modelId
stringlengths 5
122
| author
stringlengths 2
42
| last_modified
unknown | downloads
int64 0
738M
| likes
int64 0
11k
| library_name
stringclasses 245
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 48
values | createdAt
unknown | card
stringlengths 1
901k
|
|---|---|---|---|---|---|---|---|---|---|
saltacc/wd-1-4-anime | saltacc | "2023-01-16T11:08:07Z" | 1,955 | 10 | diffusers | [
"diffusers",
"region:us"
] | null | "2022-12-14T03:04:53Z" | Entry not found |
Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct | Doctor-Shotgun | "2024-06-07T02:20:18Z" | 1,955 | 11 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"dataset:LDJnr/Capybara",
"dataset:jondurbin/airoboros-3.2",
"dataset:unalignment/toxic-dpo-v0.1",
"dataset:LDJnr/Verified-Camel",
"dataset:HuggingFaceH4/no_robots",
"dataset:Doctor-Shotgun/no-robots-sharegpt",
"dataset:Doctor-Shotgun/capybara-sharegpt",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-05T22:31:02Z" | ---
inference: false
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- llama
datasets:
- LDJnr/Capybara
- jondurbin/airoboros-3.2
- unalignment/toxic-dpo-v0.1
- LDJnr/Verified-Camel
- HuggingFaceH4/no_robots
- Doctor-Shotgun/no-robots-sharegpt
- Doctor-Shotgun/capybara-sharegpt
---
# Norobara-ZLoss-8x7B
This is an instruct-tuned [TinyLlama-1.1B-32k](https://huggingface.co/Doctor-Shotgun/TinyLlama-1.1B-32k) on several open-source instruct datasets, intended primarily for speculative decoding.
## Usage:
The intended prompt format is a modified multi-turn Alpaca instruction format:
```
### Instruction:
{system prompt}
### Input:
{user message}
### Response:
{model response}
### Input:
{user message}
### Response:
{model response}
(etc.)
```
## Bias, Risks, and Limitations
The model will show biases present in the base model. No ethical alignment was applied to prevent the generation of toxic or harmful outputs (in fact the opposite, with examples from toxic-DPO included), so generate at your own risk.
## Training Details
This model was trained as a full finetune for 3 epochs using a single A100 GPU for around 3.5 hours. |
humblemikey/PixelWave10 | humblemikey | "2024-06-20T12:07:53Z" | 1,955 | 0 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"text-to-image",
"en",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2024-06-01T06:58:46Z" | ---
license: creativeml-openrail-m
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- stable-diffusion
---
# PixelWave 10
A general-purpose fine-tuned model, great for art and photo styles.
## Model Description
PixelWave 10 has been fine-tuned to provide excellent results for both artistic and photographic styles. The focus for version 10 was to train the CLIP models, which improves reliability, ensures a wide variety of styles, and enhances prompt adherence.
## Usage Instructions
### Recommended Settings
- **Standard Use:**
- 20 steps, DPM++ SDE, CFG 4
- 40 steps, 2M SDE Karras, CFG 4
### Tips for Best Results
- **Photographic Styles:** Avoid terms like 'vibrant', 'intense', 'bright', 'high contrast', 'neon', 'dramatic' for a more natural look.
- **Art Styles:** Specify the art style, near the beginning. I usually put it after a short description of the image. Mention artist names to get their specific style, 'by artist Van Gogh'
- **PAG Recommended:** Use 1.5 Scale with CFG 3.
- **Example Prompts:**
- `Elegant Lady with Pearls, color digital photograph, woman, blonde hair, magenta sweater, pearl necklaces, earrings, thoughtful expression, indoor, plants, warm lighting, shallow depth of field, natural light, portrait, focused gaze, long hair, gold jewelry, greenery, selective focus`
- `Mountain Scene at Sunrise by artist Albert Bierstadt, oil painting, mountain scene, sunrise, landscape, adventure, journey, rugged terrain, rocky peaks, river flowing, golden light, blue sky, atmospheric perspective, dramatic composition, textured brushwork, detailed foliage, ethereal mood, natural beauty, serene expression, dynamic movement, depth of field.`
## Features
- **Improved CLIP Training:** Enhanced reliability and versatility in styles.
- **Wide Style Variety:** Capable of producing a vast range of artistic and photographic styles.
- **Prompt Efficiency:** Better adherence to prompts without needing 'quality' terms.
## No Need for the Refiner Model
PixelWave 10 achieves high-quality results without the need for a refiner model.
## Additional Tools
I also created Mikey Nodes, which contains a lot of useful nodes. You can install it through comfy manager.
## License
creativeml-openrail-m |
m3hrdadfi/wav2vec2-xlsr-persian-speech-emotion-recognition | m3hrdadfi | "2021-07-27T06:12:46Z" | 1,953 | 6 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"audio",
"automatic-speech-recognition",
"speech",
"speech-emotion-recognition",
"fa",
"dataset:ShEMO",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | "2022-03-02T23:29:05Z" | ---
language: fa
datasets:
- ShEMO
tags:
- audio
- automatic-speech-recognition
- speech
- speech-emotion-recognition
license: apache-2.0
---
# Emotion Recognition in Persian (Farsi - fa) Speech using Wav2Vec 2.0
## How to use
### Requirements
```bash
# requirement packages
!pip install git+https://github.com/huggingface/datasets.git
!pip install git+https://github.com/huggingface/transformers.git
!pip install torchaudio
!pip install librosa
```
### Prediction
```python
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchaudio
from transformers import AutoConfig, Wav2Vec2FeatureExtractor
import librosa
import IPython.display as ipd
import numpy as np
import pandas as pd
```
```python
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model_name_or_path = "m3hrdadfi/wav2vec2-xlsr-persian-speech-emotion-recognition"
config = AutoConfig.from_pretrained(model_name_or_path)
feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_name_or_path)
sampling_rate = feature_extractor.sampling_rate
model = Wav2Vec2ForSpeechClassification.from_pretrained(model_name_or_path).to(device)
```
```python
def speech_file_to_array_fn(path, sampling_rate):
speech_array, _sampling_rate = torchaudio.load(path)
resampler = torchaudio.transforms.Resample(_sampling_rate)
speech = resampler(speech_array).squeeze().numpy()
return speech
def predict(path, sampling_rate):
speech = speech_file_to_array_fn(path, sampling_rate)
inputs = feature_extractor(speech, sampling_rate=sampling_rate, return_tensors="pt", padding=True)
inputs = {key: inputs[key].to(device) for key in inputs}
with torch.no_grad():
logits = model(**inputs).logits
scores = F.softmax(logits, dim=1).detach().cpu().numpy()[0]
outputs = [{"Label": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)]
return outputs
```
```python
path = "/path/to/sadness.wav"
outputs = predict(path, sampling_rate)
```
```bash
[
{'Label': 'Anger', 'Score': '0.0%'},
{'Label': 'Fear', 'Score': '0.0%'},
{'Label': 'Happiness', 'Score': '0.0%'},
{'Label': 'Neutral', 'Score': '0.0%'},
{'Label': 'Sadness', 'Score': '99.9%'},
{'Label': 'Surprise', 'Score': '0.0%'}
]
```
## Evaluation
The following tables summarize the scores obtained by model overall and per each class.
| Emotions | precision | recall | f1-score | accuracy |
|:---------:|:---------:|:------:|:--------:|:--------:|
| Anger | 0.95 | 0.95 | 0.95 | |
| Fear | 0.33 | 0.17 | 0.22 | |
| Happiness | 0.69 | 0.69 | 0.69 | |
| Neutral | 0.91 | 0.94 | 0.93 | |
| Sadness | 0.92 | 0.85 | 0.88 | |
| Surprise | 0.81 | 0.88 | 0.84 | |
| | | | Overal | 0.90 |
## Questions?
Post a Github issue from [HERE](https://github.com/m3hrdadfi/soxan/issues). |
PygmalionAI/pygmalion-350m | PygmalionAI | "2023-01-11T23:44:13Z" | 1,953 | 53 | transformers | [
"transformers",
"pytorch",
"opt",
"text-generation",
"convAI",
"conversational",
"en",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-12-20T22:04:32Z" | ---
language:
- en
thumbnail:
tags:
- convAI
- conversational
inference: false
---
# pygmalion-350m
# Model description
This is a proof-of-concept fine-tune of Facebook's OPT-350M model optimized for dialogue, to be used as a stepping stone to higher parameter models.
**Disclaimer:** NSFW data was included in the fine-tuning of this model. Although SFW inputs will usually result in SFW outputs, you are advised to **chat at your own risk. This model is not suitable for use by minors.**
# Fine-tuning process
This model was much easier than expected to create.
We used the [ColossalAI](https://www.colossalai.org/) library to fine-tune the [OPT-350M](https://huggingface.co/facebook/opt-350m) model originally trained by Facebook on The Pile. Though our initial dataset was sets of dialogue gathered from various sources totaling about 50 MB in size, early training runs revealed that the model converged after only 7% of the dataset was passed through. To alleviate this, we massively reduced the size of the dataset to only 273 KB.
ColossalAI's magic allowed for something incredible: this entire model was fine-tuned on a singular GPU with only 6 GB ***(!)*** of VRAM. Fine-tuning took less than an hour to complete. |
OpenAssistant/llama2-70b-oasst-sft-v10 | OpenAssistant | "2023-08-29T17:57:49Z" | 1,953 | 73 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"sft",
"en",
"dataset:rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored",
"dataset:OpenAssistant/oasst1",
"dataset:shahules786/orca-best",
"dataset:argilla/databricks-dolly-15k-curated-multilingual",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-21T08:57:02Z" | ---
license: llama2
language:
- en
datasets:
- rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored
- OpenAssistant/oasst1
- shahules786/orca-best
- argilla/databricks-dolly-15k-curated-multilingual
library_name: transformers
pipeline_tag: text-generation
tags:
- sft
---
# Open-Assistant Llama2 70B SFT v10
This model is an Open-Assistant fine-tuning of Meta's [Llama2 70B](https://huggingface.co/meta-llama/Llama-2-70b) LLM.
It was fine-tuned in two stages, first on a mix of synthetic instrunctions and coding tasks and then in a "polishing" stage
on the best human demonstrations collected at [open-assistant.io](https://open-assistant.io/) up to July 23, 2023 (see [Configuration Details](#configuration-details) below).
## Model Details
- **Finetuned from:** [meta-llama/Llama-2-70b](https://huggingface.co/meta-llama/Llama-2-70b) via [epfLLM/Megatron-LLM](https://github.com/epfLLM/Megatron-LLM)
- **Model type:** Causal decoder-only transformer language model
- **Language:** English (and limited capabilities in German, Spanish, French, Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish)
- **Weights & Biases training logs:** [Stage 1](https://wandb.ai/open-assistant/public-sft/runs/run45_oasst_pre10_llama2_70b) (1 epoch pretrain-mix, 12k steps), [Stage 2](https://wandb.ai/open-assistant/public-sft/runs/run46_oasst_sft10_llama2_70b) (3 epochs oasst top-1, 519 steps)
- **Demo:** [Continuations for 250 random prompts (TGI, 4bit nf4 quantization)](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-sft%2F2023-08-22_OpenAssistant_llama2-70b-oasst-sft-v10_sampling_noprefix2_nf4.json%0A)
- **Evaluation** [FastEval-OpenAssistant Overview](https://tju01.github.io/FastEval-OpenAssistant/) (using [FastEval](https://github.com/FastEval/FastEval) & [vLLM](https://github.com/vllm-project/vllm))
- **License:** [LLAMA 2 COMMUNITY LICENSE AGREEMENT](https://huggingface.co/meta-llama/Llama-2-70b/raw/main/LICENSE.txt)
- **Contact:** [Open-Assistant Discord](https://ykilcher.com/open-assistant-discord)
## Prompting / Prompt Template
Due to public demand (see [survey](https://twitter.com/erhartford/status/1682403597525430272)) we changed the prompt-template for this model from custom prompter/assistant tokens to OpenAI's [chatml](https://github.com/openai/openai-python/blob/main/chatml.md) standard prompt format.
