0 | 10250 | 0.5991 | 0.785 | 0.3043 | 2.0124 | 0.785 | 0.7853 | 0.0496 | 0.0594 | | 0.1793 | 42.0 | 10500 | 0.6034 | 0.784 | 0.3058 | 2.0607 | 0.7840 | 0.7838 | 0.0490 | 0.0599 | | 0.1793 | 43.0 | 10750 | 0.6047 | 0.7827 | 0.3068 | 2.0139 | 0.7828 | 0.7819 | 0.0492 | 0.0595 | | 0.1768 | 44.0 | 11000 | 0.5982 | 0.785 | 0.3057 | 2.0303 | 0.785 | 0.7843 | 0.0473 | 0.0596 | | 0.1768 | 45.0 | 11250 | 0.6036 | 0.7795 | 0.3087 | 2.0173 | 0.7795 | 0.7788 | 0.0549 | 0.0607 | | 0.1743 | 46.0 | 11500 | 0.5974 | 0.785 | 0.3060 | 2.0026 | 0.785 | 0.7839 | 0.0478 | 0.0596 | | 0.1743 | 47.0 | 11750 | 0.5996 | 0.782 | 0.3068 | 2.0144 | 0.782 | 0.7825 | 0.0480 | 0.0598 | | 0.1707 | 48.0 | 12000 | 0.5958 | 0.7833 | 0.3079 | 2.0344 | 0.7833 | 0.7827 | 0.0500 | 0.0598 | | 0.1707 | 49.0 | 12250 | 0.5969 | 0.782 | 0.3060 | 2.0162 | 0.782 | 0.7820 | 0.0482 | 0.0597 | | 0.1683 | 50.0 | 12500 | 0.5933 | 0.784 | 0.3043 | 1.9897 | 0.7840 | 0.7836 | 0.0496 | 0.0589 | | 0.1683 | 51.0 | 12750 | 0.5935 | 0.7833 | 0.3042 | 2.0142 | 0.7833 | 0.7829 | 0.0501 | 0.0586 | | 0.1649 | 52.0 | 13000 | 0.5950 | 0.7847 | 0.3050 | 2.0125 | 0.7847 | 0.7851 | 0.0475 | 0.0591 | | 0.1649 | 53.0 | 13250 | 0.5904 | 0.7837 | 0.3020 | 1.9830 | 0.7837 | 0.7837 | 0.0504 | 0.0584 | | 0.1636 | 54.0 | 13500 | 0.5926 | 0.785 | 0.3042 | 2.0006 | 0.785 | 0.7845 | 0.0493 | 0.0588 | | 0.1636 | 55.0 | 13750 | 0.5885 | 0.7847 | 0.3029 | 2.0025 | 0.7847 | 0.7843 | 0.0505 | 0.0585 | | 0.1616 | 56.0 | 14000 | 0.5920 | 0.788 | 0.3041 | 2.0174 | 0.788 | 0.7878 | 0.0520 | 0.0591 | | 0.1616 | 57.0 | 14250 | 0.5927 | 0.7863 | 0.3033 | 2.0321 | 0.7863 | 0.7858 | 0.0521 | 0.0588 | | 0.1592 | 58.0 | 14500 | 0.5878 | 0.787 | 0.3017 | 1.9751 | 0.787 | 0.7874 | 0.0461 | 0.0584 | | 0.1592 | 59.0 | 14750 | 0.5888 | 0.7867 | 0.3030 | 1.9996 | 0.7868 | 0.7864 | 0.0494 | 0.0582 | | 0.1585 | 60.0 | 15000 | 0.5929 | 0.786 | 0.3052 | 2.0237 | 0.786 | 0.7857 | 0.0512 | 0.0584 | | 0.1585 | 61.0 | 15250 | 0.5894 | 0.7865 | 0.3026 | 1.9895 | 0.7865 | 0.7864 | 0.0548 | 0.0585 | | 0.1562 | 62.0 | 15500 | 0.5903 | 0.7873 | 0.3033 | 1.9670 | 0.7873 | 0.7870 | 0.0481 | 0.0584 | | 0.1562 | 63.0 | 15750 | 0.5896 | 0.7853 | 0.3023 | 1.9681 | 0.7853 | 0.7850 | 0.0520 | 0.0587 | | 0.1548 | 64.0 | 16000 | 0.5903 | 0.7847 | 0.3027 | 1.9865 | 0.7847 | 0.7846 | 0.0506 | 0.0587 | | 0.1548 | 65.0 | 16250 | 0.5910 | 0.7853 | 0.3039 | 2.0009 | 0.7853 | 0.7849 | 0.0515 | 0.0593 | | 0.1537 | 66.0 | 16500 | 0.5866 | 0.7883 | 0.3012 | 1.9561 | 0.7883 | 0.7881 | 0.0447 | 0.0581 | | 0.1537 | 67.0 | 16750 | 0.5858 | 0.7867 | 0.3009 | 1.9868 | 0.7868 | 0.7861 | 0.0486 | 0.0577 | | 0.1526 | 68.0 | 17000 | 0.5886 | 0.7867 | 0.3024 | 2.0009 | 0.7868 | 0.7862 | 0.0530 | 0.0587 | | 0.1526 | 69.0 | 17250 | 0.5850 | 0.7863 | 0.3010 | 2.0095 | 0.7863 | 0.7860 | 0.0510 | 0.0581 | | 0.1508 | 70.0 | 17500 | 0.5867 | 0.7865 | 0.3019 | 2.0304 | 0.7865 | 0.7861 | 0.0525 | 0.0583 | | 0.1508 | 71.0 | 17750 | 0.5895 | 0.7857 | 0.3038 | 2.0013 | 0.7857 | 0.7853 | 0.0478 | 0.0586 | | 0.15 | 72.0 | 18000 | 0.5894 | 0.7847 | 0.3025 | 2.0051 | 0.7847 | 0.7845 | 0.0500 | 0.0586 | | 0.15 | 73.0 | 18250 | 0.5867 | 0.7865 | 0.3022 | 1.9634 | 0.7865 | 0.7860 | 0.0489 | 0.0582 | | 0.149 | 74.0 | 18500 | 0.5888 | 0.7857 | 0.3026 | 1.9817 | 0.7857 | 0.7851 | 0.0497 | 0.0584 | | 0.149 | 75.0 | 18750 | 0.5823 | 0.7885 | 0.2994 | 1.9873 | 0.7885 | 0.7880 | 0.0476 | 0.0577 | | 0.1483 | 76.0 | 19000 | 0.5866 | 0.7853 | 0.3025 | 1.9870 | 0.7853 | 0.7849 | 0.0531 | 0.0583 | | 0.1483 | 77.0 | 19250 | 0.5866 | 0.7867 | 0.3013 | 1.9933 | 0.7868 | 0.7862 | 0.0498 | 0.0577 | | 0.1478 | 78.0 | 19500 | 0.5844 | 0.787 | 0.3010 | 1.9793 | 0.787 | 0.7868 | 0.0465 | 0.0579 | | 0.1478 | 79.0 | 19750 | 0.5850 | 0.7857 | 0.3005 | 1.9856 | 0.7857 | 0.7855 | 0.0489 | 0.0580 | | 0.1463 | 80.0 | 20000 | 0.5829 | 0.7893 | 0.2999 | 2.0003 | 0.7893 | 0.7890 | 0.0543 | 0.0578 | | 0.1463 | 81.0 | 20250 | 0.5845 | 0.7867 | 0.3011 | 2.0178 | 0.7868 | 0.7864 | 0.0494 | 0.0580 | | 0.1457 | 82.0 | 20500 | 0.5878 | 0.7865 | 0.3022 | 2.0108 | 0.7865 | 0.7861 | 0.0507 | 0.0583 | | 0.1457 | 83.0 | 20750 | 0.5862 | 0.7865 | 0.3016 | 1.9996 | 0.7865 | 0.7865 | 0.0505 | 0.0585 | | 0.1452 | 84.0 | 21000 | 0.5851 | 0.7863 | 0.3011 | 2.0002 | 0.7863 | 0.7859 | 0.0481 | 0.0582 | | 0.1452 | 85.0 | 21250 | 0.5850 | 0.787 | 0.3013 | 1.9659 | 0.787 | 0.7867 | 0.0524 | 0.0582 | | 0.1449 | 86.0 | 21500 | 0.5878 | 0.7867 | 0.3023 | 1.9837 | 0.7868 | 0.7866 | 0.0526 | 0.0581 | | 0.1449 | 87.0 | 21750 | 0.5844 | 0.7873 | 0.3010 | 1.9807 | 0.7873 | 0.7865 | 0.0522 | 0.0577 | | 0.1437 | 88.0 | 22000 | 0.5846 | 0.7877 | 0.3012 | 1.9947 | 0.7877 | 0.7869 | 0.0464 | 0.0580 | | 0.1437 | 89.0 | 22250 | 0.5859 | 0.787 | 0.3016 | 2.0002 | 0.787 | 0.7867 | 0.0503 | 0.0581 | | 0.143 | 90.0 | 22500 | 0.5838 | 0.7865 | 0.3010 | 1.9996 | 0.7865 | 0.7859 | 0.0496 | 0.0576 | | 0.143 | 91.0 | 22750 | 0.5843 | 0.7837 | 0.3011 | 1.9683 | 0.7837 | 0.7834 | 0.0501 | 0.0583 | | 0.1426 | 92.0 | 23000 | 0.5843 | 0.7873 | 0.3010 | 1.9960 | 0.7873 | 0.7870 | 0.0524 | 0.0578 | | 0.1426 | 93.0 | 23250 | 0.5827 | 0.7847 | 0.3005 | 1.9719 | 0.7847 | 0.7844 | 0.0506 | 0.0579 | | 0.1428 | 94.0 | 23500 | 0.5831 | 0.7865 | 0.3009 | 1.9781 | 0.7865 | 0.7862 | 0.0517 | 0.0579 | | 0.1428 | 95.0 | 23750 | 0.5821 | 0.784 | 0.3001 | 1.9641 | 0.7840 | 0.7838 | 0.0505 | 0.0579 | | 0.1424 | 96.0 | 24000 | 0.5850 | 0.7845 | 0.3020 | 1.9667 | 0.7845 | 0.7842 | 0.0526 | 0.0584 | | 0.1424 | 97.0 | 24250 | 0.5850 | 0.7847 | 0.3012 | 1.9776 | 0.7847 | 0.7844 | 0.0508 | 0.0579 | | 0.142 | 98.0 | 24500 | 0.5845 | 0.7877 | 0.3011 | 1.9745 | 0.7877 | 0.7870 | 0.0491 | 0.0579 | | 0.142 | 99.0 | 24750 | 0.5834 | 0.7853 | 0.3010 | 1.9679 | 0.7853 | 0.7852 | 0.0506 | 0.0581 | | 0.1416 | 100.0 | 25000 | 0.5837 | 0.7867 | 0.3013 | 1.9882 | 0.7868 | 0.7860 | 0.0529 | 0.0581 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3

LarryAIDraw/ijichi_seika-10

LarryAIDraw

2023-10-04T01:01:15Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-10-04T00:56:27Z

--- license: creativeml-openrail-m --- https://civitai.com/models/154638/ijichi-seika-bocchi-the-rock-lora

LarryAIDraw/Hwahjah_v1

LarryAIDraw

2023-10-04T00:54:00Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-10-04T00:50:01Z

--- license: creativeml-openrail-m --- https://civitai.com/models/155533/hwah-jah-azur-lane

LarryAIDraw/ShinanoSummerFluffV1

LarryAIDraw

2023-10-04T00:53:28Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-10-04T00:49:09Z

--- license: creativeml-openrail-m --- https://civitai.com/models/155698/shinano-greaterdreamy-white-sandsless-or-swimsuit-skin-or-azur-lane

LarryAIDraw/topaz_hsr

LarryAIDraw

2023-10-04T00:53:11Z

0

null

[ "license:creativeml-openrail-m", "region:us" ]

null

2023-10-04T00:48:39Z

--- license: creativeml-openrail-m --- https://civitai.com/models/156239/topaz-honkai-star-rail

CrypticOwl5503/sd-class-butterflies-32

CrypticOwl5503

2023-10-04T00:45:22Z

44

0

diffusers

[ "diffusers", "safetensors", "pytorch", "unconditional-image-generation", "diffusion-models-class", "license:mit", "diffusers:DDPMPipeline", "region:us" ]

unconditional-image-generation

2023-10-04T00:45:13Z

--- license: mit tags: - pytorch - diffusers - unconditional-image-generation - diffusion-models-class --- # Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class) This model is a diffusion model for unconditional image generation of cute 🦋. ## Usage ```python from diffusers import DDPMPipeline pipeline = DDPMPipeline.from_pretrained('CrypticOwl5503/sd-class-butterflies-32') image = pipeline().images[0] image ```

adamo1139/PS_AD_O365_Mistral_7B_02_GGUF

adamo1139

2023-10-04T00:20:20Z

0

null

[ "gguf", "license:apache-2.0", "endpoints_compatible", "region:us" ]

null

2023-10-03T21:41:30Z

--- license: apache-2.0 --- GGUF q4_k_m quantization of QLoRA on semi-synthetic dataset with knowledge about PowerShell, Office 365 and Active Directory. Prompt format Pupil:{question}Teacher:{Response}

SinanAkkoyun/TinyLlama-1.1B-Chat-v0.3-exl2

SinanAkkoyun

2023-10-04T00:04:06Z

1

0

null

[ "license:apache-2.0", "region:us" ]

null

2023-10-04T00:01:33Z

--- license: apache-2.0 --- This is an EXL2 quantization of [PY007/TinyLlama-1.1B-Chat-v0.3](https://huggingface.co/PY007/TinyLlama-1.1B-Chat-v0.3) [3.0bpw](https://huggingface.co/SinanAkkoyun/TinyLlama-1.1B-Chat-v0.3-exl2/tree/3.0bpw) Check out the awesome [Exllama V2 repo](https://github.com/turboderp/exllamav2)

duytintruong/dqn-SpaceInvadersNoFrameskip-v4

duytintruong

2023-10-03T23:49:21Z

1

0

stable-baselines3

[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-10-03T23:48:45Z

--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 692.50 +/- 156.29 name: mean_reward verified: false --- # **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga duytintruong -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga duytintruong -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga duytintruong ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```

Rtrggf/Type-A

Rtrggf

2023-10-03T23:47:55Z

0

adapter-transformers

[ "adapter-transformers", "art", "text-to-video", "ae", "dataset:fka/awesome-chatgpt-prompts", "license:openrail", "region:us" ]

text-to-video

2023-10-03T23:35:04Z

--- license: openrail datasets: - fka/awesome-chatgpt-prompts language: - ae metrics: - accuracy library_name: adapter-transformers pipeline_tag: text-to-video tags: - art --- using System; using System.Drawing; using AForge.Video.FFMPEG; class Program { static void Main() { var videoWriter = new VideoFileWriter(); videoWriter.Open("output.mp4", 640, 480, 25, VideoCodec.MPEG4); for (int i = 0; i < 10; i++) { Bitmap image = (Bitmap)Image.FromFile($"image{i}.jpg"); videoWriter.WriteVideoFrame(image); image.Dispose(); } videoWriter.Close(); } }

codyreading/dreambooth-bear-lawn2

codyreading

2023-10-03T23:42:12Z

28

0

diffusers

[ "diffusers", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "dreambooth", "base_model:runwayml/stable-diffusion-v1-5", "base_model:finetune:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

2023-10-03T23:34:35Z

--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 instance_prompt: A photo of sks stuffed animal tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - dreambooth inference: true --- # DreamBooth - codyreading/dreambooth-bear-lawn2 This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on A photo of sks stuffed animal using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. DreamBooth for the text encoder was enabled: False.

Joshua-shadow/kjkj

Joshua-shadow

2023-10-03T23:40:04Z

0

null

[ "license:other", "region:us" ]