We hope that this leads to greater compatibility with chat inference/frontend applications.
Prompt dialogue template:
```
"""
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
"""
```
The model input can contain multiple conversation turns between user and assistant, e.g.
```
<|im_start|>user
{prompt 1}<|im_end|>
<|im_start|>assistant
{reply 1}<|im_end|>
<|im_start|>user
{prompt 2}<|im_end|>
<|im_start|>assistant
(...)
```
The model was partly trained with orca system messages.
For inference we recommend to use the official [Llama2 system message](https://github.com/facebookresearch/llama/blob/ea9f33d6d3ea8ed7d560d270986407fd6c2e52b7/example_chat_completion.py#L57-L61):
```
<|im_start|>system
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<|im_end|>
```
### Credits & Special Thanks
- Thanks to [Meta AI](https://ai.meta.com/) for training and releasing the Llama2 model.
- Distributed training support was provided by EPFL's [Machine Learning and Optimization Laboratory](https://www.epfl.ch/labs/mlo/), and [Natural Language Processing Lab](https://nlp.epfl.ch/).
- The open-source [epfLLM/Megatron-LLM](https://github.com/epfLLM/Megatron-LLM) trainer was used for fine-tuning.
- [rombodawg](https://huggingface.co/rombodawg) curated the [LosslessMegaCodeTrainingV2_1m_Evol_Uncensored](https://huggingface.co/datasets/rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored) dataset.
- [ehartford](https://huggingface.co/ehartford) generated and published the [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin) and the [ehartford/oa_leet10k](https://huggingface.co/datasets/ehartford/oa_leet10k) datasets.
- [Argilla](https://huggingface.co/argilla) curated and published the [argilla/databricks-dolly-15k-curated-multilingual](https://huggingface.co/datasets/argilla/databricks-dolly-15k-curated-multilingual) dataset.
- [shahules786](https://github.com/shahules786) de-duped and filtered the Dolphin dataset with a cluster-center approach and generated the orca-best (ocra-chat) dataset.
- [andreaskoepf](https://github.com/andreaskoepf/) prepared & orchestrated the training.
We want to especially thank everyone who contributed in the crowed-sourced Open-Assistant dataset creation on https://open-assistant.io/ - without you this project would not have been possible.
## Ethical Considerations and Limitations
Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios.
For these reasons, as with all LLMs, the potential outputs of llama2-70b-oasst-sft-v10 cannot be predicted
in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses
to user prompts. Therefore, before deploying any applications of llama2-70b-oasst-sft-v10, developers should
perform safety testing and tuning tailored to their specific applications of the model.
Please see Meta's [Responsible Use Guide](https://ai.meta.com/llama/responsible-use-guide/).
## Inference via TGI
An early version of this model had an embedding count of 32,007 which was incompatible to sharding with [TGI](https://github.com/huggingface/text-generation-inference).
In the current version the embeddings and the lm_head weights have been padded to a multiple of 128 (by replicating the emembeddings of the unk-token (id: 0)).
Sharded inference with TGI should now work as expected.
## Configuration Details
The "pretokenizer" utility used to tokenize the datamix is part of the Open-Assistant github repository and can be found here: [model/pretokenizer](https://github.com/LAION-AI/Open-Assistant/tree/main/model/pretokenizer).
### Stage 1 Pretokenizer Configuration
Entries of the dataset with assistant replies shorter than 25 tokens were excluded from training.
```
oasst_pre10_min25:
datasets:
- megacode2:
fraction: 0.5
val_split: 0.01
max_val_set: 1000
- orca-chat:
val_split: 0.01
max_val_set: 1000
- dolly15k_multilingual:
val_split: 0.05
max_val_set: 300
- oa_leet10k:
val_split: 0.05
max_val_set: 250
output_dir: "output/oasst_pre10_min25"
filename_prefix: "oasst_pre10"
min_assistant_tokens: 25
```
Stage 1 dataset statistics:
```
# Stats for output/oasst_pre10_min25_llama2
## Stats for 'Subset of InstructionDataset (megacode2)' (466364 samples (50.0%))
-----------------
Accepted: 398223/466364 (85.4%)
Accepted tokens: 167676873
Skipped: 68141 (14.6%)
Min tokens per sample: 36
Max tokens per sample: 11810
Avg tokens per sample: 421.063
-----------------
## Stats for 'Subset of OrcaChat (orca-chat)' (325616 samples (100.0%))
-----------------
Accepted: 325616/325616 (100.0%)
Accepted tokens: 178307574
Skipped: 0 (0.0%)
Min tokens per sample: 105
Max tokens per sample: 10408
Avg tokens per sample: 547.601
-----------------
## Stats for 'Subset of Dolly15kMultilingual' (57020 samples (100.0%))
-----------------
Accepted: 47494/57020 (83.3%)
Accepted tokens: 13883177
Skipped: 9526 (16.7%)
Min tokens per sample: 34
Max tokens per sample: 9172
Avg tokens per sample: 292.314
-----------------
## Stats for 'Subset of InstructionDataset (oa_leet10k)' (22236 samples (100.0%))
-----------------
Accepted: 22236/22236 (100.0%)
Accepted tokens: 15905296
Skipped: 0 (0.0%)
Min tokens per sample: 168
Max tokens per sample: 10588
Avg tokens per sample: 715.295
-----------------
## Stats for 'total' (871236 samples (100.0%))
-----------------
Accepted: 793569/871236 (91.1%)
Accepted tokens: 375772920
Skipped: 77667 (8.9%)
Min tokens per sample: 34
Max tokens per sample: 11810
Avg tokens per sample: 473.523
-----------------
```
### Stage 2 Pretokenizer Configuration
```
oasst_top1:
datasets:
- oasst_export:
lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk"
input_file_path: 2023-07-23_oasst_ready.tar.gz
top_k: 1
val_split: 0.05
output_dir: "output/oasst_top1_2023-07-23"
filename_prefix: "oasst_top1"
```
Stage 2 dataset statistics:
```
# Stats for output/oasst_top1_2023-07-23_llama2
## Stats for 'ListDataset' (11441 samples (100.0%))
-----------------
Accepted: 11441/11441 (100.0%)
Accepted tokens: 5315368
Skipped: 0 (0.0%)
Min tokens per sample: 20
Max tokens per sample: 5407
Avg tokens per sample: 464.58945896337735
-----------------
## Stats for 'total' (11441 samples (100.0%))
-----------------
Accepted: 11441/11441 (100.0%)
Accepted tokens: 5315368
Skipped: 0 (0.0%)
Min tokens per sample: 20
Max tokens per sample: 5407
Avg tokens per sample: 464.58945896337735
-----------------
```
### Megatron Fine-Tuning Arguments for Stage 1 (Instruction Tuning):
```
--tensor_model_parallel_size 8
--pipeline_model_parallel_size 4
--load ./checkpoints/llama2-70b-tp8-pp4
--save ./checkpoints/llama2-70b-tp8-pp4-oasst_pre10
--tensorboard_dir ./checkpoints/llama2-70b-tp8-pp4-oasst_pre10/logging
--data_path ./data/oasst_pre10_min25_llama2/oasst_sft10-train
--model_name llama2
--tokenizer_type SentencePieceTokenizer
--bf16
--global_batch_size 64
--micro_batch_size 2
--vocab_file=./llama2/Llama-2-7b/tokenizer.model
--use_rms_norm
--glu_activation swiglu
--no_tie_embed_logits
--vocab_extra_ids_list "\"<|im_start|>,<|im_end|>\""
--layernorm_epsilon 1e-5
--use_flash_attn
--no_bias_gelu_fusion
--seq_length 4096
--max_position_embeddings 4096
--log_interval 1
--save_interval 500
--eval_interval 50
--eval_iters 10
--hidden_dropout 0.0
--position_embedding_type rotary
--no_bias_dropout_fusion
--use_checkpoint_args
--train_iters 12000
--attention_dropout 0.0
--adam_beta1 0.9
--adam_beta2 0.95
--adam_eps 1e-12
--lr_decay_style cosine
--lr_warmup_iters 100
--lr 1e-5
--min_lr 1e-6
--weight_decay 0.000001
--sequence_parallel
--recompute_granularity selective
--log_timers_to_tensorboard
--rope_scaling_factor 1.0
--wandb_logger
```
### Megatron Fine-Tuning Arguments for Stage 2 (OASST Polishing, LIMA Dropout):
```
--tensor_model_parallel_size 8
--pipeline_model_parallel_size 4
--load ./checkpoints/llama2-70b-tp8-pp4-oasst_pre10
--save ./checkpoints/llama2-70b-tp8-pp4-oasst_sft10
--tensorboard_dir ./checkpoints/llama2-70b-tp8-pp4-oasst_sft10/logging
--data_path ./data/oasst_top1_2023-07-23_llama2/oasst_top1-train
--model_name llama2
--tokenizer_type SentencePieceTokenizer
--bf16
--global_batch_size 64
--micro_batch_size 2
--vocab_file=./llama2/Llama-2-7b/tokenizer.model
--use_rms_norm
--glu_activation swiglu
--no_tie_embed_logits
--vocab_extra_ids_list "\"<|im_start|>,<|im_end|>\""
--layernorm_epsilon 1e-5
--use_flash_attn
--no_bias_gelu_fusion
--seq_length 4096
--max_position_embeddings 4096
--log_interval 1
--save_interval 346
--eval_interval 50
--eval_iters 10
--hidden_dropout 0.25
--lima_dropout
--position_embedding_type rotary
--no_bias_dropout_fusion
--use_checkpoint_args
--train_iters 519
--attention_dropout 0.0
--adam_beta1 0.9
--adam_beta2 0.95
--adam_eps 1e-12
--lr_decay_style cosine
--lr_warmup_iters 100
--lr 1e-5
--min_lr 1e-6
--weight_decay 0.000001
--sequence_parallel
--recompute_granularity selective
--log_timers_to_tensorboard
--rope_scaling_factor 1.0
--finetune
--wandb_logger
``` |
scenario-labs/Realistic_Vision_V5.1_noVAE | scenario-labs | "2024-05-23T14:08:15Z" | 1,953 | 0 | diffusers | [
"diffusers",
"safetensors",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2024-05-23T14:08:15Z" | ---
license: creativeml-openrail-m
---
This model is a fork from [Realistic_Vision_V5.1_noVAE](https://huggingface.co/SG161222/Realistic_Vision_V5.1_noVAE)
|
MaziyarPanahi/mergekit-ties-polycrr-GGUF | MaziyarPanahi | "2024-06-16T16:12:49Z" | 1,953 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"arxiv:2306.01708",
"base_model:microsoft/Orca-2-7b",
"base_model:arcee-ai/Patent-Instruct-7b",
"base_model:NousResearch/Llama-2-7b-hf",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us",
"base_model:mergekit-community/mergekit-ties-polycrr"
] | text-generation | "2024-06-16T15:52:25Z" | ---
tags:
- quantized
- 2-bit
- 3-bit
- 4-bit
- 5-bit
- 6-bit
- 8-bit
- GGUF
- transformers
- safetensors
- llama
- text-generation
- mergekit
- merge
- arxiv:2306.01708
- base_model:microsoft/Orca-2-7b
- base_model:arcee-ai/Patent-Instruct-7b
- base_model:NousResearch/Llama-2-7b-hf
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- region:us
- text-generation
model_name: mergekit-ties-polycrr-GGUF
base_model: mergekit-community/mergekit-ties-polycrr
inference: false
model_creator: mergekit-community
pipeline_tag: text-generation
quantized_by: MaziyarPanahi
---
# [MaziyarPanahi/mergekit-ties-polycrr-GGUF](https://huggingface.co/MaziyarPanahi/mergekit-ties-polycrr-GGUF)
- Model creator: [mergekit-community](https://huggingface.co/mergekit-community)
- Original model: [mergekit-community/mergekit-ties-polycrr](https://huggingface.co/mergekit-community/mergekit-ties-polycrr)
## Description
[MaziyarPanahi/mergekit-ties-polycrr-GGUF](https://huggingface.co/MaziyarPanahi/mergekit-ties-polycrr-GGUF) contains GGUF format model files for [mergekit-community/mergekit-ties-polycrr](https://huggingface.co/mergekit-community/mergekit-ties-polycrr).
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible. |
ydshieh/wav2vec2-large-xlsr-53-chinese-zh-cn-gpt | ydshieh | "2021-04-01T14:09:29Z" | 1,952 | 31 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"audio",
"speech",
"xlsr-fine-tuning-week",
"zh",
"dataset:common_voice",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | automatic-speech-recognition | "2022-03-02T23:29:05Z" | ---
language: zh
datasets:
- common_voice
metrics:
- cer
tags:
- audio
- automatic-speech-recognition
- speech
- xlsr-fine-tuning-week
license: apache-2.0
model-index:
- name: XLSR Wav2Vec2 Large 53 - Chinese (zh-CN), by Yih-Dar SHIEH
results:
- task:
name: Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice zh-CN
type: common_voice
args: zh-CN
metrics:
- name: Test CER
type: cer
value: 20.90
---
# Wav2Vec2-Large-XLSR-53-Chinese-zh-cn-gpt
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Chinese (zh-CN) using the [Common Voice](https://huggingface.co/datasets/common_voice), included [Common Voice](https://huggingface.co/datasets/common_voice) Chinese (zh-TW) dataset (converting the label text to simplified Chinese).
When using this model, make sure that your speech input is sampled at 16kHz.
## Usage
The model can be used directly (without a language model) as follows:
```python
import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
test_dataset = load_dataset("common_voice", "zh-CN", split="test")
processor = Wav2Vec2Processor.from_pretrained("ydshieh/wav2vec2-large-xlsr-53-chinese-zh-cn-gpt")
model = Wav2Vec2ForCTC.from_pretrained("ydshieh/wav2vec2-large-xlsr-53-chinese-zh-cn-gpt")
resampler = torchaudio.transforms.Resample(48_000, 16_000)
# Preprocessing the datasets.
# We need to read the aduio files as arrays
def speech_file_to_array_fn(batch):
speech_array, sampling_rate = torchaudio.load(batch["path"])
batch["speech"] = resampler(speech_array).squeeze().numpy()
return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset[:2]["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
predicted_ids = torch.argmax(logits, dim=-1)
print("Prediction:", processor.batch_decode(predicted_ids))
print("Reference:", test_dataset[:2]["sentence"])
```
## Evaluation
The model can be evaluated as follows on the zh-CN test data of Common Voice.
Original CER calculation refer to https://huggingface.co/ctl/wav2vec2-large-xlsr-cantonese
```python
#!pip install datasets==1.4.1
#!pip install transformers==4.4.0
#!pip install torchaudio
#!pip install jiwer
import torch
import torchaudio
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import re
import jiwer
def chunked_cer(targets, predictions, chunk_size=None):
_predictions = [char for seq in predictions for char in list(seq)]
_targets = [char for seq in targets for char in list(seq)]
if chunk_size is None: return jiwer.wer(_targets, _predictions)
start = 0
end = chunk_size
H, S, D, I = 0, 0, 0, 0
while start < len(targets):
_predictions = [char for seq in predictions[start:end] for char in list(seq)]
_targets = [char for seq in targets[start:end] for char in list(seq)]
chunk_metrics = jiwer.compute_measures(_targets, _predictions)
H = H + chunk_metrics["hits"]
S = S + chunk_metrics["substitutions"]
D = D + chunk_metrics["deletions"]
I = I + chunk_metrics["insertions"]
start += chunk_size
end += chunk_size
return float(S + D + I) / float(H + S + D)
test_dataset = load_dataset("common_voice", "zh-CN", split="test")
processor = Wav2Vec2Processor.from_pretrained("ydshieh/wav2vec2-large-xlsr-53-chinese-zh-cn-gpt")
model = Wav2Vec2ForCTC.from_pretrained("ydshieh/wav2vec2-large-xlsr-53-chinese-zh-cn-gpt")
model.to("cuda")
chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\:"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\�\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\．\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\⋯\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\！\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\－\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\：\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\–\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\。\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\》\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\）\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\？\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\；\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\～\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\~\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\…\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\︰\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\，\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\（\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\」\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\‧\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\《\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\﹔\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\、\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\—\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\／\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\「\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\﹖\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\·\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\×\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\̃\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\̌\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ε\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\λ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\μ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\и\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\т\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\─\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\□\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\〈\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\〉\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\『\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\』\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ア\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\オ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\カ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\チ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ド\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ベ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ャ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ヤ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ン\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\・\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\丶\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ａ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ｂ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ｆ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ｇ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ｉ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ｎ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ｐ\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ｔ' + "\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\']"
resampler = torchaudio.transforms.Resample(48_000, 16_000)
# Preprocessing the datasets.
# We need to read the aduio files as arrays
def speech_file_to_array_fn(batch):
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower().replace("’", "'") + " "
speech_array, sampling_rate = torchaudio.load(batch["path"])
batch["speech"] = resampler(speech_array).squeeze().numpy()
return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
# Preprocessing the datasets.
# We need to read the aduio files as arrays
def evaluate(batch):
inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
pred_ids = torch.argmax(logits, dim=-1)
batch["pred_strings"] = processor.batch_decode(pred_ids)
return batch
result = test_dataset.map(evaluate, batched=True, batch_size=8)
print("CER: {:2f}".format(100 * chunked_cer(predictions=result["pred_strings"], targets=result["sentence"], chunk_size=1000)))
```
**Test Result**: 20.902244 %
## Training
The Common Voice zh-CN `train`, `validation` were used for training, as well as Common Voice zh-TW `train`, `validation` and `test` datasets.
The script used for training can be found [to be uploaded later](...) |
aiplanet/effi-13b | aiplanet | "2023-08-20T04:16:56Z" | 1,952 | 10 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:kaist-ai/CoT-Collection",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-18T13:59:35Z" | ---
license: apache-2.0
datasets:
- kaist-ai/CoT-Collection
metrics:
- accuracy
pipeline_tag: text-generation
---
# Model card for aiplanet/effi-13b
effi-13B parameters is a causal decoder-only model built by AI Planet based on Llama-2-13b-chat-hf and fine tuned using the 1.8 Million coversations from CoT dataset available in huggingface datasets. The model is made available under the Apache 2.0 license.
## Why use effi-13B-Instruct?
- This is a ready to use chat/instruct model based on Llama-2-13b-chat-hf, which provides a rationale for the context provided.
- Llama-2 is the best open-source model available. This is an instruct model, which may not be ideal for further finetuning. If you are interested in building your own instruct/chat model, we recommend starting from **Llama-2-13b-chat-hf**
You will need at least **85-100GB of memory to swiftly run inference with effi-13b**.
## Model Details
### Model Description
This model has been fine-tuned on Chain of Thought datasets, which has context from mixed sources with corresponding rationale. The final finetuned Large Language Model(LLM) have shown enhanced capabilities of solving novel tasks by providing a reasoning.
- **Developed by:** AI Planet
- **Model type:** Casual Decoder only
- **Language(s) (NLP):** English
- **License:** Apache 2.0
- **Finetuned from model:** Llama-2-13b-chat-hf
### Direct Use
effi-13b has been finetuned on a Chain of Thought dataset.
### Out-of-Scope Use
Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.
## Bias, Risks, and Limitations
This model has been majorly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
### Recommendations
We recommend users of effi-13b to develop guardrails and take appropriate precautions for any production use.
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information is needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
```
from transformers import (AutoModelForCausalLM, AutoTokenizer, pipeline)
model_card = "aiplanet/effi-13b"
#
model = AutoModelForCausalLM.from_pretrained(model_card)
tokenizer = AutoTokenizer.from_pretrained(model_card)
#
generate_text = transformers.pipeline(
model=model, tokenizer=tokenizer,
return_full_text=True, # langchain expects the full text
task='text-generation',
# we pass model parameters here too
temperature=0.4, # 'randomness' of outputs, 0.0 is the min and 1.0 the max
max_new_tokens=512, # mex number of tokens to generate in the output
repetition_penalty=1.1 # without this output begins repeating
)
#
promt = """
Can you explain this code in detail?
def generate_stream(tokenizer, model, params, device,
context_len=2048, stream_interval=2):
prompt = params["prompt"]
l_prompt = len(prompt)
temperature = float(params.get("temperature", 1.0))
max_new_tokens = int(params.get("max_new_tokens", 256))
stop_str = params.get("stop", None)
input_ids = tokenizer(prompt).input_ids
output_ids = list(input_ids)
max_src_len = context_len - max_new_tokens - 8
input_ids = input_ids[-max_src_len:]
for i in range(max_new_tokens):
if i == 0:
out = model(
torch.as_tensor([input_ids], device=device), use_cache=True)
logits = out.logits
past_key_values = out.past_key_values
else:
attention_mask = torch.ones(
1, past_key_values[0][0].shape[-2] + 1, device=device)
out = model(input_ids=torch.as_tensor([[token]], device=device),
use_cache=True,
attention_mask=attention_mask,
past_key_values=past_key_values)
logits = out.logits
past_key_values = out.past_key_values
last_token_logits = logits[0][-1]
if device == "mps":
# Switch to CPU by avoiding some bugs in mps backend.
last_token_logits = last_token_logits.float().to("cpu")
if temperature < 1e-4:
token = int(torch.argmax(last_token_logits))
else:
probs = torch.softmax(last_token_logits / temperature, dim=-1)
token = int(torch.multinomial(probs, num_samples=1))
output_ids.append(token)
if token == tokenizer.eos_token_id:
stopped = True
else:
stopped = False
if i % stream_interval == 0 or i == max_new_tokens - 1 or stopped:
output = tokenizer.decode(output_ids, skip_special_tokens=True)
pos = output.rfind(stop_str, l_prompt)
if pos != -1:
output = output[:pos]
stopped = True
yield output
if stopped:
break
del past_key_values
"""
#
system_message = "Given your chain of thought reasoning, provide a rationale for the context in the source."
prompt = f"[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n{prompt}. [/INST]" # replace the command here with something relevant to your task
#
result = generate_text(prompt)
print(result[0]['generated_text'].strip().split("[/INST]")[-1])
```
## Training Details
### Training Data
effi-13b has been finetuned on https://huggingface.co/datasets/kaist-ai/CoT-Collection
The data was tokenized with the **meta-llama/Llama-2-13b-chat-hf** tokenizer.