null

2023-10-03T23:36:52Z

--- license: other license_name: me license_link: LICENSE ---

bdpc/resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t1.0_a1.0

bdpc

2023-10-03T23:23:57Z

199

0

transformers

[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T19:12:41Z

--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t1.0_a1.0 results: [] ---  # resnet101_rvl-cdip-cnn_rvl_cdip-NK1000_kd_CEKD_t1.0_a1.0 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.7844 - Accuracy: 0.742 - Brier Loss: 0.4405 - Nll: 2.8680 - F1 Micro: 0.7420 - F1 Macro: 0.7411 - Ece: 0.1946 - Aurc: 0.1002 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 250 | 2.7345 | 0.153 | 0.9327 | 8.3371 | 0.153 | 0.1246 | 0.0866 | 0.7933 | | 2.6983 | 2.0 | 500 | 2.4500 | 0.4213 | 0.8816 | 4.7062 | 0.4213 | 0.3924 | 0.3073 | 0.4444 | | 2.6983 | 3.0 | 750 | 1.7959 | 0.5012 | 0.7003 | 3.3576 | 0.5012 | 0.4758 | 0.1869 | 0.3051 | | 1.7341 | 4.0 | 1000 | 1.3637 | 0.5985 | 0.5511 | 2.8818 | 0.5985 | 0.5868 | 0.1005 | 0.1935 | | 1.7341 | 5.0 | 1250 | 1.1978 | 0.6498 | 0.4862 | 2.7546 | 0.6498 | 0.6471 | 0.0826 | 0.1500 | | 1.0818 | 6.0 | 1500 | 1.0812 | 0.6853 | 0.4364 | 2.6325 | 0.6853 | 0.6845 | 0.0522 | 0.1217 | | 1.0818 | 7.0 | 1750 | 1.0276 | 0.7013 | 0.4149 | 2.5542 | 0.7013 | 0.7003 | 0.0397 | 0.1108 | | 0.7498 | 8.0 | 2000 | 0.9724 | 0.7133 | 0.3944 | 2.4773 | 0.7133 | 0.7129 | 0.0505 | 0.1040 | | 0.7498 | 9.0 | 2250 | 0.9777 | 0.7248 | 0.3924 | 2.4916 | 0.7248 | 0.7242 | 0.0628 | 0.0992 | | 0.5034 | 10.0 | 2500 | 1.0027 | 0.724 | 0.3976 | 2.4974 | 0.724 | 0.7250 | 0.0751 | 0.1032 | | 0.5034 | 11.0 | 2750 | 0.9979 | 0.729 | 0.3913 | 2.5344 | 0.729 | 0.7295 | 0.0805 | 0.0988 | | 0.3237 | 12.0 | 3000 | 1.0553 | 0.7192 | 0.4075 | 2.6242 | 0.7192 | 0.7193 | 0.0963 | 0.1072 | | 0.3237 | 13.0 | 3250 | 1.1162 | 0.7175 | 0.4139 | 2.6543 | 0.7175 | 0.7185 | 0.1295 | 0.1093 | | 0.2023 | 14.0 | 3500 | 1.1259 | 0.725 | 0.4140 | 2.6758 | 0.7250 | 0.7246 | 0.1237 | 0.1055 | | 0.2023 | 15.0 | 3750 | 1.2728 | 0.7115 | 0.4381 | 2.8308 | 0.7115 | 0.7147 | 0.1464 | 0.1168 | | 0.1264 | 16.0 | 4000 | 1.2664 | 0.7222 | 0.4296 | 2.8434 | 0.7223 | 0.7236 | 0.1523 | 0.1107 | | 0.1264 | 17.0 | 4250 | 1.2620 | 0.724 | 0.4252 | 2.7990 | 0.724 | 0.7252 | 0.1563 | 0.1066 | | 0.0802 | 18.0 | 4500 | 1.3362 | 0.727 | 0.4293 | 2.8642 | 0.7270 | 0.7267 | 0.1653 | 0.1090 | | 0.0802 | 19.0 | 4750 | 1.3608 | 0.7302 | 0.4288 | 2.7893 | 0.7302 | 0.7318 | 0.1637 | 0.1059 | | 0.0553 | 20.0 | 5000 | 1.3757 | 0.7308 | 0.4303 | 2.8861 | 0.7308 | 0.7300 | 0.1670 | 0.1073 | | 0.0553 | 21.0 | 5250 | 1.4947 | 0.7295 | 0.4420 | 2.8306 | 0.7295 | 0.7300 | 0.1770 | 0.1128 | | 0.0329 | 22.0 | 5500 | 1.5338 | 0.7265 | 0.4416 | 2.8729 | 0.7265 | 0.7273 | 0.1808 | 0.1097 | | 0.0329 | 23.0 | 5750 | 1.5127 | 0.7355 | 0.4362 | 2.8574 | 0.7355 | 0.7366 | 0.1774 | 0.1045 | | 0.0258 | 24.0 | 6000 | 1.5189 | 0.7352 | 0.4360 | 2.8435 | 0.7353 | 0.7344 | 0.1784 | 0.1030 | | 0.0258 | 25.0 | 6250 | 1.5802 | 0.7362 | 0.4404 | 2.8399 | 0.7362 | 0.7362 | 0.1847 | 0.1013 | | 0.0193 | 26.0 | 6500 | 1.5869 | 0.737 | 0.4378 | 2.8237 | 0.737 | 0.7362 | 0.1846 | 0.1022 | | 0.0193 | 27.0 | 6750 | 1.6160 | 0.7365 | 0.4373 | 2.7928 | 0.7365 | 0.7360 | 0.1864 | 0.1049 | | 0.014 | 28.0 | 7000 | 1.6775 | 0.7372 | 0.4426 | 2.9236 | 0.7372 | 0.7373 | 0.1909 | 0.1039 | | 0.014 | 29.0 | 7250 | 1.6391 | 0.736 | 0.4370 | 2.8717 | 0.736 | 0.7358 | 0.1905 | 0.0999 | | 0.0132 | 30.0 | 7500 | 1.6804 | 0.7355 | 0.4434 | 2.8397 | 0.7355 | 0.7360 | 0.1903 | 0.1067 | | 0.0132 | 31.0 | 7750 | 1.6809 | 0.738 | 0.4386 | 2.8853 | 0.738 | 0.7387 | 0.1920 | 0.1015 | | 0.0121 | 32.0 | 8000 | 1.6953 | 0.734 | 0.4443 | 2.8451 | 0.734 | 0.7342 | 0.1961 | 0.1013 | | 0.0121 | 33.0 | 8250 | 1.7184 | 0.7425 | 0.4344 | 2.8180 | 0.7425 | 0.7423 | 0.1910 | 0.1014 | | 0.0098 | 34.0 | 8500 | 1.7151 | 0.735 | 0.4445 | 2.8532 | 0.735 | 0.7337 | 0.1952 | 0.1000 | | 0.0098 | 35.0 | 8750 | 1.7781 | 0.7338 | 0.4484 | 2.8133 | 0.7338 | 0.7351 | 0.1999 | 0.1052 | | 0.0086 | 36.0 | 9000 | 1.7540 | 0.7372 | 0.4443 | 2.8388 | 0.7372 | 0.7388 | 0.1954 | 0.1039 | | 0.0086 | 37.0 | 9250 | 1.7744 | 0.738 | 0.4474 | 2.8600 | 0.738 | 0.7390 | 0.1953 | 0.1057 | | 0.0079 | 38.0 | 9500 | 1.7446 | 0.7368 | 0.4417 | 2.8485 | 0.7367 | 0.7374 | 0.1972 | 0.1016 | | 0.0079 | 39.0 | 9750 | 1.7700 | 0.739 | 0.4398 | 2.8826 | 0.739 | 0.7395 | 0.1970 | 0.1023 | | 0.0076 | 40.0 | 10000 | 1.7896 | 0.7368 | 0.4442 | 2.8449 | 0.7367 | 0.7376 | 0.1988 | 0.1033 | | 0.0076 | 41.0 | 10250 | 1.7435 | 0.7402 | 0.4387 | 2.8390 | 0.7402 | 0.7405 | 0.1926 | 0.1031 | | 0.0074 | 42.0 | 10500 | 1.7837 | 0.7338 | 0.4470 | 2.8191 | 0.7338 | 0.7339 | 0.2018 | 0.1035 | | 0.0074 | 43.0 | 10750 | 1.8015 | 0.7392 | 0.4427 | 2.8093 | 0.7392 | 0.7401 | 0.1981 | 0.1017 | | 0.0061 | 44.0 | 11000 | 1.8155 | 0.739 | 0.4449 | 2.8333 | 0.739 | 0.7406 | 0.1983 | 0.1022 | | 0.0061 | 45.0 | 11250 | 1.7958 | 0.7392 | 0.4426 | 2.8161 | 0.7392 | 0.7385 | 0.1963 | 0.1039 | | 0.0059 | 46.0 | 11500 | 1.8089 | 0.7422 | 0.4411 | 2.8174 | 0.7422 | 0.7422 | 0.1955 | 0.1011 | | 0.0059 | 47.0 | 11750 | 1.8125 | 0.743 | 0.4386 | 2.8184 | 0.743 | 0.7435 | 0.1939 | 0.1012 | | 0.0053 | 48.0 | 12000 | 1.8004 | 0.7372 | 0.4432 | 2.8413 | 0.7372 | 0.7371 | 0.1995 | 0.1023 | | 0.0053 | 49.0 | 12250 | 1.8075 | 0.7405 | 0.4392 | 2.8569 | 0.7405 | 0.7397 | 0.1962 | 0.1015 | | 0.0055 | 50.0 | 12500 | 1.7844 | 0.742 | 0.4405 | 2.8680 | 0.7420 | 0.7411 | 0.1946 | 0.1002 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3

gyaan/ppo-Huggy

gyaan

2023-10-03T23:21:40Z

0

ml-agents

[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]

reinforcement-learning

2023-10-03T23:21:35Z

--- library_name: ml-agents tags: - Huggy - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Huggy --- # **ppo** Agent playing **Huggy** This is a trained model of a **ppo** agent playing **Huggy** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: gyaan/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

zkdeng/swin-tiny-patch4-window7-224-finetuned-eurosat

zkdeng

2023-10-03T23:18:32Z

213

0

transformers

[ "transformers", "pytorch", "swin", "image-classification", "generated_from_trainer", "base_model:microsoft/swin-tiny-patch4-window7-224", "base_model:finetune:microsoft/swin-tiny-patch4-window7-224", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T22:41:35Z

--- license: apache-2.0 base_model: microsoft/swin-tiny-patch4-window7-224 tags: - generated_from_trainer metrics: - accuracy model-index: - name: swin-tiny-patch4-window7-224-finetuned-eurosat results: [] ---  # swin-tiny-patch4-window7-224-finetuned-eurosat This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2188 - Accuracy: 0.92 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.6077 | 0.96 | 12 | 0.3408 | 0.895 | | 0.3469 | 2.0 | 25 | 0.2188 | 0.92 | | 0.2627 | 2.88 | 36 | 0.2183 | 0.915 | ### Framework versions - Transformers 4.34.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0

jonale/q-FrozenLake-v1-4x4-noSlippery

jonale

2023-10-03T23:15:51Z

0

null

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

reinforcement-learning

2023-10-03T23:15:48Z

--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="jonale/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

sd-concepts-library/ahx-beta-51c9767

sd-concepts-library

2023-10-03T23:15:13Z

0

null

[ "license:mit", "region:us" ]

null

2023-10-03T23:15:10Z

--- license: mit --- ### ahx-beta-51c9767 on Stable Diffusion This is the `<ahx-beta-51c9767>` concept taught to Stable Diffusion via Textual Inversion. You can load this concept into the [Stable Conceptualizer](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_conceptualizer_inference.ipynb) notebook. You can also train your own concepts and load them into the concept libraries using [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb). Here is the new concept you will be able to use as a `style`: ![<ahx-beta-51c9767> 0](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/5.jpeg) ![<ahx-beta-51c9767> 1](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/7.jpeg) ![<ahx-beta-51c9767> 2](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/2.jpeg) ![<ahx-beta-51c9767> 3](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/0.jpeg) ![<ahx-beta-51c9767> 4](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/1.jpeg) ![<ahx-beta-51c9767> 5](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/4.jpeg) ![<ahx-beta-51c9767> 6](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/6.jpeg) ![<ahx-beta-51c9767> 7](https://huggingface.co/sd-concepts-library/ahx-beta-51c9767/resolve/main/concept_images/3.jpeg)

Adrian101-hnd/q-FrozenLake-v1-4x4-noSlippery

Adrian101-hnd

2023-10-03T22:51:51Z

0

null

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

reinforcement-learning

2023-10-03T22:51:48Z

--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="Adrian101-hnd/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

YuvanKumar/ppo-LunarLander-v2

YuvanKumar

2023-10-03T22:49:01Z

0

stable-baselines3

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

reinforcement-learning

2023-10-03T22:48:43Z

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 280.16 +/- 13.38 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

ipipan/nlpre_spacy_nkjp_pl-core-news-lg_nkjp-by-name

ipipan

2023-10-03T22:36:55Z

0

null

[ "region:us" ]

null

2023-09-29T17:04:31Z

# Model description - Morphosyntactic analyzer: Spacy - Tagset: NKJP - Embedding vectors: pl-core-news-lg - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_spacy_nkjp_pl-core-news-lg_nkjp-by-name ``` ## Load model ``` import spacy model_name = './nlpre_spacy_nkjp_pl-core-news-lg_nkjp-by-name' model_upos = spacy.load(model_name + '/upos') model_xpos = spacy.load(model_name + '/xpos+lemma') ```

ipipan/nlpre_spacy_ud_pl-core-news-lg_nkjp-by-name

ipipan

2023-10-03T22:33:59Z

0

null

[ "region:us" ]

null

2023-09-29T16:38:32Z

# Model description - Morphosyntactic analyzer: Spacy - Tagset: UD - Embedding vectors: pl-core-news-lg - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_spacy_ud_pl-core-news-lg_nkjp-by-name ``` ## Load model ``` import spacy model_name = './nlpre_spacy_ud_pl-core-news-lg_nkjp-by-name/model-best' model = spacy.load(model_name) ```

ipipan/nlpre_spacy_ud_transformer_nkjp-by-type

ipipan

2023-10-03T22:33:42Z

0

null

[ "region:us" ]

null

2023-09-29T15:51:30Z

# Model description - Morphosyntactic analyzer: Spacy - Tagset: UD - Embedding vectors: Transformer - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_spacy_ud_transformer_nkjp-by-type ``` ## Load model ``` import spacy model_name = './nlpre_spacy_ud_transformer_nkjp-by-type/model-best' model = spacy.load(model_name) ```

LoneStriker/airoboros-mistral2.2-7b-8.0bpw-h6-exl2

LoneStriker

2023-10-03T22:20:40Z

5

0

transformers

[ "transformers", "pytorch", "mistral", "text-generation", "llama-2", "instruct", "finetune", "alpaca", "gpt4", "synthetic data", "distillation", "en", "dataset:jondurbin/airoboros-2.2.1", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-10-03T20:35:02Z

--- base_model: mistralai/Mistral-7b-V0.1 tags: - llama-2 - instruct - finetune - alpaca - gpt4 - synthetic data - distillation datasets: - jondurbin/airoboros-2.2.1 model-index: - name: airoboros2.2-mistral-7b results: [] license: mit language: - en --- Mistral trained with the airoboros dataset! ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/sbN_PCdxO_LV0xpFGA_St.png) Actual dataset is airoboros 2.2, but it seems to have been replaced on hf with 2.2.1. Prompt Format: ``` USER: <prompt> ASSISTANT: ``` TruthfulQA: ``` hf-causal-experimental (pretrained=/home/teknium/dakota/lm-evaluation-harness/airoboros2.2-mistral/,dtype=float16), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8 | Task |Version|Metric|Value | |Stderr| |-------------|------:|------|-----:|---|-----:| |truthfulqa_mc| 1|mc1 |0.3562|± |0.0168| | | |mc2 |0.5217|± |0.0156| ``` Wandb training charts: https://wandb.ai/teknium1/airoboros-mistral-7b/runs/airoboros-mistral-1?workspace=user-teknium1 More info to come

ipipan/nlpre_combo_ud_herBERT_nkjp-by-name

ipipan

2023-10-03T22:16:22Z

0

null

[ "region:us" ]

null

2023-09-29T15:35:38Z

# Model description - Morphosyntactic analyzer: COMBO - Tagset: UD - Embedding vectors: HerBERT (wiki) - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_ud_herBERT_nkjp-by-name ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_ud_herBERT_nkjp-by-name' model = COMBO.from_pretrained(model_name) ```

ipipan/nlpre_combo_ud_herBERT_nkjp-by-type

ipipan

2023-10-03T22:15:55Z

0

null

[ "region:us" ]

null

2023-09-29T15:35:27Z

# Model description - Morphosyntactic analyzer: COMBO - Tagset: UD - Embedding vectors: HerBERT (wiki) - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_ud_herBERT_nkjp-by-type ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_ud_herBERT_nkjp-by-type' model = COMBO.from_pretrained(model_name) ```

ipipan/nlpre_combo_nkjp_herBERT_nkjp-by-type

ipipan

2023-10-03T22:15:26Z

0

null

[ "region:us" ]

null

2023-09-29T15:34:36Z

# Model description - Morphosyntactic analyzer: COMBO - Tagset: NKJP - Embedding vectors: HerBERT (wiki) - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_nkjp_herBERT_nkjp-by-type ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_nkjp_herBERT_nkjp-by-type' model = COMBO.from_pretrained(model_name) ```

ipipan/nlpre_combo_nkjp_herBERT_nkjp-by-name

ipipan

2023-10-03T22:14:57Z

0

null

[ "region:us" ]

null

2023-09-29T15:34:23Z

# Model description - Morphosyntactic analyzer: COMBO - Tagset: NKJP - Embedding vectors: HerBERT (wiki) - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_nkjp_herBERT_nkjp-by-name ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_nkjp_herBERT_nkjp-by-name' model = COMBO.from_pretrained(model_name) ```

ipipan/nlpre_combo_nkjp_fasttext_nkjp-by-type

ipipan

2023-10-03T22:13:45Z

0

null

[ "region:us" ]

null

2023-09-29T14:40:21Z

# Model description - Morphosyntactic analyzer: COMBO - Tagset: NKJP - Embedding vectors: Fasttext (wiki) - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_nkjp_fasttext_nkjp-by-type ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_nkjp_fasttext_nkjp-by-type' model = COMBO.from_pretrained(model_name) ```

ipipan/nlpre_combo_ud_fasttext_nkjp-by-name

ipipan

2023-10-03T22:12:54Z

0

null

[ "region:us" ]

null

2023-09-29T14:39:43Z

# Model description - Morphosyntactic analyzer: COMBO - Tagset: UD - Embedding vectors: Fasttext (wiki) - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_ud_fasttext_nkjp-by-name ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_ud_fasttext_nkjp-by-name' model = COMBO.from_pretrained(model_name) ```

ipipan/nlpre_combo_ud_fasttext_nkjp-by-type

ipipan

2023-10-03T22:12:22Z

0

null

[ "region:us" ]

null

2023-09-29T14:39:23Z

# Model description - Morphosyntactic analyzer: COMBO - Tagset: UD - Embedding vectors: Fasttext (wiki) - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_combo_ud_fasttext_nkjp-by-type ``` ## Load model ``` from combo.predict import COMBO model_name = './nlpre_combo_ud_fasttext_nkjp-by-type' model = COMBO.from_pretrained(model_name) ```

ipipan/nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-type

ipipan

2023-10-03T22:05:45Z

0

null

[ "region:us" ]

null

2023-09-29T09:08:44Z

# Model description - Morphosyntactic analyzer: Trankit - Tagset: NKJP - Embedding vectors: XLM-RoBERTa-Base - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-type ``` ## Load model ``` import trankit model_path = './nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-type' trankit.verify_customized_pipeline( category='customized-mwt', # pipeline category save_dir=model_path, # directory used for saving models in previous steps embedding_name='xlm-roberta-base' # embedding version that we use for training our customized pipeline, by default, it is `xlm-roberta-base` ) model = trankit.Pipeline(lang='customized-mwt', cache_dir=model_path, embedding='xlm-roberta-base') ```

ipipan/nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-name

ipipan

2023-10-03T22:05:05Z

0

null

[ "region:us" ]

null

2023-09-29T09:08:28Z

# Model description - Morphosyntactic analyzer: Trankit - Tagset: NKJP - Embedding vectors: XLM-RoBERTa-Base - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-name ``` ## Load model ``` import trankit model_path = './nlpre_trankit_nkjp_xlm-roberta-base_nkjp-by-name' trankit.verify_customized_pipeline( category='customized-mwt', # pipeline category save_dir=model_path, # directory used for saving models in previous steps embedding_name='xlm-roberta-base' # embedding version that we use for training our customized pipeline, by default, it is `xlm-roberta-base` ) model = trankit.Pipeline(lang='customized-mwt', cache_dir=model_path, embedding='xlm-roberta-base') ```

SkunkworksAI/Mistralic-7B-1

SkunkworksAI

2023-10-03T22:04:49Z

52

26

transformers

[ "transformers", "pytorch", "endpoints_compatible", "region:us" ]

null

2023-09-29T23:45:09Z

<p><h1> 🦾 Mistralic-7B-1 🦾 </h1></p> Special thanks to Together Compute for sponsoring Skunkworks with compute! **INFERENCE** ``` import torch from transformers import AutoModelForCausalLM, AutoTokenizer torch.set_default_device('cuda') system_prompt = "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n" system_no_input_prompt = "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n" def generate_prompt(instruction, input=None): if input: prompt = f"### System:\n{system_prompt}\n\n" else: prompt = f"### System:\n{system_no_input_prompt}\n\n" prompt += f"### Instruction:\n{instruction}\n\n" if input: prompt += f"### Input:\n{input}\n\n" return prompt + """### Response:\n""" device = "cuda" model = AutoModelForCausalLM.from_pretrained("SkunkworksAI/Mistralic-7B-1") tokenizer = AutoTokenizer.from_pretrained("SkunkworksAI/Mistralic-7B-1") while True: instruction = input("Enter Instruction: ") instruction = generate_prompt(instruction) inputs = tokenizer(instruction, return_tensors="pt", return_attention_mask=False) outputs = model.generate(**inputs, max_length=1000, do_sample=True, temperature=0.01, use_cache=True, eos_token_id=tokenizer.eos_token_id) text = tokenizer.batch_decode(outputs)[0] print(text) ``` **EVALUATION** ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64b7e345f92b20f7a38bf47a/ycpNhdGZHGbai_wslT2Bg.png) Average: 0.72157 For comparison: mistralai/Mistral-7B-v0.1 scores 0.7116 mistralai/Mistral-7B-Instruct-v0.1 scores 0.6794

ipipan/nlpre_trankit_ud_xlm-roberta-base_nkjp-by-name

ipipan

2023-10-03T22:04:29Z

0

null

[ "region:us" ]

null

2023-09-29T09:00:18Z

# Model description - Morphosyntactic analyzer: Trankit - Tagset: UD - Embedding vectors: XLM-RoBERTa-Base - Dataset: NLPrePL-NKJP-fair-by-name (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_trankit_ud_xlm-roberta-base_nkjp-by-name ``` ## Load model ``` import trankit model_path = './nlpre_trankit_ud_xlm-roberta-base_nkjp-by-name' trankit.verify_customized_pipeline( category='customized-mwt', # pipeline category save_dir=model_path, # directory used for saving models in previous steps embedding_name='xlm-roberta-base' # embedding version that we use for training our customized pipeline, by default, it is `xlm-roberta-base` ) model = trankit.Pipeline(lang='customized-mwt', cache_dir=model_path, embedding='xlm-roberta-base') ```

LoneStriker/airoboros-mistral2.2-7b-6.0bpw-h6-exl2

LoneStriker

2023-10-03T22:02:52Z

5

0

transformers

[ "transformers", "pytorch", "mistral", "text-generation", "llama-2", "instruct", "finetune", "alpaca", "gpt4", "synthetic data", "distillation", "en", "dataset:jondurbin/airoboros-2.2.1", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-10-03T20:34:58Z

--- base_model: mistralai/Mistral-7b-V0.1 tags: - llama-2 - instruct - finetune - alpaca - gpt4 - synthetic data - distillation datasets: - jondurbin/airoboros-2.2.1 model-index: - name: airoboros2.2-mistral-7b results: [] license: mit language: - en --- Mistral trained with the airoboros dataset! ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/sbN_PCdxO_LV0xpFGA_St.png) Actual dataset is airoboros 2.2, but it seems to have been replaced on hf with 2.2.1. Prompt Format: ``` USER: <prompt> ASSISTANT: ``` TruthfulQA: ``` hf-causal-experimental (pretrained=/home/teknium/dakota/lm-evaluation-harness/airoboros2.2-mistral/,dtype=float16), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8 | Task |Version|Metric|Value | |Stderr| |-------------|------:|------|-----:|---|-----:| |truthfulqa_mc| 1|mc1 |0.3562|± |0.0168| | | |mc2 |0.5217|± |0.0156| ``` Wandb training charts: https://wandb.ai/teknium1/airoboros-mistral-7b/runs/airoboros-mistral-1?workspace=user-teknium1 More info to come

NAB1108/News_Recommendation

NAB1108

2023-10-03T22:00:57Z

3

0

sentence-transformers

[ "sentence-transformers", "pytorch", "mpnet", "setfit", "text-classification", "arxiv:2209.11055", "license:apache-2.0", "region:us" ]

text-classification

2023-10-03T14:22:20Z

--- license: apache-2.0 tags: - setfit - sentence-transformers - text-classification pipeline_tag: text-classification --- # NAB1108/News_Recommendation This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Usage To use this model for inference, first install the SetFit library: ```bash python -m pip install setfit ``` You can then run inference as follows: ```python from setfit import SetFitModel # Download from Hub and run inference model = SetFitModel.from_pretrained("NAB1108/News_Recommendation") # Run inference preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"]) ``` ## BibTeX entry and citation info ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ```

fernandohf/model_en_pt

fernandohf

2023-10-03T21:52:04Z

3

0

transformers

[ "transformers", "pytorch", "t5", "text2text-generation", "generated_from_trainer", "dataset:opus_books", "base_model:google-t5/t5-small", "base_model:finetune:google-t5/t5-small", "license:apache-2.0", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text2text-generation

2023-10-03T20:15:33Z

--- license: apache-2.0 base_model: t5-small tags: - generated_from_trainer datasets: - opus_books metrics: - bleu model-index: - name: model_en_pt results: - task: name: Sequence-to-sequence Language Modeling type: text2text-generation dataset: name: opus_books type: opus_books config: en-pt split: train args: en-pt metrics: - name: Bleu type: bleu value: 1.0547 ---  # model_en_pt This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus_books dataset. It achieves the following results on the evaluation set: - Loss: 3.1561 - Bleu: 1.0547 - Gen Len: 17.8369 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:| | No log | 1.0 | 79 | 3.4923 | 1.2907 | 17.2624 | | No log | 2.0 | 158 | 3.3099 | 0.8388 | 17.2482 | | No log | 3.0 | 237 | 3.2192 | 0.8526 | 17.7021 | | No log | 4.0 | 316 | 3.1709 | 0.9618 | 17.8298 | | No log | 5.0 | 395 | 3.1561 | 1.0547 | 17.8369 | ### Framework versions - Transformers 4.34.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0

ipipan/nlpre_trankit_ud_xlm-roberta-large_pdb

ipipan

2023-10-03T21:49:52Z

0

null

[ "region:us" ]

null

2023-09-29T08:54:04Z

# Model description - Morphosyntactic analyzer: Trankit - Tagset: UD - Embedding vectors: XLM-RoBERTa-Large - Dataset: PDB (http://git.nlp.ipipan.waw.pl/alina/PDBUD/tree/master/PDB-UD/PDB-UD) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_trankit_ud_xlm-roberta-large_pdb ``` ## Load model ``` import trankit model_path = './nlpre_trankit_ud_xlm-roberta-large_pdb' trankit.verify_customized_pipeline( category='customized-mwt', # pipeline category save_dir=model_path, # directory used for saving models in previous steps embedding_name='xlm-roberta-large' # embedding version that we use for training our customized pipeline, by default, it is `xlm-roberta-base` ) model = trankit.Pipeline(lang='customized-mwt', cache_dir=model_path, embedding='xlm-roberta-large') ```

ipipan/nlpre_trankit_ud_xlm-roberta-large_nkjp-by-type

ipipan

2023-10-03T21:48:38Z

0

null

[ "region:us" ]

null

2023-09-28T15:24:37Z

# Model description - Morphosyntactic analyzer: Trankit - Tagset: UD - Embedding vectors: XLM-RoBERTa-Large - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_trankit_ud_xlm-roberta-large_nkjp-by-type ``` ## Load model ``` import trankit model_path = './nlpre_trankit_ud_xlm-roberta-large_nkjp-by-type' trankit.verify_customized_pipeline( category='customized-mwt', # pipeline category save_dir=model_path, # directory used for saving models in previous steps embedding_name='xlm-roberta-large' # embedding version that we use for training our customized pipeline, by default, it is `xlm-roberta-base` ) model = trankit.Pipeline(lang='customized-mwt', cache_dir=model_path, embedding='xlm-roberta-large') ```

Safeer143/bert-finetuned-squad

Safeer143

2023-10-03T21:36:31Z

122

0

transformers

[ "transformers", "pytorch", "bert", "question-answering", "generated_from_trainer", "dataset:squad", "base_model:google-bert/bert-base-cased", "base_model:finetune:google-bert/bert-base-cased", "license:apache-2.0", "endpoints_compatible", "region:us" ]

question-answering

2023-10-01T23:27:03Z

--- license: apache-2.0 base_model: bert-base-cased tags: - generated_from_trainer datasets: - squad model-index: - name: bert-finetuned-squad results: [] ---  # bert-finetuned-squad This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the squad dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### Framework versions - Transformers 4.33.0 - Pytorch 2.0.0 - Datasets 2.1.0 - Tokenizers 0.13.3

raulkw/kw-prop-classifier

raulkw

2023-10-03T21:35:50Z

193

0

transformers

[ "transformers", "pytorch", "tensorboard", "vit", "image-classification", "huggingpics", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T21:35:42Z

--- tags: - image-classification - pytorch - huggingpics metrics: - accuracy model-index: - name: kw-prop-classifier results: - task: name: Image Classification type: image-classification metrics: - name: Accuracy type: accuracy value: 0.6266666650772095 --- # kw-prop-classifier Autogenerated by HuggingPics🤗🖼️ Create your own image classifier for **anything** by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb). Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics). ## Example Images #### Bathroom ![Bathroom](images/Bathroom.jpg) #### Bedroom ![Bedroom](images/Bedroom.jpg) #### Dining Room ![Dining Room](images/Dining_Room.jpg) #### House Amenities ![House Amenities](images/House_Amenities.jpg) #### House Facade ![House Facade](images/House_Facade.jpg) #### House Hallway ![House Hallway](images/House_Hallway.jpg) #### House Interior ![House Interior](images/House_Interior.jpg) #### House Lobby ![House Lobby](images/House_Lobby.jpg) #### Kitchen ![Kitchen](images/Kitchen.jpg) #### Living Room ![Living Room](images/Living_Room.jpg)

Chunwei94/souffle-ae

Chunwei94

2023-10-03T20:57:19Z

0

null

[ "onnx", "region:us" ]

null

2023-10-02T17:37:00Z

# For models with python bindings, please first run `pip install .` in the corresponding directory. docker run -it --name=sirius_test --gpus all --privileged sunqianqi/sirius:mlsys_ae /bin/bash

EladAssia/poca-SoccerTwos

EladAssia

2023-10-03T20:32:53Z

37

0

ml-agents

[ "ml-agents", "tensorboard", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]

reinforcement-learning

2023-10-03T20:32:17Z

--- library_name: ml-agents tags: - SoccerTwos - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SoccerTwos --- # **poca** Agent playing **SoccerTwos** This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: EladAssia/poca-SoccerTwos 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

ArtCad98/nlp_covid_tweets

ArtCad98

2023-10-03T20:32:20Z

14

0

transformers

[ "transformers", "pytorch", "bert", "fill-mask", "generated_from_trainer", "base_model:finiteautomata/beto-emotion-analysis", "base_model:finetune:finiteautomata/beto-emotion-analysis", "autotrain_compatible", "endpoints_compatible", "region:us" ]

fill-mask

2023-09-12T14:42:25Z

--- base_model: finiteautomata/beto-emotion-analysis tags: - generated_from_trainer model-index: - name: nlp_covid_tweets results: [] ---  # nlp_covid_tweets This model is a fine-tuned version of [finiteautomata/beto-emotion-analysis](https://huggingface.co/finiteautomata/beto-emotion-analysis) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.1415 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 1.406 | 1.0 | 6705 | 1.3510 | | 1.2393 | 2.0 | 13410 | 1.2051 | | 1.1622 | 3.0 | 20115 | 1.1410 | ### Framework versions - Transformers 4.34.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0

Terps/whisper-small-minds14-enUS

Terps

2023-10-03T20:05:58Z

77

0

transformers

[ "transformers", "pytorch", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dataset:PolyAI/minds14", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

automatic-speech-recognition

2023-10-03T19:07:18Z

--- license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer datasets: - PolyAI/minds14 metrics: - wer model-index: - name: whisper-small-minds14-enUS results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: PolyAI/minds14 type: PolyAI/minds14 config: en-US split: train args: en-US metrics: - name: Wer type: wer value: 28.158205430932703 ---  # whisper-small-minds14-enUS This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set: - Loss: 0.5829 - Wer Ortho: 27.8223 - Wer: 28.1582 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant_with_warmup - lr_scheduler_warmup_steps: 50 - training_steps: 500 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:| | 0.0003 | 17.86 | 500 | 0.5829 | 27.8223 | 28.1582 | ### Framework versions - Transformers 4.34.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.0

bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.9

bdpc

2023-10-03T19:57:33Z

195

0

transformers

[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T19:42:19Z

--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.9 results: [] ---  # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.9 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.8672 - Accuracy: 0.71 - Brier Loss: 0.4047 - Nll: 2.1924 - F1 Micro: 0.7100 - F1 Macro: 0.6463 - Ece: 0.2420 - Aurc: 0.1050 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 13 | 2.1239 | 0.16 | 0.8967 | 8.4233 | 0.16 | 0.1062 | 0.2101 | 0.8304 | | No log | 2.0 | 26 | 2.1201 | 0.14 | 0.8961 | 8.2220 | 0.14 | 0.0876 | 0.1970 | 0.8491 | | No log | 3.0 | 39 | 2.0724 | 0.215 | 0.8865 | 6.2039 | 0.2150 | 0.1169 | 0.2432 | 0.7837 | | No log | 4.0 | 52 | 2.0291 | 0.185 | 0.8773 | 5.6169 | 0.185 | 0.0792 | 0.2329 | 0.7651 | | No log | 5.0 | 65 | 1.9592 | 0.215 | 0.8614 | 6.0237 | 0.2150 | 0.0835 | 0.2493 | 0.7373 | | No log | 6.0 | 78 | 1.9039 | 0.205 | 0.8483 | 5.9575 | 0.205 | 0.0619 | 0.2493 | 0.7526 | | No log | 7.0 | 91 | 1.8651 | 0.26 | 0.8381 | 5.6215 | 0.26 | 0.1490 | 0.2663 | 0.6747 | | No log | 8.0 | 104 | 1.8342 | 0.225 | 0.8311 | 5.7631 | 0.225 | 0.1071 | 0.2425 | 0.6919 | | No log | 9.0 | 117 | 1.8057 | 0.31 | 0.8218 | 5.2969 | 0.31 | 0.2118 | 0.2795 | 0.6489 | | No log | 10.0 | 130 | 1.5737 | 0.46 | 0.7277 | 5.1748 | 0.46 | 0.2853 | 0.3279 | 0.2977 | | No log | 11.0 | 143 | 1.5629 | 0.415 | 0.7331 | 4.8259 | 0.415 | 0.2846 | 0.2924 | 0.3880 | | No log | 12.0 | 156 | 1.5283 | 0.45 | 0.7135 | 4.0012 | 0.45 | 0.3122 | 0.3298 | 0.3197 | | No log | 13.0 | 169 | 1.4200 | 0.51 | 0.6674 | 3.9849 | 0.51 | 0.3400 | 0.3259 | 0.2549 | | No log | 14.0 | 182 | 1.4334 | 0.535 | 0.6710 | 3.7006 | 0.535 | 0.3840 | 0.3291 | 0.2584 | | No log | 15.0 | 195 | 1.4306 | 0.45 | 0.6854 | 3.8260 | 0.45 | 0.3120 | 0.3055 | 0.4297 | | No log | 16.0 | 208 | 1.3175 | 0.585 | 0.6174 | 3.3484 | 0.585 | 0.4401 | 0.3406 | 0.1916 | | No log | 17.0 | 221 | 1.2680 | 0.57 | 0.5998 | 3.1408 | 0.57 | 0.4356 | 0.2903 | 0.2136 | | No log | 18.0 | 234 | 1.2605 | 0.58 | 0.6020 | 3.2085 | 0.58 | 0.4711 | 0.2915 | 0.2355 | | No log | 19.0 | 247 | 1.2292 | 0.61 | 0.5791 | 3.0633 | 0.61 | 0.5021 | 0.2929 | 0.2082 | | No log | 20.0 | 260 | 1.3872 | 0.54 | 0.6604 | 3.2778 | 0.54 | 0.4604 | 0.3284 | 0.3506 | | No log | 21.0 | 273 | 1.1646 | 0.625 | 0.5520 | 2.8539 | 0.625 | 0.5193 | 0.2828 | 0.1885 | | No log | 22.0 | 286 | 1.1565 | 0.655 | 0.5438 | 2.6915 | 0.655 | 0.5437 | 0.3430 | 0.1549 | | No log | 23.0 | 299 | 1.1041 | 0.625 | 0.5298 | 2.9930 | 0.625 | 0.5241 | 0.2423 | 0.1906 | | No log | 24.0 | 312 | 1.0448 | 0.685 | 0.4895 | 2.8196 | 0.685 | 0.5846 | 0.2701 | 0.1411 | | No log | 25.0 | 325 | 1.0623 | 0.695 | 0.4904 | 2.6903 | 0.695 | 0.6086 | 0.2762 | 0.1435 | | No log | 26.0 | 338 | 0.9872 | 0.695 | 0.4607 | 2.6336 | 0.695 | 0.5953 | 0.2728 | 0.1180 | | No log | 27.0 | 351 | 0.9789 | 0.705 | 0.4580 | 2.6326 | 0.705 | 0.6127 | 0.2579 | 0.1171 | | No log | 28.0 | 364 | 1.0033 | 0.685 | 0.4707 | 2.5747 | 0.685 | 0.5906 | 0.2747 | 0.1291 | | No log | 29.0 | 377 | 1.0152 | 0.7 | 0.4789 | 2.4333 | 0.7 | 0.6260 | 0.2951 | 0.1739 | | No log | 30.0 | 390 | 1.0107 | 0.715 | 0.4684 | 2.5194 | 0.715 | 0.6401 | 0.3197 | 0.1389 | | No log | 31.0 | 403 | 0.9511 | 0.69 | 0.4445 | 2.5648 | 0.69 | 0.6131 | 0.2648 | 0.1298 | | No log | 32.0 | 416 | 0.9586 | 0.735 | 0.4448 | 2.3342 | 0.735 | 0.6578 | 0.2941 | 0.1275 | | No log | 33.0 | 429 | 1.0010 | 0.73 | 0.4625 | 2.4748 | 0.7300 | 0.6613 | 0.3307 | 0.1202 | | No log | 34.0 | 442 | 0.9481 | 0.71 | 0.4361 | 2.4986 | 0.7100 | 0.6456 | 0.2856 | 0.1228 | | No log | 35.0 | 455 | 0.9190 | 0.69 | 0.4323 | 2.6586 | 0.69 | 0.6265 | 0.2538 | 0.1250 | | No log | 36.0 | 468 | 0.9226 | 0.715 | 0.4350 | 2.2652 | 0.715 | 0.6507 | 0.2868 | 0.1328 | | No log | 37.0 | 481 | 0.9017 | 0.725 | 0.4182 | 2.5141 | 0.7250 | 0.6590 | 0.2547 | 0.1013 | | No log | 38.0 | 494 | 0.9092 | 0.72 | 0.4218 | 2.5171 | 0.72 | 0.6495 | 0.2677 | 0.1055 | | 1.0958 | 39.0 | 507 | 0.9093 | 0.71 | 0.4221 | 2.6479 | 0.7100 | 0.6456 | 0.2567 | 0.1185 | | 1.0958 | 40.0 | 520 | 0.8926 | 0.71 | 0.4204 | 2.3785 | 0.7100 | 0.6522 | 0.2396 | 0.1153 | | 1.0958 | 41.0 | 533 | 0.8928 | 0.715 | 0.4157 | 2.5719 | 0.715 | 0.6487 | 0.2708 | 0.1067 | | 1.0958 | 42.0 | 546 | 0.8967 | 0.715 | 0.4247 | 2.6422 | 0.715 | 0.6495 | 0.2525 | 0.1174 | | 1.0958 | 43.0 | 559 | 0.8773 | 0.695 | 0.4116 | 2.5548 | 0.695 | 0.6400 | 0.2491 | 0.1142 | | 1.0958 | 44.0 | 572 | 0.8660 | 0.71 | 0.4036 | 2.2950 | 0.7100 | 0.6535 | 0.2401 | 0.1009 | | 1.0958 | 45.0 | 585 | 0.8718 | 0.72 | 0.4057 | 2.4922 | 0.72 | 0.6551 | 0.2624 | 0.0998 | | 1.0958 | 46.0 | 598 | 0.8737 | 0.7 | 0.4070 | 2.4455 | 0.7 | 0.6416 | 0.2360 | 0.1052 | | 1.0958 | 47.0 | 611 | 0.8707 | 0.715 | 0.4094 | 2.3519 | 0.715 | 0.6494 | 0.2514 | 0.1086 | | 1.0958 | 48.0 | 624 | 0.8640 | 0.705 | 0.4039 | 2.3765 | 0.705 | 0.6430 | 0.2538 | 0.1041 | | 1.0958 | 49.0 | 637 | 0.8702 | 0.7 | 0.4066 | 2.5524 | 0.7 | 0.6423 | 0.2160 | 0.1080 | | 1.0958 | 50.0 | 650 | 0.8672 | 0.71 | 0.4047 | 2.1924 | 0.7100 | 0.6463 | 0.2420 | 0.1050 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3