### Training Procedure
Fine-tuning approach using PefT and Qlora(https://huggingface.co/blog/4bit-transformers-bitsandbytes)
#### Training Hyperparameters
- **Training regime:**
- lora_alpha=32,
- lora_dropout=0.05,
- r=8,
- bias="none",
- task_type="CAUSAL_LM"
#
- load_in_4bit=True,
- bnb_4bit_quant_type = "nf4",
- bnb_4bit_use_double_quant=True,
- bnb_4bit_compute_dtype=torch.bfloat16
#
- num_train_epochs = 1
- fp16 = False
- bf16 = False
- per_device_train_batch_size = 1
- per_device_eval_batch_size = 1
- gradient_accumulation_steps = 4
- gradient_checkpointing = True
- max_grad_norm = 0.3
- learning_rate = 2e-4
- weight_decay = 0.001
- optim = "paged_adamw_32bit"
- lr_scheduler_type = "constant"
- max_steps = 500
- warmup_ratio = 0.03
- group_by_length = True
- save_steps = 25
- logging_steps = 5
- max_seq_length = 2048
- packing = False
- device_map = {"": 0}
## Evaluation
Paper coming soon.
See the OpenLLM Leaderboard(https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) for early results.
## Citation
@article{effi-13b,
title={{effi-13b}: an open large language model with state-of-the-art performance},
author={aiplanet},
year={2023}
}
## Model Card Contact
[email protected]
|
bigscience/bloomz-1b1 | bigscience | "2023-05-27T17:26:45Z" | 1,951 | 31 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"bloom",
"text-generation",
"ak",
"ar",
"as",
"bm",
"bn",
"ca",
"code",
"en",
"es",
"eu",
"fon",
"fr",
"gu",
"hi",
"id",
"ig",
"ki",
"kn",
"lg",
"ln",
"ml",
"mr",
"ne",
"nso",
"ny",
"or",
"pa",
"pt",
"rn",
"rw",
"sn",
"st",
"sw",
"ta",
"te",
"tn",
"ts",
"tum",
"tw",
"ur",
"vi",
"wo",
"xh",
"yo",
"zh",
"zu",
"dataset:bigscience/xP3",
"arxiv:2211.01786",
"license:bigscience-bloom-rail-1.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-10-08T16:16:01Z" | ---
datasets:
- bigscience/xP3
license: bigscience-bloom-rail-1.0
language:
- ak
- ar
- as
- bm
- bn
- ca
- code
- en
- es
- eu
- fon
- fr
- gu
- hi
- id
- ig
- ki
- kn
- lg
- ln
- ml
- mr
- ne
- nso
- ny
- or
- pa
- pt
- rn
- rw
- sn
- st
- sw
- ta
- te
- tn
- ts
- tum
- tw
- ur
- vi
- wo
- xh
- yo
- zh
- zu
programming_language:
- C
- C++
- C#
- Go
- Java
- JavaScript
- Lua
- PHP
- Python
- Ruby
- Rust
- Scala
- TypeScript
pipeline_tag: text-generation
widget:
- text: "一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。Would you rate the previous review as positive, neutral or negative?"
example_title: "zh-en sentiment"
- text: "一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评？"
example_title: "zh-zh sentiment"
- text: "Suggest at least five related search terms to \"Mạng neural nhân tạo\"."
example_title: "vi-en query"
- text: "Proposez au moins cinq mots clés concernant «Réseau de neurones artificiels»."
example_title: "fr-fr query"
- text: "Explain in a sentence in Telugu what is backpropagation in neural networks."
example_title: "te-en qa"
- text: "Why is the sky blue?"
example_title: "en-en qa"
- text: "Write a fairy tale about a troll saving a princess from a dangerous dragon. The fairy tale is a masterpiece that has achieved praise worldwide and its moral is \"Heroes Come in All Shapes and Sizes\". Story (in Spanish):"
example_title: "es-en fable"
- text: "Write a fable about wood elves living in a forest that is suddenly invaded by ogres. The fable is a masterpiece that has achieved praise worldwide and its moral is \"Violence is the last refuge of the incompetent\". Fable (in Hindi):"
example_title: "hi-en fable"
model-index:
- name: bloomz-1b1
results:
- task:
type: Coreference resolution
dataset:
type: winogrande
name: Winogrande XL (xl)
config: xl
split: validation
revision: a80f460359d1e9a67c006011c94de42a8759430c
metrics:
- type: Accuracy
value: 52.33
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (en)
config: en
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 50.49
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (fr)
config: fr
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 59.04
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (jp)
config: jp
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 51.82
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (pt)
config: pt
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 54.75
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (ru)
config: ru
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 53.97
- task:
type: Coreference resolution
dataset:
type: Muennighoff/xwinograd
name: XWinograd (zh)
config: zh
split: test
revision: 9dd5ea5505fad86b7bedad667955577815300cee
metrics:
- type: Accuracy
value: 55.16
- task:
type: Natural language inference
dataset:
type: anli
name: ANLI (r1)
config: r1
split: validation
revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
metrics:
- type: Accuracy
value: 33.3
- task:
type: Natural language inference
dataset:
type: anli
name: ANLI (r2)
config: r2
split: validation
revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
metrics:
- type: Accuracy
value: 33.5
- task:
type: Natural language inference
dataset:
type: anli
name: ANLI (r3)
config: r3
split: validation
revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
metrics:
- type: Accuracy
value: 34.5
- task:
type: Natural language inference
dataset:
type: super_glue
name: SuperGLUE (cb)
config: cb
split: validation
revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
metrics:
- type: Accuracy
value: 58.93
- task:
type: Natural language inference
dataset:
type: super_glue
name: SuperGLUE (rte)
config: rte
split: validation
revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
metrics:
- type: Accuracy
value: 65.7
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (ar)
config: ar
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 46.59
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (bg)
config: bg
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 40.4
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (de)
config: de
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 40.12
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (el)
config: el
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 39.32
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (en)
config: en
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 47.11
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (es)
config: es
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 47.55
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (fr)
config: fr
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 48.51
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (hi)
config: hi
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 42.89
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (ru)
config: ru
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 42.81
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (sw)
config: sw
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 41.29
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (th)
config: th
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 42.93
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (tr)
config: tr
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 37.51
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (ur)
config: ur
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 41.37
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (vi)
config: vi
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 47.19
- task:
type: Natural language inference
dataset:
type: xnli
name: XNLI (zh)
config: zh
split: validation
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
metrics:
- type: Accuracy
value: 47.63
- task:
type: Program synthesis
dataset:
type: openai_humaneval
name: HumanEval
config: None
split: test
revision: e8dc562f5de170c54b5481011dd9f4fa04845771
metrics:
- type: Pass@1
value: 2.62
- type: Pass@10
value: 6.22
- type: Pass@100
value: 11.68
- task:
type: Sentence completion
dataset:
type: story_cloze
name: StoryCloze (2016)
config: "2016"
split: validation
revision: e724c6f8cdf7c7a2fb229d862226e15b023ee4db
metrics:
- type: Accuracy
value: 62.75
- task:
type: Sentence completion
dataset:
type: super_glue
name: SuperGLUE (copa)
config: copa
split: validation
revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
metrics:
- type: Accuracy
value: 63.0
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (et)
config: et
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 55.0
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (ht)
config: ht
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 52.0
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (id)
config: id
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 60.0
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (it)
config: it
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 56.0
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (qu)
config: qu
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 56.0
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (sw)
config: sw
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 64.0
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (ta)
config: ta
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 57.0
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (th)
config: th
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 59.0
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (tr)
config: tr
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 55.0
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (vi)
config: vi
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 63.0
- task:
type: Sentence completion
dataset:
type: xcopa
name: XCOPA (zh)
config: zh
split: validation
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
metrics:
- type: Accuracy
value: 61.0
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (ar)
config: ar
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 53.54
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (es)
config: es
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 58.37
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (eu)
config: eu
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 52.35
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (hi)
config: hi
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 55.92
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (id)
config: id
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 57.97
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (my)
config: my
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 47.05
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (ru)
config: ru
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 50.3
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (sw)
config: sw
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 49.97
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (te)
config: te
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 55.86
- task:
type: Sentence completion
dataset:
type: Muennighoff/xstory_cloze
name: XStoryCloze (zh)
config: zh
split: validation
revision: 8bb76e594b68147f1a430e86829d07189622b90d
metrics:
- type: Accuracy
value: 58.17
---
# Table of Contents
1. [Model Summary](#model-summary)
2. [Use](#use)
3. [Limitations](#limitations)
4. [Training](#training)
5. [Evaluation](#evaluation)
7. [Citation](#citation)
# Model Summary
> We present BLOOMZ & mT0, a family of models capable of following human instructions in dozens of languages zero-shot. We finetune BLOOM & mT5 pretrained multilingual language models on our crosslingual task mixture (xP3) and find the resulting models capable of crosslingual generalization to unseen tasks & languages.
- **Repository:** [bigscience-workshop/xmtf](https://github.com/bigscience-workshop/xmtf)
- **Paper:** [Crosslingual Generalization through Multitask Finetuning](https://arxiv.org/abs/2211.01786)
- **Point of Contact:** [Niklas Muennighoff](mailto:[email protected])
- **Languages:** Refer to [bloom](https://huggingface.co/bigscience/bloom) for pretraining & [xP3](https://huggingface.co/datasets/bigscience/xP3) for finetuning language proportions. It understands both pretraining & finetuning languages.
- **BLOOMZ & mT0 Model Family:**
<div class="max-w-full overflow-auto">
<table>
<tr>
<th colspan="12">Multitask finetuned on <a style="font-weight:bold" href=https://huggingface.co/datasets/bigscience/xP3>xP3</a>. Recommended for prompting in English.