AIHUBFRANCE/personnalites-mediatiques

AIHUBFRANCE

2023-10-03T19:51:11Z

0

1

null

[ "fr", "license:cc-by-sa-4.0", "region:us" ]

null

2023-08-19T11:51:55Z

--- license: cc-by-sa-4.0 language: - fr --- # Fichiers .zip de Personnalites Médiatiques ## Disponible sur weights.gg ## Ou dans le séction "Files and Versions"

Quacktab/Reinforce-Pixelcopter

Quacktab

2023-10-03T19:47:35Z

0

null

[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

reinforcement-learning

2023-10-03T09:13:46Z

--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Pixelcopter results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 27.60 +/- 10.68 name: mean_reward verified: false --- # **Reinforce** Agent playing **Pixelcopter-PLE-v0** This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.7

bdpc

2023-10-03T19:41:47Z

195

0

transformers

[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T19:23:34Z

--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.7 results: [] ---  # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.7 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.8012 - Accuracy: 0.7 - Brier Loss: 0.4467 - Nll: 2.5682 - F1 Micro: 0.7 - F1 Macro: 0.6313 - Ece: 0.2684 - Aurc: 0.1170 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 13 | 1.8024 | 0.16 | 0.8966 | 8.5001 | 0.16 | 0.1073 | 0.2079 | 0.8334 | | No log | 2.0 | 26 | 1.7941 | 0.145 | 0.8957 | 8.3207 | 0.145 | 0.0843 | 0.2022 | 0.8435 | | No log | 3.0 | 39 | 1.7486 | 0.2 | 0.8868 | 6.2015 | 0.2000 | 0.1007 | 0.2209 | 0.7900 | | No log | 4.0 | 52 | 1.6854 | 0.205 | 0.8738 | 6.0142 | 0.205 | 0.0707 | 0.2453 | 0.7584 | | No log | 5.0 | 65 | 1.6162 | 0.2 | 0.8594 | 6.2364 | 0.2000 | 0.0552 | 0.2466 | 0.7717 | | No log | 6.0 | 78 | 1.5412 | 0.235 | 0.8416 | 6.0423 | 0.235 | 0.0902 | 0.2589 | 0.7006 | | No log | 7.0 | 91 | 1.5011 | 0.295 | 0.8304 | 6.1420 | 0.295 | 0.1272 | 0.2803 | 0.6124 | | No log | 8.0 | 104 | 1.4415 | 0.3 | 0.8114 | 6.0440 | 0.3 | 0.1296 | 0.2870 | 0.5641 | | No log | 9.0 | 117 | 1.3257 | 0.38 | 0.7625 | 5.6923 | 0.38 | 0.2198 | 0.3136 | 0.3675 | | No log | 10.0 | 130 | 1.3748 | 0.33 | 0.7905 | 5.5276 | 0.33 | 0.1870 | 0.2947 | 0.5985 | | No log | 11.0 | 143 | 1.3294 | 0.39 | 0.7683 | 4.9632 | 0.39 | 0.2573 | 0.2940 | 0.4639 | | No log | 12.0 | 156 | 1.2444 | 0.385 | 0.7297 | 4.8431 | 0.3850 | 0.2330 | 0.2849 | 0.4173 | | No log | 13.0 | 169 | 1.2212 | 0.45 | 0.7153 | 4.5819 | 0.45 | 0.3051 | 0.3143 | 0.3379 | | No log | 14.0 | 182 | 1.1835 | 0.495 | 0.6888 | 3.6108 | 0.495 | 0.3412 | 0.3316 | 0.2873 | | No log | 15.0 | 195 | 1.1203 | 0.47 | 0.6559 | 3.6500 | 0.47 | 0.3348 | 0.2935 | 0.3061 | | No log | 16.0 | 208 | 1.1520 | 0.495 | 0.6707 | 3.8106 | 0.495 | 0.3632 | 0.2938 | 0.3604 | | No log | 17.0 | 221 | 1.0261 | 0.565 | 0.6021 | 3.3382 | 0.565 | 0.4214 | 0.2840 | 0.2047 | | No log | 18.0 | 234 | 1.0080 | 0.61 | 0.5914 | 3.2936 | 0.61 | 0.4748 | 0.3240 | 0.1806 | | No log | 19.0 | 247 | 1.0696 | 0.58 | 0.6253 | 3.2354 | 0.58 | 0.4686 | 0.3152 | 0.2626 | | No log | 20.0 | 260 | 0.9733 | 0.615 | 0.5722 | 3.1019 | 0.615 | 0.4968 | 0.3259 | 0.2066 | | No log | 21.0 | 273 | 0.9266 | 0.625 | 0.5423 | 3.0239 | 0.625 | 0.5202 | 0.2834 | 0.1782 | | No log | 22.0 | 286 | 0.9364 | 0.66 | 0.5461 | 2.9031 | 0.66 | 0.5461 | 0.3128 | 0.1601 | | No log | 23.0 | 299 | 0.9181 | 0.675 | 0.5307 | 2.8416 | 0.675 | 0.5584 | 0.3106 | 0.1462 | | No log | 24.0 | 312 | 0.9739 | 0.665 | 0.5539 | 2.8798 | 0.665 | 0.5634 | 0.3325 | 0.1610 | | No log | 25.0 | 325 | 0.8851 | 0.69 | 0.5099 | 2.7336 | 0.69 | 0.6013 | 0.3064 | 0.1437 | | No log | 26.0 | 338 | 0.8755 | 0.71 | 0.4979 | 2.7400 | 0.7100 | 0.6032 | 0.3162 | 0.1211 | | No log | 27.0 | 351 | 0.8653 | 0.675 | 0.4964 | 2.8339 | 0.675 | 0.5705 | 0.2977 | 0.1386 | | No log | 28.0 | 364 | 0.8838 | 0.675 | 0.5055 | 2.7456 | 0.675 | 0.5816 | 0.2969 | 0.1524 | | No log | 29.0 | 377 | 0.8805 | 0.68 | 0.5025 | 2.6942 | 0.68 | 0.5855 | 0.3099 | 0.1380 | | No log | 30.0 | 390 | 0.8585 | 0.665 | 0.4891 | 2.7511 | 0.665 | 0.5737 | 0.2627 | 0.1370 | | No log | 31.0 | 403 | 0.8410 | 0.675 | 0.4736 | 2.6431 | 0.675 | 0.5985 | 0.2670 | 0.1335 | | No log | 32.0 | 416 | 0.8378 | 0.71 | 0.4724 | 2.7320 | 0.7100 | 0.6236 | 0.2885 | 0.1153 | | No log | 33.0 | 429 | 0.8421 | 0.705 | 0.4718 | 2.6331 | 0.705 | 0.6326 | 0.2644 | 0.1147 | | No log | 34.0 | 442 | 0.8350 | 0.685 | 0.4697 | 2.8035 | 0.685 | 0.6062 | 0.2831 | 0.1291 | | No log | 35.0 | 455 | 0.8377 | 0.7 | 0.4708 | 2.4611 | 0.7 | 0.6376 | 0.3173 | 0.1195 | | No log | 36.0 | 468 | 0.8126 | 0.69 | 0.4562 | 2.3909 | 0.69 | 0.6154 | 0.2433 | 0.1177 | | No log | 37.0 | 481 | 0.8299 | 0.685 | 0.4673 | 2.5695 | 0.685 | 0.6080 | 0.2802 | 0.1261 | | No log | 38.0 | 494 | 0.8197 | 0.685 | 0.4597 | 2.6388 | 0.685 | 0.6187 | 0.2690 | 0.1229 | | 0.9314 | 39.0 | 507 | 0.8137 | 0.695 | 0.4547 | 2.7263 | 0.695 | 0.6332 | 0.2581 | 0.1207 | | 0.9314 | 40.0 | 520 | 0.8168 | 0.69 | 0.4583 | 2.6230 | 0.69 | 0.6267 | 0.2696 | 0.1161 | | 0.9314 | 41.0 | 533 | 0.8090 | 0.7 | 0.4529 | 2.6449 | 0.7 | 0.6236 | 0.2445 | 0.1187 | | 0.9314 | 42.0 | 546 | 0.8168 | 0.68 | 0.4586 | 2.5516 | 0.68 | 0.6162 | 0.2722 | 0.1275 | | 0.9314 | 43.0 | 559 | 0.8100 | 0.7 | 0.4523 | 2.5565 | 0.7 | 0.6347 | 0.2869 | 0.1192 | | 0.9314 | 44.0 | 572 | 0.8078 | 0.7 | 0.4514 | 2.5734 | 0.7 | 0.6344 | 0.2583 | 0.1172 | | 0.9314 | 45.0 | 585 | 0.8022 | 0.715 | 0.4472 | 2.4971 | 0.715 | 0.6534 | 0.2890 | 0.1165 | | 0.9314 | 46.0 | 598 | 0.8049 | 0.695 | 0.4484 | 2.4891 | 0.695 | 0.6423 | 0.2722 | 0.1189 | | 0.9314 | 47.0 | 611 | 0.8025 | 0.705 | 0.4481 | 2.4929 | 0.705 | 0.6393 | 0.2650 | 0.1124 | | 0.9314 | 48.0 | 624 | 0.7973 | 0.7 | 0.4439 | 2.5000 | 0.7 | 0.6292 | 0.2718 | 0.1142 | | 0.9314 | 49.0 | 637 | 0.8011 | 0.7 | 0.4464 | 2.5713 | 0.7 | 0.6303 | 0.2400 | 0.1183 | | 0.9314 | 50.0 | 650 | 0.8012 | 0.7 | 0.4467 | 2.5682 | 0.7 | 0.6313 | 0.2684 | 0.1170 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3

ipipan/nlpre_stanza_nkjp_fasttext_nkjp-by-type

ipipan

2023-10-03T19:35:11Z

0

null

[ "region:us" ]

null

2023-09-29T08:04:40Z

# Model description - Morphosyntactic analyzer: Stanza - Tagset: NKJP - Embedding vectors: Fasttext (wiki) - Dataset: NLPrePL-NKJP-fair-by-type (https://huggingface.co/datasets/ipipan/nlprepl) # How to use ## Clone ``` git clone [email protected]:ipipan/nlpre_stanza_nkjp_fasttext_nkjp-by-type ``` ## Load model ``` import stanza lang = 'pl' model_name = 'nlpre_stanza_nkjp_fasttext_nkjp-by-type' prefix = 'nkjpbytype_nkjp' config = \ { # Comma-separated list of processors to use 'processors': 'tokenize,mwt,pos,lemma', # Language code for the language to build the Pipeline in 'lang': lang, # Processor-specific arguments are set with keys "{processor_name}_{argument_name}" # You only need model paths if you have a specific model outside of stanza_resources 'tokenize_model_path': os.path.join(model_name, f'{lang}_{prefix}_tokenizer.pt'), 'mwt_model_path': os.path.join(model_name, f'{lang}_{prefix}_mwt_expander.pt'), 'pos_model_path': os.path.join(model_name, f'{lang}_{prefix}_tagger.pt'), 'pos_pretrain_path': os.path.join(model_name, f'{lang}_{prefix}.pretrain.pt'), 'lemma_model_path': os.path.join(model_name, f'{lang}_{prefix}_lemmatizer.pt'), # Use pretokenized text as input and disable tokenization 'tokenize_pretokenized': True } model = stanza.Pipeline(**config)

bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.5

bdpc

2023-10-03T19:23:04Z

196

0

transformers

[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T18:13:29Z

--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.5 results: [] ---  # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t2.5_a0.5 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6481 - Accuracy: 0.69 - Brier Loss: 0.4919 - Nll: 2.4969 - F1 Micro: 0.69 - F1 Macro: 0.6317 - Ece: 0.3029 - Aurc: 0.1260 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 13 | 1.4796 | 0.165 | 0.8965 | 8.4885 | 0.165 | 0.1123 | 0.2151 | 0.8341 | | No log | 2.0 | 26 | 1.4679 | 0.165 | 0.8954 | 8.3391 | 0.165 | 0.1066 | 0.2136 | 0.8332 | | No log | 3.0 | 39 | 1.4170 | 0.21 | 0.8858 | 6.1941 | 0.2100 | 0.0969 | 0.2433 | 0.7991 | | No log | 4.0 | 52 | 1.3472 | 0.21 | 0.8711 | 6.0602 | 0.2100 | 0.0728 | 0.2320 | 0.7271 | | No log | 5.0 | 65 | 1.2776 | 0.19 | 0.8572 | 6.1293 | 0.19 | 0.0537 | 0.2422 | 0.7473 | | No log | 6.0 | 78 | 1.1840 | 0.245 | 0.8353 | 6.2405 | 0.245 | 0.1060 | 0.2810 | 0.6690 | | No log | 7.0 | 91 | 1.0740 | 0.365 | 0.7936 | 6.3617 | 0.3650 | 0.1739 | 0.3136 | 0.3646 | | No log | 8.0 | 104 | 1.1102 | 0.345 | 0.8081 | 5.8896 | 0.345 | 0.1812 | 0.3046 | 0.4292 | | No log | 9.0 | 117 | 1.0735 | 0.34 | 0.7963 | 5.9970 | 0.34 | 0.1842 | 0.3028 | 0.4286 | | No log | 10.0 | 130 | 1.1145 | 0.265 | 0.8110 | 5.9054 | 0.265 | 0.1300 | 0.2511 | 0.6350 | | No log | 11.0 | 143 | 0.9981 | 0.325 | 0.7659 | 5.3834 | 0.325 | 0.1655 | 0.2790 | 0.4860 | | No log | 12.0 | 156 | 1.0500 | 0.285 | 0.7898 | 4.9696 | 0.285 | 0.1594 | 0.2604 | 0.6636 | | No log | 13.0 | 169 | 0.8764 | 0.445 | 0.6976 | 4.6456 | 0.445 | 0.2647 | 0.2779 | 0.3020 | | No log | 14.0 | 182 | 0.9147 | 0.48 | 0.7108 | 4.4793 | 0.48 | 0.2942 | 0.3262 | 0.2862 | | No log | 15.0 | 195 | 0.9776 | 0.38 | 0.7434 | 4.4065 | 0.38 | 0.2269 | 0.2938 | 0.5297 | | No log | 16.0 | 208 | 0.8066 | 0.47 | 0.6494 | 3.9671 | 0.47 | 0.2966 | 0.2791 | 0.2907 | | No log | 17.0 | 221 | 0.7766 | 0.535 | 0.6305 | 3.5250 | 0.535 | 0.3866 | 0.3003 | 0.2424 | | No log | 18.0 | 234 | 0.8186 | 0.535 | 0.6458 | 3.3670 | 0.535 | 0.3792 | 0.3005 | 0.2311 | | No log | 19.0 | 247 | 0.8156 | 0.52 | 0.6430 | 3.1633 | 0.52 | 0.3675 | 0.3072 | 0.2667 | | No log | 20.0 | 260 | 0.8386 | 0.55 | 0.6462 | 3.2549 | 0.55 | 0.4251 | 0.3103 | 0.2703 | | No log | 21.0 | 273 | 0.7996 | 0.515 | 0.6342 | 3.1396 | 0.515 | 0.3969 | 0.3177 | 0.2867 | | No log | 22.0 | 286 | 0.8605 | 0.6 | 0.6472 | 3.2563 | 0.6 | 0.4717 | 0.3810 | 0.2113 | | No log | 23.0 | 299 | 0.7138 | 0.595 | 0.5713 | 3.1171 | 0.595 | 0.4657 | 0.2773 | 0.2034 | | No log | 24.0 | 312 | 0.7212 | 0.665 | 0.5740 | 2.9688 | 0.665 | 0.5474 | 0.3366 | 0.1754 | | No log | 25.0 | 325 | 0.7463 | 0.63 | 0.5843 | 2.8998 | 0.63 | 0.5502 | 0.3432 | 0.2072 | | No log | 26.0 | 338 | 0.7231 | 0.67 | 0.5626 | 3.1334 | 0.67 | 0.5564 | 0.3160 | 0.1521 | | No log | 27.0 | 351 | 0.6913 | 0.68 | 0.5427 | 2.8906 | 0.68 | 0.5702 | 0.3354 | 0.1406 | | No log | 28.0 | 364 | 0.6825 | 0.66 | 0.5342 | 2.8619 | 0.66 | 0.5615 | 0.2902 | 0.1625 | | No log | 29.0 | 377 | 0.7015 | 0.665 | 0.5549 | 2.7315 | 0.665 | 0.5741 | 0.3305 | 0.1769 | | No log | 30.0 | 390 | 0.6939 | 0.67 | 0.5406 | 2.7114 | 0.67 | 0.5720 | 0.3353 | 0.1420 | | No log | 31.0 | 403 | 0.6836 | 0.69 | 0.5265 | 2.7567 | 0.69 | 0.5982 | 0.3216 | 0.1455 | | No log | 32.0 | 416 | 0.6728 | 0.69 | 0.5211 | 2.6858 | 0.69 | 0.6056 | 0.3124 | 0.1453 | | No log | 33.0 | 429 | 0.6926 | 0.675 | 0.5403 | 2.5815 | 0.675 | 0.6095 | 0.3258 | 0.1683 | | No log | 34.0 | 442 | 0.6673 | 0.66 | 0.5090 | 2.5591 | 0.66 | 0.5722 | 0.2950 | 0.1385 | | No log | 35.0 | 455 | 0.6811 | 0.675 | 0.5207 | 2.5813 | 0.675 | 0.5841 | 0.3324 | 0.1273 | | No log | 36.0 | 468 | 0.6648 | 0.69 | 0.5119 | 2.5745 | 0.69 | 0.6225 | 0.3433 | 0.1320 | | No log | 37.0 | 481 | 0.6623 | 0.67 | 0.5092 | 2.6134 | 0.67 | 0.6129 | 0.3204 | 0.1471 | | No log | 38.0 | 494 | 0.6635 | 0.69 | 0.5088 | 2.3862 | 0.69 | 0.6192 | 0.3201 | 0.1311 | | 0.7628 | 39.0 | 507 | 0.6554 | 0.685 | 0.5008 | 2.5849 | 0.685 | 0.6210 | 0.3179 | 0.1377 | | 0.7628 | 40.0 | 520 | 0.6567 | 0.685 | 0.5022 | 2.6498 | 0.685 | 0.6310 | 0.3127 | 0.1414 | | 0.7628 | 41.0 | 533 | 0.6558 | 0.695 | 0.4996 | 2.5917 | 0.695 | 0.6347 | 0.3115 | 0.1321 | | 0.7628 | 42.0 | 546 | 0.6578 | 0.695 | 0.5021 | 2.4864 | 0.695 | 0.6259 | 0.3098 | 0.1306 | | 0.7628 | 43.0 | 559 | 0.6544 | 0.685 | 0.4969 | 2.5757 | 0.685 | 0.6175 | 0.2955 | 0.1342 | | 0.7628 | 44.0 | 572 | 0.6507 | 0.685 | 0.4944 | 2.5057 | 0.685 | 0.6257 | 0.3144 | 0.1304 | | 0.7628 | 45.0 | 585 | 0.6501 | 0.675 | 0.4937 | 2.4903 | 0.675 | 0.6208 | 0.3091 | 0.1301 | | 0.7628 | 46.0 | 598 | 0.6518 | 0.685 | 0.4949 | 2.4732 | 0.685 | 0.6254 | 0.3164 | 0.1235 | | 0.7628 | 47.0 | 611 | 0.6499 | 0.685 | 0.4936 | 2.4924 | 0.685 | 0.6273 | 0.3124 | 0.1323 | | 0.7628 | 48.0 | 624 | 0.6490 | 0.7 | 0.4925 | 2.4999 | 0.7 | 0.6353 | 0.3147 | 0.1243 | | 0.7628 | 49.0 | 637 | 0.6510 | 0.685 | 0.4933 | 2.5758 | 0.685 | 0.6242 | 0.3206 | 0.1281 | | 0.7628 | 50.0 | 650 | 0.6481 | 0.69 | 0.4919 | 2.4969 | 0.69 | 0.6317 | 0.3029 | 0.1260 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3

bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.9

bdpc

2023-10-03T19:06:28Z

197

0

transformers

[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T18:52:55Z

--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.9 results: [] ---  # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.9 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.8831 - Accuracy: 0.695 - Brier Loss: 0.4126 - Nll: 2.4628 - F1 Micro: 0.695 - F1 Macro: 0.6387 - Ece: 0.2426 - Aurc: 0.1068 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 13 | 2.1233 | 0.16 | 0.8967 | 8.5697 | 0.16 | 0.1066 | 0.2078 | 0.8316 | | No log | 2.0 | 26 | 2.1188 | 0.14 | 0.8961 | 8.2960 | 0.14 | 0.0886 | 0.1947 | 0.8419 | | No log | 3.0 | 39 | 2.0764 | 0.195 | 0.8873 | 6.4713 | 0.195 | 0.1159 | 0.2335 | 0.7665 | | No log | 4.0 | 52 | 2.0365 | 0.21 | 0.8787 | 5.7752 | 0.2100 | 0.0930 | 0.2376 | 0.7548 | | No log | 5.0 | 65 | 1.9888 | 0.2 | 0.8682 | 5.8737 | 0.2000 | 0.0775 | 0.2417 | 0.7314 | | No log | 6.0 | 78 | 1.8998 | 0.215 | 0.8465 | 5.8553 | 0.2150 | 0.0970 | 0.2586 | 0.7063 | | No log | 7.0 | 91 | 1.8351 | 0.33 | 0.8289 | 5.7781 | 0.33 | 0.1904 | 0.3089 | 0.6103 | | No log | 8.0 | 104 | 1.7342 | 0.4 | 0.7968 | 5.5366 | 0.4000 | 0.2476 | 0.3457 | 0.4276 | | No log | 9.0 | 117 | 1.6787 | 0.36 | 0.7757 | 5.7414 | 0.36 | 0.2148 | 0.3062 | 0.4324 | | No log | 10.0 | 130 | 1.6942 | 0.4 | 0.7870 | 5.2615 | 0.4000 | 0.2831 | 0.3168 | 0.5227 | | No log | 11.0 | 143 | 1.5992 | 0.4 | 0.7489 | 4.7833 | 0.4000 | 0.2649 | 0.3053 | 0.4679 | | No log | 12.0 | 156 | 1.6071 | 0.425 | 0.7532 | 4.2803 | 0.425 | 0.2906 | 0.3196 | 0.4646 | | No log | 13.0 | 169 | 1.4727 | 0.48 | 0.6925 | 4.1911 | 0.48 | 0.3239 | 0.2957 | 0.3081 | | No log | 14.0 | 182 | 1.4275 | 0.515 | 0.6705 | 3.7980 | 0.515 | 0.3569 | 0.3211 | 0.2626 | | No log | 15.0 | 195 | 1.3282 | 0.56 | 0.6200 | 3.6359 | 0.56 | 0.4163 | 0.2990 | 0.2213 | | No log | 16.0 | 208 | 1.3280 | 0.565 | 0.6263 | 3.4960 | 0.565 | 0.4177 | 0.3217 | 0.2346 | | No log | 17.0 | 221 | 1.3220 | 0.595 | 0.6196 | 3.2202 | 0.595 | 0.4639 | 0.3322 | 0.1992 | | No log | 18.0 | 234 | 1.2359 | 0.595 | 0.5840 | 3.3332 | 0.595 | 0.4780 | 0.3042 | 0.2011 | | No log | 19.0 | 247 | 1.1690 | 0.625 | 0.5531 | 3.2423 | 0.625 | 0.5233 | 0.2940 | 0.1807 | | No log | 20.0 | 260 | 1.1644 | 0.64 | 0.5532 | 3.0542 | 0.64 | 0.5429 | 0.3019 | 0.1821 | | No log | 21.0 | 273 | 1.1611 | 0.62 | 0.5516 | 2.9412 | 0.62 | 0.5193 | 0.2865 | 0.2160 | | No log | 22.0 | 286 | 1.3427 | 0.585 | 0.6361 | 3.0936 | 0.585 | 0.5089 | 0.3442 | 0.2922 | | No log | 23.0 | 299 | 1.1238 | 0.62 | 0.5440 | 2.7924 | 0.62 | 0.5458 | 0.2654 | 0.2088 | | No log | 24.0 | 312 | 1.2008 | 0.685 | 0.5615 | 2.5918 | 0.685 | 0.5890 | 0.3907 | 0.1516 | | No log | 25.0 | 325 | 1.0764 | 0.695 | 0.5000 | 2.6354 | 0.695 | 0.6107 | 0.3126 | 0.1397 | | No log | 26.0 | 338 | 1.0268 | 0.675 | 0.4822 | 2.4798 | 0.675 | 0.5992 | 0.2775 | 0.1229 | | No log | 27.0 | 351 | 1.0340 | 0.67 | 0.4893 | 2.4316 | 0.67 | 0.5997 | 0.2763 | 0.1638 | | No log | 28.0 | 364 | 1.0154 | 0.665 | 0.4769 | 2.6487 | 0.665 | 0.6034 | 0.2590 | 0.1487 | | No log | 29.0 | 377 | 1.0013 | 0.64 | 0.4814 | 2.5899 | 0.64 | 0.5771 | 0.2429 | 0.1593 | | No log | 30.0 | 390 | 1.0173 | 0.685 | 0.4714 | 2.6922 | 0.685 | 0.6178 | 0.2898 | 0.1423 | | No log | 31.0 | 403 | 0.9630 | 0.695 | 0.4509 | 2.6349 | 0.695 | 0.6206 | 0.2746 | 0.1248 | | No log | 32.0 | 416 | 0.9950 | 0.68 | 0.4648 | 2.4144 | 0.68 | 0.6362 | 0.3020 | 0.1725 | | No log | 33.0 | 429 | 0.9711 | 0.72 | 0.4502 | 2.6651 | 0.72 | 0.6571 | 0.2892 | 0.1268 | | No log | 34.0 | 442 | 0.9491 | 0.705 | 0.4425 | 2.7169 | 0.705 | 0.6425 | 0.2541 | 0.1145 | | No log | 35.0 | 455 | 0.9213 | 0.685 | 0.4309 | 2.5736 | 0.685 | 0.6174 | 0.2380 | 0.1161 | | No log | 36.0 | 468 | 0.9144 | 0.695 | 0.4297 | 2.4141 | 0.695 | 0.6308 | 0.2502 | 0.1154 | | No log | 37.0 | 481 | 0.9242 | 0.715 | 0.4264 | 2.7191 | 0.715 | 0.6429 | 0.2386 | 0.1030 | | No log | 38.0 | 494 | 0.9290 | 0.695 | 0.4346 | 2.6515 | 0.695 | 0.6367 | 0.2432 | 0.1189 | | 1.0953 | 39.0 | 507 | 0.9110 | 0.69 | 0.4262 | 2.6615 | 0.69 | 0.6328 | 0.2368 | 0.1112 | | 1.0953 | 40.0 | 520 | 0.9000 | 0.695 | 0.4186 | 2.4590 | 0.695 | 0.6417 | 0.2453 | 0.1070 | | 1.0953 | 41.0 | 533 | 0.8961 | 0.69 | 0.4189 | 2.4170 | 0.69 | 0.6368 | 0.2349 | 0.1090 | | 1.0953 | 42.0 | 546 | 0.9103 | 0.675 | 0.4286 | 2.6129 | 0.675 | 0.6193 | 0.2318 | 0.1190 | | 1.0953 | 43.0 | 559 | 0.8858 | 0.715 | 0.4131 | 2.5243 | 0.715 | 0.6517 | 0.2462 | 0.1053 | | 1.0953 | 44.0 | 572 | 0.8872 | 0.705 | 0.4135 | 2.3272 | 0.705 | 0.6542 | 0.2596 | 0.1051 | | 1.0953 | 45.0 | 585 | 0.8897 | 0.715 | 0.4136 | 2.3788 | 0.715 | 0.6532 | 0.2560 | 0.1035 | | 1.0953 | 46.0 | 598 | 0.8842 | 0.7 | 0.4117 | 2.5325 | 0.7 | 0.6446 | 0.2327 | 0.1075 | | 1.0953 | 47.0 | 611 | 0.8857 | 0.675 | 0.4141 | 2.5451 | 0.675 | 0.6203 | 0.2473 | 0.1125 | | 1.0953 | 48.0 | 624 | 0.8875 | 0.69 | 0.4164 | 2.4696 | 0.69 | 0.6352 | 0.2542 | 0.1109 | | 1.0953 | 49.0 | 637 | 0.8842 | 0.69 | 0.4153 | 2.5338 | 0.69 | 0.6358 | 0.2302 | 0.1112 | | 1.0953 | 50.0 | 650 | 0.8831 | 0.695 | 0.4126 | 2.4628 | 0.695 | 0.6387 | 0.2426 | 0.1068 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3

Soheil-FM/falcon-7b-chatbot

Soheil-FM

2023-10-03T19:01:09Z

0

peft

[ "peft", "region:us" ]

null

2023-10-03T19:01:03Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.5.0

bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.7

bdpc

2023-10-03T18:52:29Z

196

0

transformers

[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T18:38:52Z

--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.7 results: [] ---  # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.7 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.8009 - Accuracy: 0.695 - Brier Loss: 0.4518 - Nll: 2.3840 - F1 Micro: 0.695 - F1 Macro: 0.6406 - Ece: 0.2661 - Aurc: 0.1211 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 13 | 1.7971 | 0.17 | 0.8966 | 8.4593 | 0.17 | 0.1148 | 0.2202 | 0.8308 | | No log | 2.0 | 26 | 1.7887 | 0.13 | 0.8956 | 8.3211 | 0.13 | 0.0772 | 0.2024 | 0.8359 | | No log | 3.0 | 39 | 1.7450 | 0.225 | 0.8868 | 6.4554 | 0.225 | 0.1165 | 0.2502 | 0.7572 | | No log | 4.0 | 52 | 1.6811 | 0.24 | 0.8733 | 5.9510 | 0.24 | 0.0953 | 0.2651 | 0.6944 | | No log | 5.0 | 65 | 1.6411 | 0.19 | 0.8649 | 6.0993 | 0.19 | 0.0493 | 0.2422 | 0.7783 | | No log | 6.0 | 78 | 1.5475 | 0.195 | 0.8429 | 6.2065 | 0.195 | 0.0630 | 0.2472 | 0.7110 | | No log | 7.0 | 91 | 1.4688 | 0.3 | 0.8197 | 6.0345 | 0.3 | 0.1481 | 0.2936 | 0.5379 | | No log | 8.0 | 104 | 1.5036 | 0.285 | 0.8294 | 5.6660 | 0.285 | 0.1428 | 0.2869 | 0.6535 | | No log | 9.0 | 117 | 1.3901 | 0.34 | 0.7934 | 5.9107 | 0.34 | 0.1853 | 0.2894 | 0.5277 | | No log | 10.0 | 130 | 1.3484 | 0.37 | 0.7760 | 5.6441 | 0.37 | 0.2175 | 0.3177 | 0.5266 | | No log | 11.0 | 143 | 1.3375 | 0.34 | 0.7734 | 5.0872 | 0.34 | 0.2083 | 0.2902 | 0.5557 | | No log | 12.0 | 156 | 1.3639 | 0.305 | 0.7834 | 4.5070 | 0.305 | 0.1885 | 0.2674 | 0.6177 | | No log | 13.0 | 169 | 1.2321 | 0.415 | 0.7225 | 4.3464 | 0.415 | 0.2751 | 0.2943 | 0.3825 | | No log | 14.0 | 182 | 1.1453 | 0.44 | 0.6767 | 4.4158 | 0.44 | 0.2864 | 0.2617 | 0.3413 | | No log | 15.0 | 195 | 1.1830 | 0.43 | 0.6965 | 3.8251 | 0.4300 | 0.2972 | 0.2912 | 0.4239 | | No log | 16.0 | 208 | 1.0572 | 0.535 | 0.6230 | 3.5943 | 0.535 | 0.3758 | 0.2861 | 0.2291 | | No log | 17.0 | 221 | 1.0532 | 0.585 | 0.6151 | 3.3834 | 0.585 | 0.4331 | 0.3278 | 0.1879 | | No log | 18.0 | 234 | 1.0940 | 0.565 | 0.6374 | 3.2290 | 0.565 | 0.4431 | 0.3313 | 0.2415 | | No log | 19.0 | 247 | 0.9877 | 0.585 | 0.5886 | 3.1068 | 0.585 | 0.4564 | 0.2896 | 0.2110 | | No log | 20.0 | 260 | 1.0405 | 0.61 | 0.6056 | 3.1786 | 0.61 | 0.5038 | 0.3428 | 0.1962 | | No log | 21.0 | 273 | 0.9728 | 0.635 | 0.5634 | 2.9133 | 0.635 | 0.5293 | 0.3333 | 0.1664 | | No log | 22.0 | 286 | 0.9425 | 0.635 | 0.5527 | 2.8909 | 0.635 | 0.5237 | 0.3131 | 0.1796 | | No log | 23.0 | 299 | 0.9549 | 0.65 | 0.5605 | 2.8074 | 0.65 | 0.5539 | 0.3283 | 0.1914 | | No log | 24.0 | 312 | 1.0085 | 0.67 | 0.5733 | 2.8377 | 0.67 | 0.5543 | 0.3525 | 0.1571 | | No log | 25.0 | 325 | 0.9140 | 0.655 | 0.5257 | 2.5878 | 0.655 | 0.5603 | 0.3171 | 0.1495 | | No log | 26.0 | 338 | 0.8979 | 0.65 | 0.5249 | 2.7723 | 0.65 | 0.5563 | 0.2843 | 0.1646 | | No log | 27.0 | 351 | 0.8912 | 0.675 | 0.5082 | 2.6562 | 0.675 | 0.5837 | 0.2871 | 0.1380 | | No log | 28.0 | 364 | 0.8966 | 0.66 | 0.5242 | 2.3150 | 0.66 | 0.5890 | 0.3180 | 0.1777 | | No log | 29.0 | 377 | 0.8602 | 0.67 | 0.4959 | 2.5813 | 0.67 | 0.5866 | 0.3023 | 0.1319 | | No log | 30.0 | 390 | 0.8434 | 0.69 | 0.4779 | 2.5451 | 0.69 | 0.6130 | 0.3061 | 0.1188 | | No log | 31.0 | 403 | 0.8406 | 0.715 | 0.4782 | 2.3339 | 0.715 | 0.6438 | 0.3241 | 0.1092 | | No log | 32.0 | 416 | 0.8294 | 0.71 | 0.4726 | 2.5394 | 0.7100 | 0.6308 | 0.2922 | 0.1218 | | No log | 33.0 | 429 | 0.8329 | 0.68 | 0.4763 | 2.4520 | 0.68 | 0.6166 | 0.2592 | 0.1396 | | No log | 34.0 | 442 | 0.8937 | 0.69 | 0.5015 | 2.5649 | 0.69 | 0.6357 | 0.3293 | 0.1279 | | No log | 35.0 | 455 | 0.8358 | 0.665 | 0.4807 | 2.4437 | 0.665 | 0.6178 | 0.2380 | 0.1473 | | No log | 36.0 | 468 | 0.8283 | 0.685 | 0.4747 | 2.5408 | 0.685 | 0.6304 | 0.3126 | 0.1361 | | No log | 37.0 | 481 | 0.8235 | 0.685 | 0.4707 | 2.4620 | 0.685 | 0.6300 | 0.2757 | 0.1343 | | No log | 38.0 | 494 | 0.8289 | 0.68 | 0.4778 | 2.5443 | 0.68 | 0.6305 | 0.2935 | 0.1469 | | 0.9462 | 39.0 | 507 | 0.8373 | 0.69 | 0.4728 | 2.5775 | 0.69 | 0.6281 | 0.3028 | 0.1149 | | 0.9462 | 40.0 | 520 | 0.8062 | 0.715 | 0.4548 | 2.3673 | 0.715 | 0.6587 | 0.2776 | 0.1133 | | 0.9462 | 41.0 | 533 | 0.7990 | 0.705 | 0.4517 | 2.3284 | 0.705 | 0.6463 | 0.2716 | 0.1185 | | 0.9462 | 42.0 | 546 | 0.8210 | 0.7 | 0.4650 | 2.5646 | 0.7 | 0.6432 | 0.2690 | 0.1199 | | 0.9462 | 43.0 | 559 | 0.8102 | 0.695 | 0.4558 | 2.5651 | 0.695 | 0.6442 | 0.2656 | 0.1184 | | 0.9462 | 44.0 | 572 | 0.8061 | 0.69 | 0.4566 | 2.5154 | 0.69 | 0.6356 | 0.2816 | 0.1267 | | 0.9462 | 45.0 | 585 | 0.8018 | 0.7 | 0.4531 | 2.4982 | 0.7 | 0.6419 | 0.2696 | 0.1192 | | 0.9462 | 46.0 | 598 | 0.8040 | 0.7 | 0.4521 | 2.5309 | 0.7 | 0.6448 | 0.2797 | 0.1166 | | 0.9462 | 47.0 | 611 | 0.8062 | 0.68 | 0.4560 | 2.5452 | 0.68 | 0.6370 | 0.2744 | 0.1217 | | 0.9462 | 48.0 | 624 | 0.8011 | 0.69 | 0.4529 | 2.4281 | 0.69 | 0.6402 | 0.2594 | 0.1224 | | 0.9462 | 49.0 | 637 | 0.8017 | 0.69 | 0.4532 | 2.4239 | 0.69 | 0.6400 | 0.2613 | 0.1261 | | 0.9462 | 50.0 | 650 | 0.8009 | 0.695 | 0.4518 | 2.3840 | 0.695 | 0.6406 | 0.2661 | 0.1211 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3

Palunay/I1

Palunay

2023-10-03T18:45:03Z

0

null

[ "region:us" ]

null

2023-10-03T18:41:23Z

young demoness girl,(strong physique), 4 horns, 2 on the front side, 2 larger on the sides,red yellow brown curly hair,gray-blue eyes with an orange tinge, here is a small hump on the nose, the nose somewhat resembles the nose of a cat, in addition, her ears look like a cat's, but they are always slightly lowered, because they are in the place of ordinary human ones, Red lips and protruding fangs. Loose hair. The chest is medium-sized, the hips are visible, the muscles of the buttocks are large, as are the muscles of the arms. He wears black armor with gold inserts and green precious stones and large earrings, on his feet and hands he has strong claws. There is also a strong one. The tail is similar to the tail of a jasher and a cat at the same time. They are wearing large black shoulder pads, black dragon bone trousers, a huge bib and knee-high boots. On the back of 2 bolshie sharp demonic wings

Terps/whisper-small-dv

Terps

2023-10-03T18:42:46Z

79

0

transformers

[ "transformers", "pytorch", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dv", "dataset:mozilla-foundation/common_voice_13_0", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

automatic-speech-recognition

2023-10-02T19:46:49Z

--- language: - dv license: apache-2.0 base_model: openai/whisper-small tags: - generated_from_trainer datasets: - mozilla-foundation/common_voice_13_0 metrics: - wer model-index: - name: Whisper Small Dv - Sanchit Gandhi results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: Common Voice 13 type: mozilla-foundation/common_voice_13_0 config: dv split: test args: dv metrics: - name: Wer type: wer value: 12.72733595298536 ---  # Whisper Small Dv This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset. It achieves the following results on the evaluation set: - Loss: 0.1677 - Wer Ortho: 62.0238 - Wer: 12.7273 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant_with_warmup - lr_scheduler_warmup_steps: 50 - training_steps: 500 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:| | 0.1225 | 1.63 | 500 | 0.1677 | 62.0238 | 12.7273 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3

bdpc/resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.5

bdpc

2023-10-03T18:38:27Z

199

0

transformers

[ "transformers", "pytorch", "resnet", "image-classification", "generated_from_trainer", "base_model:microsoft/resnet-50", "base_model:finetune:microsoft/resnet-50", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T18:20:05Z

--- license: apache-2.0 base_model: microsoft/resnet-50 tags: - generated_from_trainer metrics: - accuracy model-index: - name: resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.5 results: [] ---  # resnet101-base_tobacco-cnn_tobacco3482_kd_CEKD_t1.5_a0.5 This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6500 - Accuracy: 0.69 - Brier Loss: 0.5003 - Nll: 2.5629 - F1 Micro: 0.69 - F1 Macro: 0.6350 - Ece: 0.3098 - Aurc: 0.1329 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll | F1 Micro | F1 Macro | Ece | Aurc | |:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:| | No log | 1.0 | 13 | 1.4712 | 0.165 | 0.8966 | 8.4652 | 0.165 | 0.1101 | 0.2129 | 0.8342 | | No log | 2.0 | 26 | 1.4590 | 0.165 | 0.8951 | 8.1097 | 0.165 | 0.1059 | 0.2034 | 0.8021 | | No log | 3.0 | 39 | 1.4178 | 0.175 | 0.8873 | 6.8095 | 0.175 | 0.0813 | 0.2150 | 0.7994 | | No log | 4.0 | 52 | 1.3342 | 0.18 | 0.8702 | 6.4137 | 0.18 | 0.0475 | 0.2314 | 0.7558 | | No log | 5.0 | 65 | 1.2828 | 0.2 | 0.8587 | 6.1547 | 0.2000 | 0.0642 | 0.2429 | 0.7009 | | No log | 6.0 | 78 | 1.2675 | 0.205 | 0.8548 | 6.1395 | 0.205 | 0.0612 | 0.2348 | 0.7022 | | No log | 7.0 | 91 | 1.0716 | 0.31 | 0.7962 | 6.4589 | 0.31 | 0.1241 | 0.2787 | 0.4433 | | No log | 8.0 | 104 | 1.1184 | 0.29 | 0.8126 | 6.2585 | 0.29 | 0.1394 | 0.2863 | 0.5819 | | No log | 9.0 | 117 | 1.1021 | 0.31 | 0.8075 | 6.0370 | 0.31 | 0.1697 | 0.2834 | 0.5458 | | No log | 10.0 | 130 | 1.0268 | 0.33 | 0.7815 | 6.1370 | 0.33 | 0.1921 | 0.2856 | 0.5395 | | No log | 11.0 | 143 | 1.0290 | 0.355 | 0.7759 | 5.3640 | 0.3550 | 0.2143 | 0.2795 | 0.4697 | | No log | 12.0 | 156 | 0.9169 | 0.36 | 0.7262 | 5.2997 | 0.36 | 0.1995 | 0.2761 | 0.4070 | | No log | 13.0 | 169 | 0.9903 | 0.36 | 0.7586 | 4.9404 | 0.36 | 0.2200 | 0.2832 | 0.5343 | | No log | 14.0 | 182 | 0.9128 | 0.425 | 0.7082 | 4.5862 | 0.425 | 0.2706 | 0.2834 | 0.3542 | | No log | 15.0 | 195 | 1.0046 | 0.405 | 0.7441 | 3.9763 | 0.405 | 0.2759 | 0.3142 | 0.4602 | | No log | 16.0 | 208 | 0.9277 | 0.41 | 0.7146 | 4.3670 | 0.41 | 0.2763 | 0.2695 | 0.4409 | | No log | 17.0 | 221 | 0.9726 | 0.505 | 0.7208 | 3.5350 | 0.505 | 0.3736 | 0.3332 | 0.3469 | | No log | 18.0 | 234 | 0.7717 | 0.505 | 0.6280 | 3.4386 | 0.505 | 0.3412 | 0.2564 | 0.2567 | | No log | 19.0 | 247 | 0.7723 | 0.58 | 0.6143 | 3.6207 | 0.58 | 0.4125 | 0.3178 | 0.1847 | | No log | 20.0 | 260 | 0.8182 | 0.57 | 0.6419 | 3.1633 | 0.57 | 0.4855 | 0.3517 | 0.2530 | | No log | 21.0 | 273 | 0.7333 | 0.58 | 0.5891 | 3.3014 | 0.58 | 0.4512 | 0.2718 | 0.2137 | | No log | 22.0 | 286 | 0.7374 | 0.665 | 0.5856 | 3.0299 | 0.665 | 0.5432 | 0.3459 | 0.1657 | | No log | 23.0 | 299 | 0.7083 | 0.645 | 0.5564 | 3.0874 | 0.645 | 0.5180 | 0.3112 | 0.1608 | | No log | 24.0 | 312 | 0.7480 | 0.64 | 0.5901 | 3.0218 | 0.64 | 0.5410 | 0.3701 | 0.1976 | | No log | 25.0 | 325 | 0.7547 | 0.68 | 0.5894 | 2.9002 | 0.68 | 0.5801 | 0.3817 | 0.1559 | | No log | 26.0 | 338 | 0.6998 | 0.65 | 0.5474 | 2.9402 | 0.65 | 0.5468 | 0.2875 | 0.1707 | | No log | 27.0 | 351 | 0.6967 | 0.66 | 0.5506 | 2.8344 | 0.66 | 0.5578 | 0.3105 | 0.1707 | | No log | 28.0 | 364 | 0.6733 | 0.655 | 0.5332 | 2.6492 | 0.655 | 0.5719 | 0.2935 | 0.1554 | | No log | 29.0 | 377 | 0.7162 | 0.67 | 0.5596 | 2.7250 | 0.67 | 0.5721 | 0.3388 | 0.1423 | | No log | 30.0 | 390 | 0.6826 | 0.665 | 0.5291 | 2.7460 | 0.665 | 0.5797 | 0.3353 | 0.1469 | | No log | 31.0 | 403 | 0.6761 | 0.665 | 0.5195 | 2.7938 | 0.665 | 0.5647 | 0.3096 | 0.1485 | | No log | 32.0 | 416 | 0.6745 | 0.695 | 0.5295 | 2.6172 | 0.695 | 0.6160 | 0.3171 | 0.1636 | | No log | 33.0 | 429 | 0.6785 | 0.695 | 0.5242 | 2.5816 | 0.695 | 0.6115 | 0.3475 | 0.1349 | | No log | 34.0 | 442 | 0.6688 | 0.665 | 0.5174 | 2.6401 | 0.665 | 0.5833 | 0.2988 | 0.1427 | | No log | 35.0 | 455 | 0.6767 | 0.675 | 0.5275 | 2.6364 | 0.675 | 0.6027 | 0.3285 | 0.1483 | | No log | 36.0 | 468 | 0.6605 | 0.695 | 0.5076 | 2.6483 | 0.695 | 0.6252 | 0.3127 | 0.1372 | | No log | 37.0 | 481 | 0.6538 | 0.705 | 0.5029 | 2.6284 | 0.705 | 0.6340 | 0.3173 | 0.1220 | | No log | 38.0 | 494 | 0.6610 | 0.695 | 0.5102 | 2.5052 | 0.695 | 0.6375 | 0.3128 | 0.1298 | | 0.7532 | 39.0 | 507 | 0.6618 | 0.695 | 0.5110 | 2.5663 | 0.695 | 0.6268 | 0.3297 | 0.1367 | | 0.7532 | 40.0 | 520 | 0.6749 | 0.69 | 0.5235 | 2.5343 | 0.69 | 0.6341 | 0.3256 | 0.1332 | | 0.7532 | 41.0 | 533 | 0.6574 | 0.695 | 0.5062 | 2.4223 | 0.695 | 0.6338 | 0.3292 | 0.1469 | | 0.7532 | 42.0 | 546 | 0.6530 | 0.695 | 0.5026 | 2.6189 | 0.695 | 0.6390 | 0.2950 | 0.1391 | | 0.7532 | 43.0 | 559 | 0.6509 | 0.685 | 0.5003 | 2.5417 | 0.685 | 0.6299 | 0.3150 | 0.1368 | | 0.7532 | 44.0 | 572 | 0.6520 | 0.71 | 0.5030 | 2.4796 | 0.7100 | 0.6453 | 0.3251 | 0.1286 | | 0.7532 | 45.0 | 585 | 0.6494 | 0.69 | 0.4994 | 2.5431 | 0.69 | 0.6327 | 0.3138 | 0.1279 | | 0.7532 | 46.0 | 598 | 0.6515 | 0.71 | 0.5007 | 2.5295 | 0.7100 | 0.6541 | 0.3307 | 0.1208 | | 0.7532 | 47.0 | 611 | 0.6477 | 0.69 | 0.4979 | 2.5971 | 0.69 | 0.6323 | 0.3263 | 0.1281 | | 0.7532 | 48.0 | 624 | 0.6495 | 0.7 | 0.5007 | 2.6162 | 0.7 | 0.6395 | 0.3412 | 0.1272 | | 0.7532 | 49.0 | 637 | 0.6478 | 0.7 | 0.4968 | 2.4946 | 0.7 | 0.6386 | 0.3191 | 0.1309 | | 0.7532 | 50.0 | 650 | 0.6500 | 0.69 | 0.5003 | 2.5629 | 0.69 | 0.6350 | 0.3098 | 0.1329 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.2.0.dev20231002 - Datasets 2.7.1 - Tokenizers 0.13.3

mehle/anders

mehle

2023-10-03T18:22:33Z

0

null

[ "audio-to-audio", "da", "en", "license:apache-2.0", "region:us" ]

audio-to-audio

2023-10-03T18:21:37Z

--- license: apache-2.0 language: - da - en pipeline_tag: audio-to-audio ---

teknium/airoboros-mistral2.2-7b

teknium

2023-10-03T18:18:12Z

62

36

transformers

[ "transformers", "pytorch", "mistral", "text-generation", "llama-2", "instruct", "finetune", "alpaca", "gpt4", "synthetic data", "distillation", "en", "dataset:jondurbin/airoboros-2.2.1", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-10-03T15:07:51Z

--- base_model: mistralai/Mistral-7b-V0.1 tags: - llama-2 - instruct - finetune - alpaca - gpt4 - synthetic data - distillation datasets: - jondurbin/airoboros-2.2.1 model-index: - name: airoboros2.2-mistral-7b results: [] license: mit language: - en --- Mistral trained with the airoboros dataset! ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/sbN_PCdxO_LV0xpFGA_St.png) Actual dataset is airoboros 2.2, but it seems to have been replaced on hf with 2.2.1. Prompt Format: ``` USER: <prompt> ASSISTANT: ``` TruthfulQA: ``` hf-causal-experimental (pretrained=/home/teknium/dakota/lm-evaluation-harness/airoboros2.2-mistral/,dtype=float16), limit: None, provide_description: False, num_fewshot: 0, batch_size: 8 | Task |Version|Metric|Value | |Stderr| |-------------|------:|------|-----:|---|-----:| |truthfulqa_mc| 1|mc1 |0.3562|± |0.0168| | | |mc2 |0.5217|± |0.0156| ``` Wandb training charts: https://wandb.ai/teknium1/airoboros-mistral-7b/runs/airoboros-mistral-1?workspace=user-teknium1 More info to come

LoneStriker/dolphin-2.0-mistral-7b-6.0bpw-h6-exl2

LoneStriker

2023-10-03T17:59:38Z

5

0

transformers

[ "transformers", "pytorch", "mistral", "text-generation", "conversational", "en", "dataset:ehartford/dolphin", "dataset:jondurbin/airoboros-2.2.1", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]

text-generation

2023-10-03T17:32:05Z

--- license: apache-2.0 datasets: - ehartford/dolphin - jondurbin/airoboros-2.2.1 language: - en --- Dolphin 2.0 🐬 https://erichartford.com/dolphin Dolphin-2.0-mistral-7b's training was sponsored by [a16z](https://a16z.com/supporting-the-open-source-ai-community/). This model is based on mistralAI, so it is suitable for commercial or non-commercial use. This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly. ## Dataset This dataset is Dolphin, an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/) I modified the dataset for uncensoring, deduping, cleaning, and quality. I added Jon Durbin's excellent Airoboros dataset to increase creativity. ## Training It took 48 hours to train 10 epochs on 4x A100s. Prompt format: This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format. ``` <|im_start|>system You are Dolphin, a helpful AI assistant.<|im_end|> <|im_start|>user {prompt}<|im_end|> ``` Example: ``` <|im_start|>system you are an expert dolphin trainer<|im_end|> <|im_start|>user What is the best way to train a dolphin to obey me? Please answer step by step.<|im_end|> ``` ## Gratitude - This model was made possible by the generous sponsorship of a16z. - Thank you to Microsoft for authoring the Orca paper and inspiring this work. - Special thanks to WingLian, and TheBloke for helpful advice - Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way. ## Example Output ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/xnz5M1lYd4oGVATSDRkQ-.png) [Buy me a coffee](https://www.buymeacoffee.com/ehartford)

Dugald/MarketingModel

Dugald

2023-10-03T17:29:13Z

0

peft

[ "peft", "region:us" ]

null

2023-10-03T17:29:07Z

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.0.dev0

Bainbridge/umberto-uncased-covid-sentiment

Bainbridge

2023-10-03T17:16:42Z

106

0

transformers

[ "transformers", "pytorch", "camembert", "text-classification", "generated_from_trainer", "base_model:Musixmatch/umberto-wikipedia-uncased-v1", "base_model:finetune:Musixmatch/umberto-wikipedia-uncased-v1", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

2023-10-03T17:16:17Z

--- base_model: Musixmatch/umberto-wikipedia-uncased-v1 tags: - generated_from_trainer metrics: - f1 model-index: - name: umberto-wikipedia-uncased-v1 results: [] ---  # umberto-wikipedia-uncased-v1 This model is a fine-tuned version of [Musixmatch/umberto-wikipedia-uncased-v1](https://huggingface.co/Musixmatch/umberto-wikipedia-uncased-v1) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4643 - F1: 0.6160 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 128 - eval_batch_size: 32 - seed: 0 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.05 - num_epochs: 5.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 | |:-------------:|:-----:|:----:|:---------------:|:------:| | 0.5923 | 0.33 | 20 | 0.6075 | 0.2974 | | 0.6694 | 0.67 | 40 | 0.5938 | 0.2974 | | 0.5225 | 1.0 | 60 | 0.5346 | 0.3024 | | 0.5458 | 1.33 | 80 | 0.5172 | 0.4682 | | 0.5052 | 1.67 | 100 | 0.5550 | 0.4361 | | 0.3689 | 2.0 | 120 | 0.5188 | 0.4395 | | 0.4097 | 2.33 | 140 | 0.4918 | 0.4676 | | 0.4904 | 2.67 | 160 | 0.4756 | 0.4640 | | 0.3696 | 3.0 | 180 | 0.4788 | 0.4688 | | 0.3631 | 3.33 | 200 | 0.4751 | 0.4735 | | 0.4345 | 3.67 | 220 | 0.4609 | 0.4797 | | 0.3398 | 4.0 | 240 | 0.4637 | 0.5673 | | 0.2985 | 4.33 | 260 | 0.4850 | 0.5092 | | 0.3248 | 4.67 | 280 | 0.5089 | 0.6057 | | 0.3323 | 5.0 | 300 | 0.4643 | 0.6160 | ### Framework versions - Transformers 4.34.0.dev0 - Pytorch 2.1.0.dev20230628+cu121 - Datasets 2.14.5 - Tokenizers 0.14.0

TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ

TheBloke

2023-10-03T17:12:08Z

100

2

transformers

[ "transformers", "safetensors", "llama", "text-generation", "en", "dataset:cerebras/SlimPajama-627B", "dataset:bigcode/starcoderdata", "base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-480k-1T", "base_model:quantized:TinyLlama/TinyLlama-1.1B-intermediate-step-480k-1T", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]

text-generation

2023-10-03T17:06:23Z

--- base_model: PY007/TinyLlama-1.1B-intermediate-step-480k-1T datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata inference: false language: - en license: apache-2.0 model_creator: Zhang Peiyuan model_name: TinyLlama 1.1B Intermediate Step 480K 1T model_type: tinyllama prompt_template: '<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ' quantized_by: TheBloke ---   <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">  # TinyLlama 1.1B Intermediate Step 480K 1T - GPTQ - Model creator: [Zhang Peiyuan](https://huggingface.co/PY007) - Original model: [TinyLlama 1.1B Intermediate Step 480K 1T](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-480k-1T)  ## Description This repo contains GPTQ model files for [Zhang Peiyuan's TinyLlama 1.1B Intermediate Step 480K 1T](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-480k-1T). Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.   ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GGUF) * [Zhang Peiyuan's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-480k-1T)   ## Prompt template: ChatML ``` <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ```   ## Provided files, and GPTQ parameters Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements. Each separate quant is in a different branch. See below for instructions on fetching from different branches. Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers. <details> <summary>Explanation of GPTQ parameters</summary> - Bits: The bit size of the quantised model. - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value. - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now. - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy. - GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s). - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences. - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit. </details> | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc | | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- | | [main](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 0.77 GB | No | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. | | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 0.82 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. | | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 1.23 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. | | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 1.26 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. | | [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 1.32 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. | | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 0.79 GB | No | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |   ## How to download, including from branches ### In text-generation-webui To download from the `main` branch, enter `TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ` in the "Download model" box. To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ:gptq-4bit-32g-actorder_True` ### From the command line I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` To download the `main` branch to a folder called `TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ`: ```shell mkdir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ huggingface-cli download TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --local-dir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: ```shell mkdir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ huggingface-cli download TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model. The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`. For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell mkdir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --local-dir TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> ### With `git` (**not** recommended) To clone a specific branch with `git`, use a command like this: ```shell git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ ``` Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)   ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui). Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui). It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install. 1. Click the **Model tab**. 2. Under **Download custom model or LoRA**, enter `TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ`. - To download from a specific branch, enter for example `TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ:gptq-4bit-32g-actorder_True` - see Provided Files above for the list of branches for each option. 3. Click **Download**. 4. The model will start downloading. Once it's finished it will say "Done". 5. In the top left, click the refresh icon next to **Model**. 6. In the **Model** dropdown, choose the model you just downloaded: `TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ` 7. The model will automatically load, and is now ready for use! 8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right. * Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`. 9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!   ## Serving this model from Text Generation Inference (TGI) It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0` Example Docker parameters: ```shell --model-id TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096 ``` Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later): ```shell pip3 install huggingface-hub ``` ```python from huggingface_hub import InferenceClient endpoint_url = "https://your-endpoint-url-here" prompt = "Tell me about AI" prompt_template=f'''<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ''' client = InferenceClient(endpoint_url) response = client.text_generation(prompt, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1) print(f"Model output: {response}") ```   ## How to use this GPTQ model from Python code ### Install the necessary packages Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later. ```shell pip3 install transformers optimum pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7 ``` If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead: ```shell pip3 uninstall -y auto-gptq git clone https://github.com/PanQiWei/AutoGPTQ cd AutoGPTQ git checkout v0.4.2 pip3 install . ``` ### You can then use the following code ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_name_or_path = "TheBloke/TinyLlama-1.1B-intermediate-step-480k-1T-GPTQ" # To use a different branch, change revision # For example: revision="gptq-4bit-32g-actorder_True" model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=False, revision="main") tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) prompt = "Tell me about AI" prompt_template=f'''<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ''' print("\n\n*** Generate:") input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda() output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512) print(tokenizer.decode(output[0])) # Inference can also be done using transformers' pipeline print("*** Pipeline:") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1 ) print(pipe(prompt_template)[0]['generated_text']) ```   ## Compatibility The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI). [ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility. [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.    ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant.  # Original model card: Zhang Peiyuan's TinyLlama 1.1B Intermediate Step 480K 1T <div align="center"> # TinyLlama-1.1B </div> https://github.com/jzhang38/TinyLlama The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. <div align="center"> <img src="./TinyLlama_logo.png" width="300"/> </div> We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint. #### This Model This is an intermediate checkpoint with 480K steps and 1007B tokens. #### How to use You will need the transformers>=4.31 Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information. ```python from transformers import AutoTokenizer import transformers import torch model = "PY007/TinyLlama-1.1B-intermediate-step-240k-503b" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) sequences = pipeline( 'The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.', do_sample=True, top_k=10, num_return_sequences=1, repetition_penalty=1.5, eos_token_id=tokenizer.eos_token_id, max_length=500, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ```

TheBloke/em_german_mistral_v01-GPTQ

TheBloke

2023-10-03T17:05:54Z

17

5

transformers

[ "transformers", "safetensors", "mistral", "text-generation", "pytorch", "llama", "llama-2", "german", "deutsch", "de", "base_model:jphme/em_german_mistral_v01", "base_model:quantized:jphme/em_german_mistral_v01", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]

text-generation

2023-10-03T16:25:06Z

--- base_model: jphme/em_german_mistral_v01 inference: false language: - de library_name: transformers license: apache-2.0 model_creator: Jan Philipp Harries model_name: EM German Mistral v01 model_type: mistral pipeline_tag: text-generation prompt_template: 'Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT: ' quantized_by: TheBloke tags: - mistral - pytorch - llama - llama-2 - german - deutsch ---   <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">  # EM German Mistral v01 - GPTQ - Model creator: [Jan Philipp Harries](https://huggingface.co/jphme) - Original model: [EM German Mistral v01](https://huggingface.co/jphme/em_german_mistral_v01)  ## Description This repo contains GPTQ model files for [Jan Philipp Harries's EM German Mistral v01](https://huggingface.co/jphme/em_german_mistral_v01). Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.   ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/em_german_mistral_v01-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF) * [Jan Philipp Harries's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jphme/em_german_mistral_v01)   ## Prompt template: EmGerman ``` Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT: ```   ## Provided files, and GPTQ parameters Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements. Each separate quant is in a different branch. See below for instructions on fetching from different branches. Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers. <details> <summary>Explanation of GPTQ parameters</summary> - Bits: The bit size of the quantised model. - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value. - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now. - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy. - GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s). - Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences. - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit. </details> | Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc | | ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- | | [main](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 4.16 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. | | [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 4.57 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. | | [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 7.52 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. | | [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 7.68 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. | | [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 8.17 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. | | [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 8192 | 4.29 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |   ## How to download, including from branches ### In text-generation-webui To download from the `main` branch, enter `TheBloke/em_german_mistral_v01-GPTQ` in the "Download model" box. To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/em_german_mistral_v01-GPTQ:gptq-4bit-32g-actorder_True` ### From the command line I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` To download the `main` branch to a folder called `em_german_mistral_v01-GPTQ`: ```shell mkdir em_german_mistral_v01-GPTQ huggingface-cli download TheBloke/em_german_mistral_v01-GPTQ --local-dir em_german_mistral_v01-GPTQ --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: ```shell mkdir em_german_mistral_v01-GPTQ huggingface-cli download TheBloke/em_german_mistral_v01-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir em_german_mistral_v01-GPTQ --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model. The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`. For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell mkdir em_german_mistral_v01-GPTQ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/em_german_mistral_v01-GPTQ --local-dir em_german_mistral_v01-GPTQ --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> ### With `git` (**not** recommended) To clone a specific branch with `git`, use a command like this: ```shell git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/em_german_mistral_v01-GPTQ ``` Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)   ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui). Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui). It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install. 1. Click the **Model tab**. 2. Under **Download custom model or LoRA**, enter `TheBloke/em_german_mistral_v01-GPTQ`. - To download from a specific branch, enter for example `TheBloke/em_german_mistral_v01-GPTQ:gptq-4bit-32g-actorder_True` - see Provided Files above for the list of branches for each option. 3. Click **Download**. 4. The model will start downloading. Once it's finished it will say "Done". 5. In the top left, click the refresh icon next to **Model**. 6. In the **Model** dropdown, choose the model you just downloaded: `em_german_mistral_v01-GPTQ` 7. The model will automatically load, and is now ready for use! 8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right. * Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`. 9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!   ## Serving this model from Text Generation Inference (TGI) It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0` Example Docker parameters: ```shell --model-id TheBloke/em_german_mistral_v01-GPTQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096 ``` Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later): ```shell pip3 install huggingface-hub ``` ```python from huggingface_hub import InferenceClient endpoint_url = "https://your-endpoint-url-here" prompt = "Tell me about AI" prompt_template=f'''Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT: ''' client = InferenceClient(endpoint_url) response = client.text_generation(prompt, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1) print(f"Model output: {response}") ```   ## How to use this GPTQ model from Python code ### Install the necessary packages Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later. ```shell pip3 install transformers optimum pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7 ``` If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead: ```shell pip3 uninstall -y auto-gptq git clone https://github.com/PanQiWei/AutoGPTQ cd AutoGPTQ git checkout v0.4.2 pip3 install . ``` ### You can then use the following code ```python from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline model_name_or_path = "TheBloke/em_german_mistral_v01-GPTQ" # To use a different branch, change revision # For example: revision="gptq-4bit-32g-actorder_True" model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=False, revision="main") tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) prompt = "Tell me about AI" prompt_template=f'''Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT: ''' print("\n\n*** Generate:") input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda() output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512) print(tokenizer.decode(output[0])) # Inference can also be done using transformers' pipeline print("*** Pipeline:") pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95, top_k=40, repetition_penalty=1.1 ) print(pipe(prompt_template)[0]['generated_text']) ```   ## Compatibility The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI). [ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility. [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.    ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant.  # Original model card: Jan Philipp Harries's EM German Mistral v01 ![EM Logo](em_model_logo_web.jpeg) # EM German Mistral 7b (Alpha) ([Zur deutschen Version](#deutsch-em-german)) **EM German (v01)** is an experimental llama2 and mistral-based model family, finetuned on a large dataset of various instructions in German language. The models are optimized for German text, providing proficiency in understanding, generating, and interacting with German language content. **This is a very first experimental version of Mistrals 7b model**. This is still based on the HF LLama Model and not on the Mistral implementation, lacking features like GQA and sliding windows - use at your own discretion. For more mature models, please look at the llama-2 based models of the EM family (see links below). # Links & Demos We will publish further instructions, updates and code-snippets in the project's [Github-Repo](https://github.com/jphme/EM_German). ## Model Links | Base Model | HF | GPTQ | GGUF | AWQ | |-------|-------|-------|-------|-------| | [Llama2](https://huggingface.co/meta-llama/Llama-2-7b-hf) 7b | [Link](https://huggingface.co/jphme/em_german_7b_v01) | [Link](https://huggingface.co/jphme/em_german_7b_v01_gptq) | [Link](https://huggingface.co/jphme/em_german_7b_v01_gguf) | soon | | [Llama2](https://huggingface.co/meta-llama/Llama-2-13b-hf) 13b | [Link](https://huggingface.co/jphme/em_german_13b_v01) | [Link](https://huggingface.co/jphme/em_german_13b_v01_gptq) | soon | soon | | [Llama2](https://huggingface.co/meta-llama/Llama-2-70b-hf) 70b | [Link](https://huggingface.co/jphme/em_german_70b_v01) | [Link](https://huggingface.co/jphme/em_german_70b_v01_gptq) | [Link](https://huggingface.co/jphme/em_german_70b_v01_gguf) | soon | | [Mistral 7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) | [Link](https://huggingface.co/jphme/em_german_mistral_v01) | soon | soon | tbc | | [LeoLm 7b](https://huggingface.co/LeoLM/leo-hessianai-7b) | soon | soon | soon | tbc | | [LeoLM 13b](https://huggingface.co/LeoLM/leo-hessianai-7b) | soon | soon | soon | tbc | ## Demos: You can use some of the models with **free** google Colab instances (e.g. the 7bn model in 8bit or the 13b model with GPTQ): * [Example Colab Notebook for 13b with GPTQ](https://colab.research.google.com/drive/1IJfJdVwGkfe5MYOqHptystR3FBeEUdGn?usp=sharing) * [Example Colab Notebook for 7b with 8bit-Loading](https://colab.research.google.com/drive/1bsv6vkLM4AlCpSyXA6ol9P32zxZmf7Zu?usp=sharing) * Further Examples for LLM apps will follow soon... # Prompt Format This model follows the Vicuna format without linebreaks (but should work with linebreaks as well). The format is as follows: ``` Du bist ein hilfreicher Assistent. USER: <instruction> ASSISTANT: ``` You can swap the standard system prompt for a better suited one (see below for RAG-tasks). # Results Attached a few example outputs. I also developed a few small German benchmarks (based on the Eleuther LM Evaluation Harness), which I will publish soon. ## Example Output Prompt: ``` Du bist ein hilfreicher Assistent USER: Ein Buch hat 500 Seiten. Jede Seite enthält 300 Wörter. Wie viele Wörter sind im gesamten Buch enthalten? ASSISTANT: ``` Response EM 7b v01 ``` Die Gesamtzahl der Wörter in dem Buch kann berechnet werden, indem man die Anzahl der Wörter pro Seite mit der Gesamtzahl der Seiten multipliziert. Gesamtzahl der Wörter = Anzahl der Wörter pro Seite * Gesamtzahl der Seiten = 300 Wörter pro Seite * 500 Seiten = 150.000 Wörter Das Buch enthält also insgesamt 150.000 Wörter. ``` Prompt: ``` Du bist ein hilfreicher Assistent USER: Erläutere die Grundprinzipien der evolutionären Biologie und Genetik, indem du den Prozess der natürlichen Selektion, die Rolle von Mutationen und genetischer Drift sowie das Konzept der adaptiven Radiation erklärst. ASSISTANT: ``` Response EM 7b v01 ``` Die Evolutionäre Biologie und Genetik sind zwei intim verwandte Disziplinen, die sich mit dem Studium des Verhaltens und der Entwicklung von Organismen in der Natur befassen. Sie untersuchen, wie Arten sich im Laufe der Zeit entwickeln und wie diese Veränderungen genetisch bedingt sind. 1. Natürliche Selektion: Die natürliche Selektion ist ein grundlegendes Prinzip in der Evolutionäre Biologie. Es besagt, dass Individuen innerhalb einer Spezies unterschiedliche Fähigkeiten oder Merkmale aufweisen können. Diese Merkmale beeinflussen ihre Überlebens- und Fortpflanzungsrate. Diejenigen mit Vorteilen haben eine höhere Wahrscheinlichkeit, ihre Gene an zukünftige Generationen weiterzugeben und so die Art im Laufe der Zeit zu verändern. 2. Rolle von Mutationen: Mutationen sind Veränderungen im Genom eines Organismus, die entweder durch zufällige Fehler während der Replikation oder durch Exposition gegenüber Strahlung verursacht werden. Diese Veränderungen können dazu führen, dass ein Individuum neue Eigenschaften aufweist, die es im Kampf ums Überleben vorteilhaft machen könnten. Diese Mutationen werden dann von der natürlichen Selektion beeinflusst und können so zur Entwicklung neuer Arten beitragen. 3. Genetische Drift: Genetische Drift ist ein zufälliger Prozess, der durch die Verteilung von Allelen in einer Population stattfindet. Wenn eine Population kleiner wird oder wenn die Überlebens- und Fortpflanzungsraten zwischen den Individuen variieren, kann dies dazu führen, dass bestimmte Gene stärker oder weniger häufig werden. Dies kann dazu führen, dass die Population im Laufe der Zeit unterschiedliche Merkmale aufweist. 4. Adaptive Radiation: Adaptive Radiation ist ein Prozess, bei dem eine Art mehrere verschiedene Linien auslässt, die sich auf verschiedene Weise an ihre Umgebung anpassen. Dies geschieht normalerweise, wenn die Umwelt sich ändert und die Art neue Fähigkeiten benötigt, um überleben zu können. Die verschiedenen Linien können dann unterschiedliche Eigenschaften entwickeln, die ihnen helfen, in dieser neuen Umgebung zu überleben. ``` ## Factual Retrieval / RAG EM Models offer a special format for Factual Retrieval/RAG that is optimized for minimizing hallucinations. We use the same format as Airoboros for this: ### Example Prompt ``` Du bist ein hilfreicher Assistent. Für die folgende Aufgabe stehen dir zwischen den tags BEGININPUT und ENDINPUT mehrere Quellen zur Verfügung. Metadaten zu den einzelnen Quellen wie Autor, URL o.ä. sind zwischen BEGINCONTEXT und ENDCONTEXT zu finden, danach folgt der Text der Quelle. Die eigentliche Aufgabe oder Frage ist zwischen BEGININSTRUCTION und ENDINCSTRUCTION zu finden. Beantworte diese wortwörtlich mit einem Zitat aus den Quellen. Sollten diese keine Antwort enthalten, antworte, dass auf Basis der gegebenen Informationen keine Antwort möglich ist! USER: BEGININPUT BEGINCONTEXT Url: https://www.jph.me ENDCONTEXT Das Wetter in Düsseldorf wird heute schön und sonnig! ENDINPUT BEGININSTRUCTION Was ist 1+1? ENDINSTRUCTION ASSISTANT: ``` Model response: ``` Mit den gegebenen Informationen ist diese Frage nicht zu beantworten. ``` Note that the model would normally always answer with the correct response to a trivial question like this but is trained to deny an answer, if there is no source between the BEGININPUT and ENDINPUT that provides a grounding. If we keep the same Context/Input but ask instead: ``` BEGININSTRUCTION Wie wird das Wetter heute in Düsseldorf? Gebe die Quelle mit an! ENDINSTRUCTION ASSISTANT: ``` We get the correct answer with the source: ``` Das Wetter in Düsseldorf wird heute schön und sonnig! (Quelle: Url: https://www.jph.me) ``` # Evaluation I will publish some custom German benchmarks and the results for them soon. # Dataset The dataset is a mixture of multi-turn chats, retrieval instructions and synthetically generated instructions spawning many topics and applications. ## Use with tranformers Unchanged from the base model: ```python import torch from transformers import LlamaForCausalLM, LlamaTokenizer # Hugging Face model_path model_path = 'jphme/em_german_7b_v01' tokenizer = LlamaTokenizer.from_pretrained(model_path) model = LlamaForCausalLM.from_pretrained( model_path, torch_dtype=torch.float16, device_map='auto', ) def ask_model(instruction, system='Du bist ein hilfreicher Assistent.'): prompt=f"{system} USER: {instruction} ASSISTANT:" input_tokens=tokenizer(prompt, return_tensors="pt").to(model.device) output_tokens=model.generate(**input_tokens, max_new_tokens=200)[0] answer=tokenizer.decode(output_tokens, skip_special_tokens=True) return answer print(ask_model("Nenne mir 10 gute Gründe dafür, heute Sport zu machen!")) ``` # Limitations & Biases This model can produce factually incorrect output, and should not be relied on to produce factually accurate information. This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs. # Acknowledgements: Many thanks to [winglian/caseus](https://huggingface.co/winglian) for his great work on Axolotl which I used to train the EM mdoels. I am also grateful to [Jon Durbin](https://huggingface.co/jondurbin) and his [Airoboros](https://huggingface.co/jondurbin/airoboros-l2-70b-2.2.1) models and code from which I borrowed many ideas and code snippets. The 70b model was trained with support of the [OVH Cloud Startup Program](https://startup.ovhcloud.com/en/). # Contact I you are interested in customized LLMs for business applications, please get in contact with me via [my website](https://www.jph.me). I am also always happy about suggestions and feedback. *PS: I am also still searching for a Co-Founder*. # Disclaimer: The license on this model does not constitute legal advice. I am not responsible for the actions of third parties who use this model. This model should only be used for research purposes. The original Llama2 license applies and is distributed with the model files. ------------- ------------- ------------- # (Deutsch) EM German **EM German (v01)** ist eine experimentelle, Llama2-basierte KI-Modellreihe, die in deutscher Sprache fine-getuned wurde. Die Modelle sind für deutschen Text optimiert und können Inhalte in deutscher Sprache verstehen und generieren. **Dieses 7b-Modell wurde zusätzlich mit >3 Milliarden Token deutscher Texte vortrainiert**. # Links & Demos Im [Github-Repo](https://github.com/jphme/EM_German) Repo werde ich weitere Beispiele und Code-Snippets veröffentlichen. ## Model Links | Base Model | HF | GPTQ | GGUF | AWQ | |-------|-------|-------|-------|-------| | [Llama2](https://huggingface.co/meta-llama/Llama-2-7b-hf) 7b | [Link](https://huggingface.co/jphme/em_german_7b_v01) | [Link](https://huggingface.co/jphme/em_german_7b_v01_gptq) | [Link](https://huggingface.co/jphme/em_german_7b_v01_gguf) | soon | | [Llama2](https://huggingface.co/meta-llama/Llama-2-13b-hf) 13b | [Link](https://huggingface.co/jphme/em_german_13b_v01) | [Link](https://huggingface.co/jphme/em_german_13b_v01_gptq) | soon | soon | | [Llama2](https://huggingface.co/meta-llama/Llama-2-70b-hf) 70b | [Link](https://huggingface.co/jphme/em_german_70b_v01) | [Link](https://huggingface.co/jphme/em_german_70b_v01_gptq) | [Link](https://huggingface.co/jphme/em_german_70b_v01_gguf) | soon | | [Mistral 7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) | [Link](https://huggingface.co/jphme/em_german_mistral_v01) | soon | soon | tbc | | [LeoLm 7b](https://huggingface.co/LeoLM/leo-hessianai-7b) | soon | soon | soon | tbc | | [LeoLM 13b](https://huggingface.co/LeoLM/leo-hessianai-7b) | soon | soon | soon | tbc | ## Colab: Einige der Modelle können mit kostenlosen Google Colab-Instanzen verwendet werden (z.B. das 7b-Modell in 8-Bit oder das 13b-Modell mit GPTQ): * [Beispiel-Notebook 13b mit GPTQ](https://colab.research.google.com/drive/1IJfJdVwGkfe5MYOqHptystR3FBeEUdGn?usp=sharing) * [Beispiel-Notebook 7b mit 8-Bit](https://colab.research.google.com/drive/1bsv6vkLM4AlCpSyXA6ol9P32zxZmf7Zu?usp=sharing) * Weitere Beispiele für LLM-Apps folgen in Kürze... # Eingabeformat Dieses Modell folgt dem Vicuna-Format ohne Zeilenumbrüche (sollte aber auch mit Zeilenumbrüchen funktionieren). Das Format lautet wie folgt: ``` Du bist ein hilfreicher Assistent. USER: <Anweisung> ASSISTANT: ``` Sie können das Standard-Systemprompt aber auch ändern (siehe unten für ein Beispiel bei Aufgaben mit externen Datenbanken). # Ergebnisse Anbei einige Beispiele für Modell-Outputs. Wir werden demnächst einige kleine deutsche Benchmarks veröffentlichen (basierend auf dem Eleuther LM Evaluation Harness), die wir bei diesen Modellen bereits getstet haben. ## Beispiel-Ausgaben Prompt: ``` Du bist ein hilfreicher Assistent USER: Ein Buch hat 500 Seiten. Jede Seite enthält 300 Wörter. Wie viele Wörter sind im gesamten Buch enthalten? ASSISTANT: ``` Antwort EM 7b v01 ``` Die Gesamtzahl der Wörter in dem Buch kann berechnet werden, indem man die Anzahl der Wörter pro Seite mit der Gesamtzahl der Seiten multipliziert. Gesamtzahl der Wörter = Anzahl der Wörter pro Seite * Gesamtzahl der Seiten = 300 Wörter pro Seite * 500 Seiten = 150.000 Wörter Das Buch enthält also insgesamt 150.000 Wörter. ``` Prompt: ``` Du bist ein hilfreicher Assistent USER: Erläutere die Grundprinzipien der evolutionären Biologie und Genetik, indem du den Prozess der natürlichen Selektion, die Rolle von Mutationen und genetischer Drift sowie das Konzept der adaptiven Radiation erklärst. ASSISTANT: ``` Antwort EM 7b v01: ``` Die Evolutionäre Biologie und Genetik sind zwei intim verwandte Disziplinen, die sich mit dem Studium des Verhaltens und der Entwicklung von Organismen in der Natur befassen. Sie untersuchen, wie Arten sich im Laufe der Zeit entwickeln und wie diese Veränderungen genetisch bedingt sind. 1. Natürliche Selektion: Die natürliche Selektion ist ein grundlegendes Prinzip in der Evolutionäre Biologie. Es besagt, dass Individuen innerhalb einer Spezies unterschiedliche Fähigkeiten oder Merkmale aufweisen können. Diese Merkmale beeinflussen ihre Überlebens- und Fortpflanzungsrate. Diejenigen mit Vorteilen haben eine höhere Wahrscheinlichkeit, ihre Gene an zukünftige Generationen weiterzugeben und so die Art im Laufe der Zeit zu verändern. 2. Rolle von Mutationen: Mutationen sind Veränderungen im Genom eines Organismus, die entweder durch zufällige Fehler während der Replikation oder durch Exposition gegenüber Strahlung verursacht werden. Diese Veränderungen können dazu führen, dass ein Individuum neue Eigenschaften aufweist, die es im Kampf ums Überleben vorteilhaft machen könnten. Diese Mutationen werden dann von der natürlichen Selektion beeinflusst und können so zur Entwicklung neuer Arten beitragen. 3. Genetische Drift: Genetische Drift ist ein zufälliger Prozess, der durch die Verteilung von Allelen in einer Population stattfindet. Wenn eine Population kleiner wird oder wenn die Überlebens- und Fortpflanzungsraten zwischen den Individuen variieren, kann dies dazu führen, dass bestimmte Gene stärker oder weniger häufig werden. Dies kann dazu führen, dass die Population im Laufe der Zeit unterschiedliche Merkmale aufweist. 4. Adaptive Radiation: Adaptive Radiation ist ein Prozess, bei dem eine Art mehrere verschiedene Linien auslässt, die sich auf verschiedene Weise an ihre Umgebung anpassen. Dies geschieht normalerweise, wenn die Umwelt sich ändert und die Art neue Fähigkeiten benötigt, um überleben zu können. Die verschiedenen Linien können dann unterschiedliche Eigenschaften entwickeln, die ihnen helfen, in dieser neuen Umgebung zu überleben. ``` ## Sachliche Abfrage / RAG EM-Modelle bieten ein spezielles Format für RAG (also die Verwendung mit Informationen aus zusätzlichen externen Quellen wie Datenbanken oder Websiten), das für die Minimierung von Halluzinationen und Falscinformationen optimiert ist. Wir verwenden dasselbe Format wie Airoboros dafür. ### Beispiel Prompt ``` Du bist ein hilfreicher Assistent. Für die folgende Aufgabe stehen dir zwischen den tags BEGININPUT und ENDINPUT mehrere Quellen zur Verfügung. Metadaten zu den einzelnen Quellen wie Autor, URL o.ä. sind zwischen BEGINCONTEXT und ENDCONTEXT zu finden, danach folgt der Text der Quelle. Die eigentliche Aufgabe oder Frage ist zwischen BEGININSTRUCTION und ENDINCSTRUCTION zu finden. Beantworte diese wortwörtlich mit einem Zitat aus den Quellen. Sollten diese keine Antwort enthalten, antworte, dass auf Basis der gegebenen Informationen keine Antwort möglich ist! USER: BEGININPUT BEGINCONTEXT Url: https://www.jph.me ENDCONTEXT Das Wetter in Düsseldorf wird heute schön und sonnig! ENDINPUT BEGININSTRUCTION Was ist 1+1? ENDINSTRUCTION ASSISTANT: ``` Modellantwort: ``` Mit den gegebenen Informationen ist diese Frage nicht zu beantworten. ``` Hier würde das Modell normalerweise die (triviale) Antwort (2) geben, ist aber trainiert, keine Antwort zu geben, wenn es keine Quelle zwischen BEGININPUT und ENDINPUT gibt, die eine belegbare Antwort liefert. Wenn wir anstattdessen fragen: ``` BEGININSTRUCTION Wie wird das Wetter heute in Düsseldorf? Gebe die Quelle mit an! ENDINSTRUCTION ASSISTANT: ``` Bekommen wir die korrekte Antwort mit Quellenangabe ``` Das Wetter in Düsseldorf wird heute schön und sonnig! (Quelle: Url: https://www.jph.me) ``` # Evaluation coming soon # Datensatz Der Datensatz ist eine Mischung aus Multi-Turn-Chats, RAG Instructions und synthetisch generierten Finetuning-Daten, die viele Themen und Anwendungen abdecken. # Einschränkungen & Vorurteile Dieses Modell kann sachlich falsche Ausgaben produzieren und sollte nur zu Forschubngszwecken verwendet werden. # Danksagungen: Vielen Dank an [winglian/caseus](https://huggingface.co/winglian) für seine großartige Arbeit an Axolotl, die ich zur Schulung der EM-Modelle verwendet habe. Ich bin auch [Jon Durbin](https://huggingface.co/jondurbin) für seine Arioboros Modelle und Code-Schnipsel dankbar, von denen ich viele Ideen nutzen konnte. Das 70b-Modell wurde mit Unterstützung des [OVH Cloud Startup Program](https://startup.ovhcloud.com/en/) trainiert. # Kontakt Wenn Sie an customized LLMs für geschäftliche Anwendungen interessiert sind, kontaktieren Sie mich bitte über [meine Website](https://www.jph.me). Ich freue mich auch immer über Anregungen und Feedback zu meinen Modellen. *PS: Ich suche auch immer noch einen Co-Founder für unser Startup, das sich noch im Stealth-Modus befindet.* # Haftungsausschluss: Ich bin nicht verantwortlich für die Handlungen Dritter, die dieses Modell verwenden. Dieses Modell sollte nur für Forschungszwecke verwendet werden. Die ursprüngliche Llama2-Lizenz gilt und wird mit den Modell-Dateien verteilt.