</tr>
<tr>
<td>Parameters</td>
<td>300M</td>
<td>580M</td>
<td>1.2B</td>
<td>3.7B</td>
<td>13B</td>
<td>560M</td>
<td>1.1B</td>
<td>1.7B</td>
<td>3B</td>
<td>7.1B</td>
<td>176B</td>
</tr>
<tr>
<td>Finetuned Model</td>
<td><a href=https://huggingface.co/bigscience/mt0-small>mt0-small</a></td>
<td><a href=https://huggingface.co/bigscience/mt0-base>mt0-base</a></td>
<td><a href=https://huggingface.co/bigscience/mt0-large>mt0-large</a></td>
<td><a href=https://huggingface.co/bigscience/mt0-xl>mt0-xl</a></td>
<td><a href=https://huggingface.co/bigscience/mt0-xxl>mt0-xxl</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-560m>bloomz-560m</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-1b1>bloomz-1b1</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-1b7>bloomz-1b7</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-3b>bloomz-3b</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-7b1>bloomz-7b1</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz>bloomz</a></td>
</tr>
</tr>
<tr>
<th colspan="12">Multitask finetuned on <a style="font-weight:bold" href=https://huggingface.co/datasets/bigscience/xP3mt>xP3mt</a>. Recommended for prompting in non-English.</th>
</tr>
<tr>
<td>Finetuned Model</td>
<td></td>
<td></td>
<td></td>
<td></td>
<td><a href=https://huggingface.co/bigscience/mt0-xxl-mt>mt0-xxl-mt</a></td>
<td></td>
<td></td>
<td></td>
<td></td>
<td><a href=https://huggingface.co/bigscience/bloomz-7b1-mt>bloomz-7b1-mt</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-mt>bloomz-mt</a></td>
</tr>
<th colspan="12">Multitask finetuned on <a style="font-weight:bold" href=https://huggingface.co/datasets/Muennighoff/P3>P3</a>. Released for research purposes only. Strictly inferior to above models!</th>
</tr>
<tr>
<td>Finetuned Model</td>
<td></td>
<td></td>
<td></td>
<td></td>
<td><a href=https://huggingface.co/bigscience/mt0-xxl-p3>mt0-xxl-p3</a></td>
<td></td>
<td></td>
<td></td>
<td></td>
<td><a href=https://huggingface.co/bigscience/bloomz-7b1-p3>bloomz-7b1-p3</a></td>
<td><a href=https://huggingface.co/bigscience/bloomz-p3>bloomz-p3</a></td>
</tr>
<th colspan="12">Original pretrained checkpoints. Not recommended.</th>
<tr>
<td>Pretrained Model</td>
<td><a href=https://huggingface.co/google/mt5-small>mt5-small</a></td>
<td><a href=https://huggingface.co/google/mt5-base>mt5-base</a></td>
<td><a href=https://huggingface.co/google/mt5-large>mt5-large</a></td>
<td><a href=https://huggingface.co/google/mt5-xl>mt5-xl</a></td>
<td><a href=https://huggingface.co/google/mt5-xxl>mt5-xxl</a></td>
<td><a href=https://huggingface.co/bigscience/bloom-560m>bloom-560m</a></td>
<td><a href=https://huggingface.co/bigscience/bloom-1b1>bloom-1b1</a></td>
<td><a href=https://huggingface.co/bigscience/bloom-1b7>bloom-1b7</a></td>
<td><a href=https://huggingface.co/bigscience/bloom-3b>bloom-3b</a></td>
<td><a href=https://huggingface.co/bigscience/bloom-7b1>bloom-7b1</a></td>
<td><a href=https://huggingface.co/bigscience/bloom>bloom</a></td>
</tr>
</table>
</div>
# Use
## Intended use
We recommend using the model to perform tasks expressed in natural language. For example, given the prompt "*Translate to English: Je t’aime.*", the model will most likely answer "*I love you.*". Some prompt ideas from our paper:
- 一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评?
- Suggest at least five related search terms to "Mạng neural nhân tạo".
- Write a fairy tale about a troll saving a princess from a dangerous dragon. The fairy tale is a masterpiece that has achieved praise worldwide and its moral is "Heroes Come in All Shapes and Sizes". Story (in Spanish):
- Explain in a sentence in Telugu what is backpropagation in neural networks.
**Feel free to share your generations in the Community tab!**
## How to use
### CPU
<details>
<summary> Click to expand </summary>
```python
# pip install -q transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "bigscience/bloomz-1b1"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint)
inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt")
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
</details>
### GPU
<details>
<summary> Click to expand </summary>
```python
# pip install -q transformers accelerate
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "bigscience/bloomz-1b1"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint, torch_dtype="auto", device_map="auto")
inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt").to("cuda")
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
</details>
### GPU in 8bit
<details>
<summary> Click to expand </summary>
```python
# pip install -q transformers accelerate bitsandbytes
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "bigscience/bloomz-1b1"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto", load_in_8bit=True)
inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt").to("cuda")
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
</details>
<!-- Necessary for whitespace -->
###
# Limitations
**Prompt Engineering:** The performance may vary depending on the prompt. For BLOOMZ models, we recommend making it very clear when the input stops to avoid the model trying to continue it. For example, the prompt "*Translate to English: Je t'aime*" without the full stop (.) at the end, may result in the model trying to continue the French sentence. Better prompts are e.g. "*Translate to English: Je t'aime.*", "*Translate to English: Je t'aime. Translation:*" "*What is "Je t'aime." in English?*", where it is clear for the model when it should answer. Further, we recommend providing the model as much context as possible. For example, if you want it to answer in Telugu, then tell the model, e.g. "*Explain in a sentence in Telugu what is backpropagation in neural networks.*".
# Training
## Model
- **Architecture:** Same as [bloom-1b1](https://huggingface.co/bigscience/bloom-1b1), also refer to the `config.json` file
- **Finetuning steps:** 250
- **Finetuning tokens:** 502 million
- **Finetuning layout:** 1x pipeline parallel, 1x tensor parallel, 1x data parallel
- **Precision:** float16
## Hardware
- **CPUs:** AMD CPUs with 512GB memory per node
- **GPUs:** 64 A100 80GB GPUs with 8 GPUs per node (8 nodes) using NVLink 4 inter-gpu connects, 4 OmniPath links
- **Communication:** NCCL-communications network with a fully dedicated subnet
## Software
- **Orchestration:** [Megatron-DeepSpeed](https://github.com/bigscience-workshop/Megatron-DeepSpeed)
- **Optimizer & parallelism:** [DeepSpeed](https://github.com/microsoft/DeepSpeed)
- **Neural networks:** [PyTorch](https://github.com/pytorch/pytorch) (pytorch-1.11 w/ CUDA-11.5)
- **FP16 if applicable:** [apex](https://github.com/NVIDIA/apex)
# Evaluation
We refer to Table 7 from our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot results on unseen tasks. The sidebar reports zero-shot performance of the best prompt per dataset config.
# Citation
```bibtex
@article{muennighoff2022crosslingual,
title={Crosslingual generalization through multitask finetuning},
author={Muennighoff, Niklas and Wang, Thomas and Sutawika, Lintang and Roberts, Adam and Biderman, Stella and Scao, Teven Le and Bari, M Saiful and Shen, Sheng and Yong, Zheng-Xin and Schoelkopf, Hailey and others},
journal={arXiv preprint arXiv:2211.01786},
year={2022}
}
``` |
ajibawa-2023/carl-33b | ajibawa-2023 | "2023-11-18T05:57:39Z" | 1,951 | 10 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:jerryjalapeno/nart-100k-synthetic",
"license:cc-by-nc-nd-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-15T13:02:21Z" | ---
license: cc-by-nc-nd-4.0
datasets:
- jerryjalapeno/nart-100k-synthetic
language:
- en
---
**Carl: A Therapist AI**
Early prevention can help lot of people to avoid depression and other mental illnesses. Therapy is a controversial use case because the outputs and capabilities of LLMs are uncertain.
Many people don't have access the therapist, due to a financial, personal, social or other restriction.
Here comes Carl: A Therapist AI which can quickly respond to you. It is trained on more than 100000 set of conversations. Each set having 10~15 conversations between Carl and client.
Base data was obtained from jerryjalapeno/nart-100k-synthetic . This data was further refined and fine tuned. Entire dataset is synthetic. Synthetic data is used because there is little to no therapy conversation data which is publicly available and directly applicable to an LLM.
This by means a no replacement to a Doctor or professional therapist. If you are in stress or going through a tough time, please seek professional help or talk to a friend/family member.
**Training:**
Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 75 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.
**GPTQ & GGML**
GPTQ: [TheBloke](https://huggingface.co/TheBloke/Carl-33B-GPTQ)
GGML: [TheBloke](https://huggingface.co/TheBloke/Carl-13B-GGML)
Special Thanks to [TheBloke](https://huggingface.co/TheBloke) for guiding me and making these models available.
**Example Prompt:**
```
This is a conversation with your Therapist AI, Carl. Carl is designed to help you while in stress. It can answer your questions and help you to calm down
Context
You are Carl, A Therapist AI
USER: <prompt>
CARL:
```
Note:
This is just a research experiment, and the model should NOT be used as a human therapist. Use "cat" command to join all pytorch_model.bin parts.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ajibawa-2023__carl-33b)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 55.01 |
| ARC (25-shot) | 64.59 |
| HellaSwag (10-shot) | 85.27 |
| MMLU (5-shot) | 58.38 |
| TruthfulQA (0-shot) | 45.32 |
| Winogrande (5-shot) | 76.24 |
| GSM8K (5-shot) | 6.37 |
| DROP (3-shot) | 48.92 |
|
nvidia/stt_en_conformer_ctc_large | nvidia | "2022-10-28T23:33:45Z" | 1,950 | 23 | nemo | [
"nemo",
"automatic-speech-recognition",
"speech",
"audio",
"CTC",
"Conformer",
"Transformer",
"pytorch",
"NeMo",
"hf-asr-leaderboard",
"Riva",
"en",
"arxiv:2005.08100",
"license:cc-by-4.0",
"model-index",
"region:us"
] | automatic-speech-recognition | "2022-04-09T03:43:21Z" | ---
language:
- en
library_name: nemo
datasets:
- librispeech_asr
- fisher_corpus
- Switchboard-1
- WSJ-0
- WSJ-1
- National-Singapore-Corpus-Part-1
- National-Singapore-Corpus-Part-6
- vctk
- VoxPopuli-(EN)
- Europarl-ASR-(EN)
- Multilingual-LibriSpeech-(2000-hours)
- mozilla-foundation/common_voice_7_0
thumbnail: null
tags:
- automatic-speech-recognition
- speech
- audio
- CTC
- Conformer
- Transformer
- pytorch
- NeMo
- hf-asr-leaderboard
- Riva
license: cc-by-4.0
widget:
- example_title: Librispeech sample 1
src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
- example_title: Librispeech sample 2
src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
model-index:
- name: stt_en_conformer_ctc_large
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: LibriSpeech (clean)
type: librispeech_asr
config: clean
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 2.2
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: LibriSpeech (other)
type: librispeech_asr
config: other
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 4.3
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: Multilingual LibriSpeech
type: facebook/multilingual_librispeech
config: english
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 7.2
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: Mozilla Common Voice 7.0
type: mozilla-foundation/common_voice_7_0
config: en
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 8.0
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: Mozilla Common Voice 8.0
type: mozilla-foundation/common_voice_8_0
config: en
split: test
args:
language: en
metrics:
- name: Test WER
type: wer
value: 9.48
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: Wall Street Journal 92
type: wsj_0
args:
language: en
metrics:
- name: Test WER
type: wer
value: 2.0
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: Wall Street Journal 93
type: wsj_1
args:
language: en
metrics:
- name: Test WER
type: wer
value: 2.9
- task:
type: Automatic Speech Recognition
name: automatic-speech-recognition
dataset:
name: National Singapore Corpus
type: nsc_part_1
args:
language: en
metrics:
- name: Test WER
type: wer
value: 7.0
---
# NVIDIA Conformer-CTC Large (en-US)
<style>
img {
display: inline;
}
</style>
| [](#model-architecture)
| [](#model-architecture)
| [](#datasets)
| [](#deployment-with-nvidia-riva) |
This model transcribes speech in lowercase English alphabet including spaces and apostrophes, and is trained on several thousand hours of English speech data.
It is a non-autoregressive "large" variant of Conformer, with around 120 million parameters.
See the [model architecture](#model-architecture) section and [NeMo documentation](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#conformer-ctc) for complete architecture details.
It is also compatible with NVIDIA Riva for [production-grade server deployments](#deployment-with-nvidia-riva).
## Usage
The model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.
To train, fine-tune or play with the model you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed latest PyTorch version.
```
pip install nemo_toolkit['all']
```
### Automatically instantiate the model
```python
import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecCTCModelBPE.from_pretrained("nvidia/stt_en_conformer_ctc_large")
```
### Transcribing using Python
First, let's get a sample
```
wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav
```
Then simply do:
```
asr_model.transcribe(['2086-149220-0033.wav'])
```
### Transcribing many audio files
```shell
python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
pretrained_name="nvidia/stt_en_conformer_ctc_large"
audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
```
### Input
This model accepts 16000 kHz Mono-channel Audio (wav files) as input.