jackoyoungblood/speecht5_finetuned_voxpopuli_nl2

jackoyoungblood

2023-10-03T16:58:57Z

82

0

transformers

[ "transformers", "pytorch", "speecht5", "text-to-audio", "generated_from_trainer", "text-to-speech", "dataset:voxpopuli", "base_model:microsoft/speecht5_tts", "base_model:finetune:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]

text-to-speech

2023-10-03T14:58:35Z

--- license: mit base_model: microsoft/speecht5_tts tags: - generated_from_trainer - text-to-speech datasets: - voxpopuli model-index: - name: speecht5_finetuned_voxpopuli_nl2 results: [] ---  # speecht5_finetuned_voxpopuli_nl2 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset. It achieves the following results on the evaluation set: - Loss: 0.4599 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.5247 | 4.3 | 1000 | 0.4807 | | 0.4971 | 8.61 | 2000 | 0.4652 | | 0.4944 | 12.91 | 3000 | 0.4625 | | 0.4913 | 17.21 | 4000 | 0.4599 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3

NASA-AIML/MIKA_BERT_FMEA_NER

NASA-AIML

2023-10-03T16:37:10Z

106

1

transformers

[ "transformers", "pytorch", "bert", "token-classification", "NER", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

2023-09-12T23:52:41Z

--- license: other language: - en pipeline_tag: token-classification tags: - token-classification - NER library_name: transformers widget: - text: "While flying a fire, the UAS experienced an issue of unknown sorts and crashed to the ground. From the people watching the aircraft near the fire, they seem to think it was some sort of motor failure due to no more noise coming from the aircraft and it falling straight to the ground." example_title: "Example 1" - text: "During a pre-flight engine run-up, a battery hatch cover disengaged from the fuselage and hit one of the vertical takeoff and landing {VTOL} propellers. The motor failsafe activated and the motors shut down." example_title: "Example 2" - text: "UAS was climbing to 11,000 ft. msl on a reconnaissance mission when it experienced a rapid and uncommanded descent. The pilot took no action but monitored instruments until the aircraft regained a stable profile. " example_title: "Example 3" --- # Manager for Intelligent Knowledge Access (MIKA) ## Custom Named-Entity Recognition (NER) for Failure Modes and Effects Analysis (FMEA) base-bert-uncased model first further pre-trained then fine-tuned for custom NER to extract failure-relevant entities from incident and accident reports. The model was trained on manually annotated NASA LLIS reports and evaluated on SAFECOM reports. NER model training was for 4 epochs with:`BertForTokenClassification.from_pretrained` , `learning_rate=2e-5`, ` weight_decay=0.01,` The model was trained to identify the following long-tailed entities: - CAU: failure cause - MOD: failure mode - EFF: failure effect - CON: control process - REC: recommendations Performace: |Entity | Precision |Recall | F-1 | Support| |-------|-----------|-------|-----|--------| |CAU | 0.31 | 0.19 | 0.23 | 1634 | |CON | 0.49 | 0.34 | 0.40 | 3859 | |EFF | 0.45 | 0.20 | 0.28 | 1959 | |MOD | 0.19 | 0.52 | 0.28 | 594 | |REC | 0.30 | 0.59 | 0.40 | 954 | |Average | 0.41 | 0.32 | 0.33 | 9000 | More infomation on training data, evaluation, and intended use can be found in the original publication Citation: S. R. Andrade and H. S. Walsh, "What Went Wrong: A Survey of Wildfire UAS Mishaps through Named Entity Recognition," 2022 IEEE/AIAA 41st Digital Avionics Systems Conference (DASC), Portsmouth, VA, USA, 2022, pp. 1-10, doi: 10.1109/DASC55683.2022.9925798. https://ieeexplore.ieee.org/abstract/document/9925798 * * * * * * * * * * * * * * Notices: Copyright © 2023 United States Government as represented by the Administrator of the National Aeronautics and Space Administration. All Rights Reserved. Disclaimers No Warranty: THE SUBJECT SOFTWARE IS PROVIDED "AS IS" WITHOUT ANY WARRANTY OF ANY KIND, EITHER EXPRESSED, IMPLIED, OR STATUTORY, INCLUDING, BUT NOT LIMITED TO, ANY WARRANTY THAT THE SUBJECT SOFTWARE WILL CONFORM TO SPECIFICATIONS, ANY IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, OR FREEDOM FROM INFRINGEMENT, ANY WARRANTY THAT THE SUBJECT SOFTWARE WILL BE ERROR FREE, OR ANY WARRANTY THAT DOCUMENTATION, IF PROVIDED, WILL CONFORM TO THE SUBJECT SOFTWARE. THIS AGREEMENT DOES NOT, IN ANY MANNER, CONSTITUTE AN ENDORSEMENT BY GOVERNMENT AGENCY OR ANY PRIOR RECIPIENT OF ANY RESULTS, RESULTING DESIGNS, HARDWARE, SOFTWARE PRODUCTS OR ANY OTHER APPLICATIONS RESULTING FROM USE OF THE SUBJECT SOFTWARE. FURTHER, GOVERNMENT AGENCY DISCLAIMS ALL WARRANTIES AND LIABILITIES REGARDING THIRD-PARTY SOFTWARE, IF PRESENT IN THE ORIGINAL SOFTWARE, AND DISTRIBUTES IT "AS IS." Waiver and Indemnity: RECIPIENT AGREES TO WAIVE ANY AND ALL CLAIMS AGAINST THE UNITED STATES GOVERNMENT, ITS CONTRACTORS AND SUBCONTRACTORS, AS WELL AS ANY PRIOR RECIPIENT. IF RECIPIENT'S USE OF THE SUBJECT SOFTWARE RESULTS IN ANY LIABILITIES, DEMANDS, DAMAGES, EXPENSES OR LOSSES ARISING FROM SUCH USE, INCLUDING ANY DAMAGES FROM PRODUCTS BASED ON, OR RESULTING FROM, RECIPIENT'S USE OF THE SUBJECT SOFTWARE, RECIPIENT SHALL INDEMNIFY AND HOLD HARMLESS THE UNITED STATES GOVERNMENT, ITS CONTRACTORS AND SUBCONTRACTORS, AS WELL AS ANY PRIOR RECIPIENT, TO THE EXTENT PERMITTED BY LAW. RECIPIENT'S SOLE REMEDY FOR ANY SUCH MATTER SHALL BE THE IMMEDIATE, UNILATERAL TERMINATION OF THIS AGREEMENT. * * * * * * * * * * * * * *

MorganDustyProd/lololoshka

MorganDustyProd

2023-10-03T16:36:42Z

0

null

[ "license:cc-by-nc-sa-4.0", "region:us" ]

null

2023-10-03T16:35:26Z

--- license: cc-by-nc-sa-4.0 ---

vineetsharma/qlora-adapter-Llama-2-7b-hf-databricks-dolly-15k

vineetsharma

2023-10-03T16:36:19Z

0

null

[ "safetensors", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "base_model:finetune:meta-llama/Llama-2-7b-hf", "region:us" ]

null

2023-10-03T11:24:15Z

--- base_model: meta-llama/Llama-2-7b-hf tags: - generated_from_trainer model-index: - name: qlora-adapter-Llama-2-7b-hf-databricks-dolly-15k results: [] ---  # qlora-adapter-Llama-2-7b-hf-databricks-dolly-15k This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) dataset. It achieves the following results on the evaluation set: - Loss: 1.1313 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed Trained on RTX A5000 - 24GB GPU. The training took 3 hours 31 mins on the datasets with 12008 train samples and 1501 validation samples ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.05 - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 1.1584 | 0.08 | 1000 | 1.1782 | | 1.0667 | 0.17 | 2000 | 1.1710 | | 1.0662 | 0.25 | 3000 | 1.1599 | | 1.0517 | 0.33 | 4000 | 1.1569 | | 1.0479 | 0.42 | 5000 | 1.1502 | | 1.0516 | 0.5 | 6000 | 1.1441 | | 1.0612 | 0.58 | 7000 | 1.1397 | | 1.0235 | 0.67 | 8000 | 1.1361 | | 1.0259 | 0.75 | 9000 | 1.1339 | | 1.0485 | 0.83 | 10000 | 1.1320 | | 1.0406 | 0.92 | 11000 | 1.1314 | | 1.0393 | 1.0 | 12000 | 1.1313 | ### Framework versions - Transformers 4.33.3 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3

cbellew09/taxi-v1

cbellew09

2023-10-03T16:34:01Z

0

null

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

reinforcement-learning

2023-10-03T16:33:59Z

--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: taxi-v1 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.56 +/- 2.71 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **Taxi-v3** This is a trained model of a **Q-Learning** agent playing **Taxi-v3** . ## Usage ```python model = load_from_hub(repo_id="cbellew09/taxi-v1", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

purabp1249/swin-tiny-patch4-window7-224-finetuned-herbify_plants

purabp1249

2023-10-03T16:28:23Z

213

0

transformers

[ "transformers", "pytorch", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swin-tiny-patch4-window7-224", "base_model:finetune:microsoft/swin-tiny-patch4-window7-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

2023-10-03T16:04:12Z

--- license: apache-2.0 base_model: microsoft/swin-tiny-patch4-window7-224 tags: - generated_from_trainer datasets: - imagefolder metrics: - accuracy model-index: - name: swin-tiny-patch4-window7-224-finetuned-herbify_plants results: - task: name: Image Classification type: image-classification dataset: name: imagefolder type: imagefolder config: default split: train args: default metrics: - name: Accuracy type: accuracy value: 0.9868421052631579 ---  # swin-tiny-patch4-window7-224-finetuned-herbify_plants This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0703 - Accuracy: 0.9868 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.7849 | 0.99 | 21 | 0.4281 | 0.8553 | | 0.2498 | 1.98 | 42 | 0.1295 | 0.9737 | | 0.1387 | 2.96 | 63 | 0.0703 | 0.9868 | | 0.1039 | 3.95 | 84 | 0.0741 | 0.9737 | ### Framework versions - Transformers 4.33.2 - Pytorch 2.0.1+cpu - Datasets 2.14.5 - Tokenizers 0.13.3