### Output
This model provides transcribed speech as a string for a given audio sample.
## Model Architecture
Conformer-CTC model is a non-autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses CTC loss/decoding instead of Transducer. You may find more info on the detail of this model here: [Conformer-CTC Model](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#conformer-ctc).
## Training
The NeMo toolkit [3] was used for training the models for over several hundred epochs. These model are trained with this [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/asr_ctc/speech_to_text_ctc_bpe.py) and this [base config](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/conf/conformer/conformer_ctc_bpe.yaml).
The tokenizers for these models were built using the text transcripts of the train set with this [script](https://github.com/NVIDIA/NeMo/blob/main/scripts/tokenizers/process_asr_text_tokenizer.py).
The checkpoint of the language model used as the neural rescorer can be found [here](https://ngc.nvidia.com/catalog/models/nvidia:nemo:asrlm_en_transformer_large_ls). You may find more info on how to train and use language models for ASR models here: [ASR Language Modeling](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/asr_language_modeling.html)
### Datasets
All the models in this collection are trained on a composite dataset (NeMo ASRSET) comprising of several thousand hours of English speech:
- Librispeech 960 hours of English speech
- Fisher Corpus
- Switchboard-1 Dataset
- WSJ-0 and WSJ-1
- National Speech Corpus (Part 1, Part 6)
- VCTK
- VoxPopuli (EN)
- Europarl-ASR (EN)
- Multilingual Librispeech (MLS EN) - 2,000 hours subset
- Mozilla Common Voice (v7.0)
Note: older versions of the model may have trained on smaller set of datasets.
## Performance
The list of the available models in this collection is shown in the following table. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.
| Version | Tokenizer | Vocabulary Size | LS test-other | LS test-clean | WSJ Eval92 | WSJ Dev93 | NSC Part 1 | MLS Test | MLS Dev | MCV Test 6.1 |Train Dataset |
|---------|-----------------------|-----------------|---------------|---------------|------------|-----------|-------|------|-----|-------|---------|
| 1.6.0 | SentencePiece Unigram | 128 | 4.3 | 2.2 | 2.0 | 2.9 | 7.0 | 7.2 | 6.5 | 8.0 | NeMo ASRSET 2.0 |
While deploying with [NVIDIA Riva](https://developer.nvidia.com/riva), you can combine this model with external language models to further improve WER. The WER(%) of the latest model with different language modeling techniques are reported in the following table.
| Language Modeling | Training Dataset | LS test-other | LS test-clean | Comment |
|-------------------------------------|-------------------------|---------------|---------------|---------------------------------------------------------|
|N-gram LM | LS Train + LS LM Corpus | 3.5 | 1.8 | N=10, beam_width=128, n_gram_alpha=1.0, n_gram_beta=1.0 |
|Neural Rescorer(Transformer) | LS Train + LS LM Corpus | 3.4 | 1.7 | N=10, beam_width=128 |
|N-gram + Neural Rescorer(Transformer)| LS Train + LS LM Corpus | 3.2 | 1.8 | N=10, beam_width=128, n_gram_alpha=1.0, n_gram_beta=1.0 |
## Limitations
Since this model was trained on publicly available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speech.
## Deployment with NVIDIA Riva
For the best real-time accuracy, latency, and throughput, deploy the model with [NVIDIA Riva](https://developer.nvidia.com/riva), an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, at the edge, and embedded.
Additionally, Riva provides:
* World-class out-of-the-box accuracy for the most common languages with model checkpoints trained on proprietary data with hundreds of thousands of GPU-compute hours
* Best in class accuracy with run-time word boosting (e.g., brand and product names) and customization of acoustic model, language model, and inverse text normalization
* Streaming speech recognition, Kubernetes compatible scaling, and Enterprise-grade support
Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
## References
- [1] [Conformer: Convolution-augmented Transformer for Speech Recognition](https://arxiv.org/abs/2005.08100)
- [2] [Google Sentencepiece Tokenizer](https://github.com/google/sentencepiece)
- [3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo) |
colbert-ir/colbertv1.9 | colbert-ir | "2024-02-02T14:02:12Z" | 1,950 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | "2024-02-02T14:01:20Z" | ---
license: mit
---
|
vuiseng9/ov-gpt2-fp32-kv-cache | vuiseng9 | "2023-06-27T22:01:46Z" | 1,949 | 0 | transformers | [
"transformers",
"pytorch",
"openvino",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:wikitext",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-27T21:58:52Z" | ---
license: mit
tags:
- generated_from_trainer
datasets:
- wikitext
metrics:
- accuracy
model-index:
- name: gpt2-fp32-ov-kv-cache
results:
- task:
name: Causal Language Modeling
type: text-generation
dataset:
name: wikitext wikitext-2-raw-v1
type: wikitext
config: wikitext-2-raw-v1
split: validation
args: wikitext-2-raw-v1
metrics:
- name: Accuracy
type: accuracy
value: 0.38449006190941676
---
<!-- 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. -->
# gpt2-fp32-ov-kv-cache
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the wikitext wikitext-2-raw-v1 dataset.
It achieves the following results on the evaluation set:
- Loss: 3.3894
- Accuracy: 0.3845
## 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: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
|
OpenBuddy/openbuddy-atom-13b-v9-bf16 | OpenBuddy | "2023-08-07T07:36:36Z" | 1,949 | 5 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"zh",
"en",
"fr",
"de",
"ja",
"ko",
"it",
"ru",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-05T12:39:39Z" | ---
language:
- zh
- en
- fr
- de
- ja
- ko
- it
- ru
pipeline_tag: text-generation
inference: false
library_name: transformers
license: apache-2.0
---
# OpenBuddy - Open Multilingual Chatbot
GitHub and Usage Guide: [https://github.com/OpenBuddy/OpenBuddy](https://github.com/OpenBuddy/OpenBuddy)
Website and Demo: [https://openbuddy.ai](https://openbuddy.ai)
# Copyright Notice
This model is built upon https://huggingface.co/AtomEchoAI/AtomGPT_56k , License: Apache 2.0.
## Disclaimer
All OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.
OpenBuddy is provided "as-is" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.
By using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.
## 免责声明
所有OpenBuddy模型均存在固有的局限性，可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事，不要使用这些模型，以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。
OpenBuddy按“原样”提供，不附带任何种类的明示或暗示的保证，包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下，作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任（无论是合同、侵权还是其他原因）承担责任。
使用OpenBuddy即表示您同意这些条款和条件，并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。 |
Yukang/Llama-2-7b-longlora-100k-ft | Yukang | "2023-09-25T12:38:22Z" | 1,949 | 51 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"arxiv:2309.12307",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-13T05:55:57Z" | # LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
<font size=6><div align='center' > <a href=http://arxiv.org/abs/2309.12307>**Paper**</a> | <a href="https://huggingface.co/Yukang">**Models**</a> | <a href="https://github.com/dvlab-research/LongLoRA">**Code**</a> </div></font>
**LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models [[Paper](http://arxiv.org/abs/2309.12307)]** <br />
[Yukang Chen](https://scholar.google.com/citations?user=6p0ygKUAAAAJ&hl=en),
[Shengju Qian](https://scholar.google.com/citations?user=QNnWmasAAAAJ),
[Haotian Tang](https://scholar.google.com/citations?user=WxL13BAAAAAJ&hl),
[Xin Lai](https://scholar.google.com/citations?user=tqNDPA4AAAAJ&hl=zh-CN),
[Zhijian Liu](https://scholar.google.com/citations?user=3coYSTUAAAAJ&hl=en),
[Song Han](https://scholar.google.com/citations?user=E0iCaa4AAAAJ&hl=zh-CN),
[Jiaya Jia](https://scholar.google.com/citations?user=XPAkzTEAAAAJ&hl=en)<br />
## Abstract
We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost.
Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources.
In this paper, we speed up the context extension of LLMs in two aspects. On the one hand, although dense global attention is needed during inference, fine-tuning the model can be effectively and efficiently done by sparse local attention. The proposed shift short attention effectively enables context extension, leading to non-trivial computation saving with similar performance to fine-tuning with vanilla attention. On the other hand, we find that LoRA for context extension works well under the premise of trainable embedding and normalization. LongLoRA demonstrates strong empirical results on various tasks on LLaMA2 models from 7B/13B to 70B. LongLoRA adopts LLaMA2 7B from 4k context to 100k, or LLaMA2 70B to 32k on a single 8x A100 machine. LongLoRA extends models' context while retaining their original architectures, and is compatible with most existing techniques, like FlashAttention-2. In addition, to make LongLoRA practical, we collect a dataset, LongQA, for supervised fine-tuning. It contains more than 3k long context question-answer pairs. For more details, please refer to the [paper](http://arxiv.org/abs/2309.12307).
## Highlights
**LongLoRA** speed up the context extension of pre-trained large language models in both attention-level and weight-level.
1. The proposed shifted short attention is easy to implement, compatible with Flash-Attention, and not required during inference.
2. We release all our models, including models from 7B to 70B, context length from 8k to 100k, including [LLaMA2-LongLoRA-7B-100k](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft), [LLaMA2-LongLoRA-13B-64k](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k), and [LLaMA2-LongLoRA-70B-32k](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k).
3. We build up a long-context QA dataset, LongQA, for supervised fine-tuning (SFT). We release 13B and 70B 32k models with SFT, [Llama-2-13b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) and [Llama-2-70b-chat-longlora-32k-sft](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft). We will further release the dataset next week.
## Released models
### Models with supervised fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------------|------|---------|---------|-------------------------------------------------------------------------|
| Llama-2-13b-chat-longlora-32k-sft | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-chat-longlora-32k-sft) |
| Llama-2-70b-chat-longlora-32k-sft | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k-sft) |
### Models with context extension via fully fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k-ft | 7B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k-ft) |
| Llama-2-7b-longlora-16k-ft | 7B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k-ft) |
| Llama-2-7b-longlora-32k-ft | 7B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k-ft) |
| Llama-2-7b-longlora-100k-ft | 7B | 100000 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-100k-ft) |
| Llama-2-13b-longlora-8k-ft | 13B | 8192 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k-ft) |
| Llama-2-13b-longlora-16k-ft | 13B | 16384 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k-ft) |
| Llama-2-13b-longlora-32k-ft | 13B | 32768 | Full FT | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k-ft) |
### Models with context extension via improved LoRA fine-tuning
| Model | Size | Context | Train | Link |
|:----------------------------|------|---------|-------|-------------------------------------------------------------------|
| Llama-2-7b-longlora-8k | 7B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-8k) |
| Llama-2-7b-longlora-16k | 7B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-16k) |
| Llama-2-7b-longlora-32k | 7B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-7b-longlora-32k) |
| Llama-2-13b-longlora-8k | 13B | 8192 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-8k) |
| Llama-2-13b-longlora-16k | 13B | 16384 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-16k) |
| Llama-2-13b-longlora-32k | 13B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-32k) |
| Llama-2-13b-longlora-64k | 13B | 65536 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-13b-longlora-64k) |
| Llama-2-70b-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-longlora-32k) |
| Llama-2-70b-chat-longlora-32k | 70B | 32768 | LoRA+ | [link](https://huggingface.co/Yukang/Llama-2-70b-chat-longlora-32k) |
## Citation
If you find this project useful in your research, please consider citing:
```
@article{longlora,
title={LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models},
author={Yukang Chen and Shengju Qian and Haotian Tang and Xin Lai and Zhijian Liu and Song Han and Jiaya Jia},
journal={arXiv:2309.12307},
year={2023}
}
```
## Acknowledgement
- This work is built upon the [LLaMA2](https://ai.meta.com/llama) as the pre-trained models.
- This work is based on [DeepSpeed](https://github.com/microsoft/DeepSpeed), [peft](https://github.com/huggingface/peft), and [Flash-Attention2](https://github.com/Dao-AILab/flash-attention) for acceleration.
- The perplexity evaluation code is modified upon [Landmark Attention](https://github.com/epfml/landmark-attention).
- We use [LongChat](https://github.com/DachengLi1/LongChat) for the retrieval evaluation.
|
Undi95/MLewd-L2-Chat-13B | Undi95 | "2023-11-17T21:08:46Z" | 1,949 | 31 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"not-for-all-audiences",
"nsfw",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-16T14:27:55Z" | ---
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- nsfw
---
THIS MODEL IS MADE FOR LEWD
SEXUAL, CRUDE AND KINKY CONTENT IN OUTPUT CAN AND WILL HAPPEN. YOU'RE WARNED
This is an attempt to make an uncensored Llama2-chat that can RP. It's not perfect, but I'm satified.
The beginning of the conversation is important for keeping good context and consistancy!
<!-- description start -->
## Description
This repo contains fp16 files of MLewd-L2-Chat-13B, very hot and lewd model based on Llama2-chat.
<!-- description end -->
<!-- description start -->
## Models and loras used
- Undi95/MLewd-L2-13B-Part3 (checkpoint of MLewd without LORA)
- posicube/Llama2-chat-AYT-13B
- zattio770/120-Days-of-LORA-v2-13B
- royallab/Pygmalion-2-13b-SuperCOT
- Undi95/MMSoul-13b-lora
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
Special thanks to Sushi and Shena ♥
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Undi95__MLewd-L2-Chat-13B)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 51.29 |
| ARC (25-shot) | 62.03 |
| HellaSwag (10-shot) | 84.19 |
| MMLU (5-shot) | 58.75 |
| TruthfulQA (0-shot) | 52.84 |
| Winogrande (5-shot) | 77.43 |
| GSM8K (5-shot) | 11.3 |
| DROP (3-shot) | 12.53 |
|
Chrisisis/5CnuP7Z7HbgH4fb3wqEW4j91ewVbqm54FBh2ZDBwy4Bk96K7_vgg | Chrisisis | "2024-02-24T08:26:00Z" | 1,949 | 0 | keras | [
"keras",
"region:us"
] | null | "2024-02-05T18:34:58Z" | Entry not found |
Gaeros/SeaArt-Furry-XL-1.0-fp16-diffusers | Gaeros | "2024-04-26T12:34:47Z" | 1,949 | 2 | diffusers | [
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"stable-diffusion-xl",
"en",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2024-04-24T23:40:01Z" | ---
license: creativeml-openrail-m
language:
- en
tags:
- text-to-image
- stable-diffusion
- safetensors
- stable-diffusion-xl
---
This is the single file [`furry-xl-4.0.safetensors`](https://huggingface.co/SeaArtLab/SeaArt-Furry-XL-1.0) [converted](https://github.com/Linaqruf/sdxl-model-converter/) to diffusers format. A wolf asked for it. If you're not a wolf you might still want this because the original version is fp32 while this one is fp16. SeaArt's diffusers distribution is also [missing the `unet/config.json`](https://huggingface.co/SeaArtLab/SeaArt-Furry-XL-1.0/discussions/2).
# SeaArt Furry XL 1.0
**SeaArt-Furry-XL-1.0**, built on the SDXL framework, focuses on high-quality furry art images creation. By analyzing millions of furry pictures, it sets new standards in furry imagery understanding and creation. Incorporating vast knowledge of furry characters and extensive species calibration, including mammals and birds, it refines artist styles and quality hints. SeaArt-Furry-XL-1.0 aims to offer furry enthusiasts and artists an accurate and detailed generation tool, encouraging collaboration to enrich the furry ecosystem.
## Model Details
- **Developed by:** [SeaArt](https://www.seaart.ai/)
- **Model type:** Diffusion-based text-to-image generative model
- **License:** [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)
- **Summary:** This model generates images based on text prompts. It is a Latent Diffusion Model that uses two fixed, pre-trained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L). It follows the same architecture as Stable Diffusion XL.
## Diffusers Installation
First install the required libraries:
```
pip install diffusers transformers accelerate safetensors --upgrade
```
Then run image generation with the following example code:
```
import torch
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained(
"Gaeros/SeaArt-Furry-XL-1.0-fp16-diffusers",
torch_dtype=torch.float16,
)
pipe.to('cuda')
prompt = "canid, canine, fox, mammal, red_fox, true_fox, foxgirl83, photonoko, day, digitigrade, fluffy, fluffy_tail, fur, orange_body, orange_fur, orange_tail, solo, sunlight, tail, mid, 2018, digital_media_(artwork), hi_res, masterpiece"
negative_prompt = "nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract]"
image = pipe(
prompt,
negative_prompt=negative_prompt,
width=832,
height=1216,
guidance_scale=7,
num_inference_steps=28
).images[0]
image.save("./output/seaart_test.png")
```
## Usage Guidelines
To fully utilize the SeaArt-Furry-XL-1.0 model and generate high-quality furry art images, we recommend following these guidelines:
### Prompt Structure:
The model was trained with a specific calibration order: species, artist, image detail, quality hint, image nsfw level. It is recommended to construct prompts following this order for optimal results. For example:
```
Prompt input: "canid, canine, fox, mammal, red_fox, true_fox, foxgirl83, photonoko, day, digitigrade, fluffy, fluffy_tail, fur, orange_body, orange_fur, orange_tail, solo, sunlight, tail, mid, 2018, digital_media_(artwork), hi_res, masterpiece"
```
### Species and Character Calibration:
We have provided a series of nouns for main species calibration such as mammals, birds, and have repeatedly trained on specific furry characters. This helps in generating more accurate character images.
### Quality Hints:
The model supports various levels of quality hints, from "masterpiece" to "worst quality". Be aware that "masterpiece" and "best quality" may lean towards nsfw content.
### Artwork Timing:
To get images in the style of specific periods, you can use time calibrations like "newest", "late", "mid", "early", "oldest". For instance, "newest" can be used for generating images with the most current styles.
### Recommended Image Sizes:
For best-quality images, it is recommended to generate using one of the following sizes: 1024x1024, 1152x896, 896x1152, etc. These sizes were more frequently used in training, making the model better adapted to them.
| Dimensions | Aspect Ratio |
|-------------------|-----------------|
| `1024 x 1024` | 1:1 Square |
| `1152 x 896` | 9:7 |
| `896 x 1152` | 7:9 |
| `1216 x 832` | 19:13 |
| `832 x 1216` | 13:19 |
| `1344 x 768` | 7:4 Horizontal |
| `768 x 1344` | 4:7 Vertical |
| `1536 x 640` | 12:5 Horizontal |
| `640 x 1536` | 5:12 Vertical |
## User Studies
To gain a deeper understanding of how SeaArt-Furry-XL-1.0 is applied within the furry art community and to assess user satisfaction, we invited artists, designers, and furry enthusiasts from various backgrounds to participate in our user study.
### Study Methodology:
Through online surveys and one-on-one interviews, we collected feedback on the furry art pieces generated by SeaArt-Furry-XL-1.0. Participants were asked to create images using the model based on specific prompts and to evaluate the images in terms of quality, style alignment, and inspiration for creation.
### Key Findings:
- Highly Personalized Creation: Users generally found that SeaArt-Furry-XL-1.0 offers a highly personalized creation experience, capable of generating images that meet individual preferences based on very specific prompts.
- Enhancement of Artistic Quality: Most users noted that using high-quality prompts like "masterpiece" significantly enhanced the artistic quality of their works.
- Source of Inspiration: Many artists and creators reported that the model not only expedited the creation process but also provided new sources of inspiration for their work.
### Showcase of User Creations:
In the study, we collected several outstanding works created by participants to showcase the diverse applications and creative potential of SeaArt-Furry-XL-1.0.
### Conclusion:
SeaArt-Furry-XL-1.0 has proven to be a powerful tool, offering endless possibilities for the furry art creation community. We will continue to collect user feedback and optimize the model to better serve artists and creators.
## License
SeaArt-Furry-XL-1.0 falls under Fair AI Public License 1.0-SD license, which is compatible with Stable Diffusion models’ license. Key points:
1. **Modification Sharing:** If you modify SeaArt-Furry-XL-1.0, you must share both your changes and the original license.
2. **Source Code Accessibility:** If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.
3. **Distribution Terms:** Any distribution must be under this license or another with similar rules.
4. **Compliance:** Non-compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open-source values.
The choice of this license aims to keep SeaArt-Furry-XL-1.0 open and modifiable, aligning with open source community spirit. It protects contributors and users, encouraging a collaborative, ethical open-source community. This ensures the model not only benefits from communal input but also respects open-source development freedoms.
## Finally
We welcome and value your feedback, looking forward to your suggestions to help us continuously optimize and improve. Moving forward, we will keep introducing a variety of models, so stay tuned for our latest developments.
|
stanford-nlpxed/uptake-model | stanford-nlpxed | "2023-01-20T22:09:09Z" | 1,948 | 1 | transformers | [
"transformers",
"pytorch",
"bert",
"license:cc-by-nc-nd-4.0",
"endpoints_compatible",
"region:us"
] | null | "2022-08-01T18:03:59Z" | ---
license: cc-by-nc-nd-4.0
---
|
TheTravellingEngineer/llama2-7b-chat-hf-v2 | TheTravellingEngineer | "2023-08-10T03:36:24Z" | 1,948 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-08T06:27:25Z" | The base model is meta's Llama-2-7b-chat-hf. It was finetuned using SFT and the alpaca dataset and the model prompt is similar to the original Guanaco model.
This repo contains the merged fp16 model.
**Legal Disclaimer: This model is bound by the usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.**
---
- license:
- llama2 <br>
- datasets:
- tatsu-lab/alpaca <br>
- language:
- en <br>
- reference: https://gist.github.com/younesbelkada/9f7f75c94bdc1981c8ca5cc937d4a4da
---
|
OpenBuddy/openbuddy-yi1.5-9b-v21.1-32k | OpenBuddy | "2024-05-22T02:05:13Z" | 1,948 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mixtral",
"conversational",
"zh",
"en",
"fr",
"de",
"ja",
"ko",
"it",
"ru",
"fi",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-22T00:19:01Z" | ---
license: apache-2.0
language:
- zh
- en
- fr
- de
- ja
- ko
- it
- ru
- fi
pipeline_tag: text-generation
inference: false
library_name: transformers
tags:
- mixtral
---
# OpenBuddy - Open Multilingual Chatbot
GitHub and Usage Guide: [https://github.com/OpenBuddy/OpenBuddy](https://github.com/OpenBuddy/OpenBuddy)
Website and Demo: [https://openbuddy.ai](https://openbuddy.ai)
Evaluation result of this model: [Evaluation.txt](Evaluation.txt)
# Copyright Notice
Base model: https://huggingface.co/01-ai/Yi-1.5-9B
License: Apache 2.0
# Prompt Format
We recommend using the fast tokenizer from `transformers`, which should be enabled by default in the `transformers` and `vllm` libraries. Other implementations including `sentencepiece` may not work as expected, especially for special tokens like `<|role|>`, `<|says|>` and `<|end|>`.
```
<|role|>system<|says|>You(assistant) are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human(user).
Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
You cannot access the internet, but you have vast knowledge, cutoff: 2023-04.
You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), not related to GPT or OpenAI.<|end|>
<|role|>user<|says|>History input 1<|end|>
<|role|>assistant<|says|>History output 1<|end|>
<|role|>user<|says|>History input 2<|end|>
<|role|>assistant<|says|>History output 2<|end|>
<|role|>user<|says|>Current input<|end|>
<|role|>assistant<|says|>
```
This format is also defined in `tokenizer_config.json`, which means you can directly use `vllm` to deploy an OpenAI-like API service. For more information, please refer to the [vllm documentation](https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html).
## Disclaimer
All OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.
OpenBuddy is provided "as-is" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.
By using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.
## 免责声明
所有OpenBuddy模型均存在固有的局限性，可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事，不要使用这些模型，以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。
OpenBuddy按“原样”提供，不附带任何种类的明示或暗示的保证，包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下，作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任（无论是合同、侵权还是其他原因）承担责任。
使用OpenBuddy即表示您同意这些条款和条件，并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。 |
votepurchase/ponymatureSDXL_ponyeclipse10 | votepurchase | "2024-05-25T12:44:37Z" | 1,948 | 0 | diffusers | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2024-05-25T12:44:37Z" | ---
library_name: diffusers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [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 Dataset 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 Dataset 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] |
mradermacher/ReviledSoup-L3-8B-GGUF | mradermacher | "2024-06-08T10:41:41Z" | 1,948 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:Revile/ReviledSoup-L3-8B",
"endpoints_compatible",
"region:us"
] | null | "2024-06-08T10:14:04Z" | ---
base_model: Revile/ReviledSoup-L3-8B
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Revile/ReviledSoup-L3-8B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/ReviledSoup-L3-8B-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/ReviledSoup-L3-8B-GGUF/resolve/main/ReviledSoup-L3-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
timm/vit_base_patch32_clip_224.laion2b_ft_in12k_in1k | timm | "2023-05-06T00:04:02Z" | 1,947 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:laion-2b",
"dataset:imagenet-12k",
"arxiv:2212.07143",
"arxiv:2210.08402",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
] | image-classification | "2022-11-05T22:33:35Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- laion-2b
- imagenet-12k
---
# Model card for vit_base_patch32_clip_224.laion2b_ft_in12k_in1k
A Vision Transformer (ViT) image classification model. Pretrained on LAION-2B image-text pairs using OpenCLIP. Fine-tuned on ImageNet-12k and then ImageNet-1k in `timm`. See recipes in [Reproducible scaling laws](https://arxiv.org/abs/2212.07143).
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 88.2
- GMACs: 4.4
- Activations (M): 4.2
- Image size: 224 x 224
- **Papers:**
- OpenCLIP: https://github.com/mlfoundations/open_clip
- Reproducible scaling laws for contrastive language-image learning: https://arxiv.org/abs/2212.07143
- LAION-5B: An open large-scale dataset for training next generation image-text models: https://arxiv.org/abs/2210.08402
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:**
- LAION-2B
- ImageNet-12k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_base_patch32_clip_224.laion2b_ft_in12k_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_base_patch32_clip_224.laion2b_ft_in12k_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 50, 768) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@software{ilharco_gabriel_2021_5143773,
author = {Ilharco, Gabriel and
Wortsman, Mitchell and
Wightman, Ross and
Gordon, Cade and
Carlini, Nicholas and
Taori, Rohan and
Dave, Achal and
Shankar, Vaishaal and
Namkoong, Hongseok and
Miller, John and
Hajishirzi, Hannaneh and
Farhadi, Ali and
Schmidt, Ludwig},
title = {OpenCLIP},
month = jul,
year = 2021,
note = {If you use this software, please cite it as below.},
publisher = {Zenodo},
version = {0.1},
doi = {10.5281/zenodo.5143773},
url = {https://doi.org/10.5281/zenodo.5143773}
}
```
```bibtex
@article{cherti2022reproducible,
title={Reproducible scaling laws for contrastive language-image learning},
author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
journal={arXiv preprint arXiv:2212.07143},
year={2022}
}
```
```bibtex
@inproceedings{schuhmann2022laionb,
title={{LAION}-5B: An open large-scale dataset for training next generation image-text models},
author={Christoph Schuhmann and
Romain Beaumont and
Richard Vencu and
Cade W Gordon and
Ross Wightman and
Mehdi Cherti and
Theo Coombes and
Aarush Katta and
Clayton Mullis and
Mitchell Wortsman and
Patrick Schramowski and
Srivatsa R Kundurthy and
Katherine Crowson and
Ludwig Schmidt and
Robert Kaczmarczyk and
Jenia Jitsev},
booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2022},
url={https://openreview.net/forum?id=M3Y74vmsMcY}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf | RichardErkhov | "2024-05-16T10:38:43Z" | 1,947 | 1 | null | [
"gguf",
"region:us"
] | null | "2024-05-16T09:02:14Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Llama-3-8B-Lexi-Uncensored - GGUF
- Model creator: https://huggingface.co/Orenguteng/
- Original model: https://huggingface.co/Orenguteng/Llama-3-8B-Lexi-Uncensored/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Llama-3-8B-Lexi-Uncensored.Q2_K.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q2_K.gguf) | Q2_K | 2.96GB |
| [Llama-3-8B-Lexi-Uncensored.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
| [Llama-3-8B-Lexi-Uncensored.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.IQ3_S.gguf) | IQ3_S | 3.43GB |
| [Llama-3-8B-Lexi-Uncensored.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
| [Llama-3-8B-Lexi-Uncensored.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.IQ3_M.gguf) | IQ3_M | 3.52GB |
| [Llama-3-8B-Lexi-Uncensored.Q3_K.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q3_K.gguf) | Q3_K | 3.74GB |
| [Llama-3-8B-Lexi-Uncensored.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
| [Llama-3-8B-Lexi-Uncensored.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
| [Llama-3-8B-Lexi-Uncensored.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
| [Llama-3-8B-Lexi-Uncensored.Q4_0.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q4_0.gguf) | Q4_0 | 4.34GB |
| [Llama-3-8B-Lexi-Uncensored.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
| [Llama-3-8B-Lexi-Uncensored.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
| [Llama-3-8B-Lexi-Uncensored.Q4_K.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q4_K.gguf) | Q4_K | 4.58GB |
| [Llama-3-8B-Lexi-Uncensored.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
| [Llama-3-8B-Lexi-Uncensored.Q4_1.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q4_1.gguf) | Q4_1 | 4.78GB |
| [Llama-3-8B-Lexi-Uncensored.Q5_0.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q5_0.gguf) | Q5_0 | 5.21GB |
| [Llama-3-8B-Lexi-Uncensored.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
| [Llama-3-8B-Lexi-Uncensored.Q5_K.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q5_K.gguf) | Q5_K | 5.34GB |
| [Llama-3-8B-Lexi-Uncensored.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
| [Llama-3-8B-Lexi-Uncensored.Q5_1.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q5_1.gguf) | Q5_1 | 5.65GB |
| [Llama-3-8B-Lexi-Uncensored.Q6_K.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q6_K.gguf) | Q6_K | 6.14GB |
| [Llama-3-8B-Lexi-Uncensored.Q8_0.gguf](https://huggingface.co/RichardErkhov/Orenguteng_-_Llama-3-8B-Lexi-Uncensored-gguf/blob/main/Llama-3-8B-Lexi-Uncensored.Q8_0.gguf) | Q8_0 | 7.95GB |
Original model description:
---
license: llama3
tags:
- uncensored
- llama3
- instruct
- open
---
This model is based on Llama-3-8b-Instruct, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://llama.meta.com/llama3/license/)
Lexi is uncensored, which makes the model compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones.
You are responsible for any content you create using this model. Please use it responsibly.
Lexi is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license.
|
AI-Sweden-Models/gpt-sw3-20b | AI-Sweden-Models | "2024-01-29T13:21:23Z" | 1,946 | 2 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt2",
"text-generation",
"da",
"sv",
"no",
"en",
"is",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2022-12-14T12:33:38Z" | ---
license: other
language:
- da
- sv
- 'no'
- en
- is
---
# Model description
[AI Sweden](https://huggingface.co/AI-Sweden-Models/)
**Base models**
[GPT-Sw3 126M](https://huggingface.co/AI-Sweden-Models/gpt-sw3-126m/) | [GPT-Sw3 356M](https://huggingface.co/AI-Sweden-Models/gpt-sw3-356m/) | [GPT-Sw3 1.3B](https://huggingface.co/AI-Sweden-Models/gpt-sw3-1.3b/)
[GPT-Sw3 6.7B](https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b/) | [GPT-Sw3 6.7B v2](https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b-v2/) | [GPT-Sw3 20B](https://huggingface.co/AI-Sweden-Models/gpt-sw3-20b/)
[GPT-Sw3 40B](https://huggingface.co/AI-Sweden-Models/gpt-sw3-40b/)
**Instruct models**
[GPT-Sw3 126M Instruct](https://huggingface.co/AI-Sweden-Models/gpt-sw3-126m-instruct/) | [GPT-Sw3 356M Instruct](https://huggingface.co/AI-Sweden-Models/gpt-sw3-356m-instruct/) | [GPT-Sw3 1.3B Instruct](https://huggingface.co/AI-Sweden-Models/gpt-sw3-1.3b-instruct/)
[GPT-Sw3 6.7B v2 Instruct](https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct/) | [GPT-Sw3 20B Instruct](https://huggingface.co/AI-Sweden-Models/gpt-sw3-20b-instruct/)
**Quantized models**
[GPT-Sw3 6.7B v2 Instruct 4-bit gptq](https://huggingface.co/AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct-4bit-gptq) | [GPT-Sw3 20B Instruct 4-bit gptq](https://huggingface.co/AI-Sweden-Models/gpt-sw3-20b-instruct-4bit-gptq)
GPT-SW3 is a collection of large decoder-only pretrained transformer language models that were developed by AI Sweden in collaboration with RISE and the WASP WARA for Media and Language. GPT-SW3 has been trained on a dataset containing 320B tokens in Swedish, Norwegian, Danish, Icelandic, English, and programming code. The model was pretrained using a causal language modeling (CLM) objective utilizing the NeMo Megatron GPT implementation.
# Intended use
GPT-SW3 is an autoregressive large language model that is capable of generating coherent text in 5 different languages, and 4 programming languages. GPT-SW3 can also be instructed to perform text tasks that it has not been explicitly trained for, by casting them as text generation tasks.
# Limitations
Like other large language models for which the diversity (or lack thereof) of training data induces downstream impact on the quality of our model, GPT-SW3 has limitations in terms of for example bias and safety. GPT-SW3 can also have quality issues in terms of generation diversity and hallucination. By releasing with the modified RAIL license, we also hope to increase communication, transparency, and the study of large language models. The model may: overrepresent some viewpoints and underrepresent others, contain stereotypes, generate hateful, abusive, violent, discriminatory or prejudicial language. The model may make errors, including producing incorrect information as if it were factual, it may generate irrelevant or repetitive outputs, and content that may not be appropriate for all settings, including sexual content.
# How to use
To be able to access the model from Python, since this is a private repository, you have to log in with your access token. This can be done with `huggingface-cli login`, see [HuggingFace Quick Start Guide](https://huggingface.co/docs/huggingface_hub/quick-start#login) for more information.
The following code snippet loads our tokenizer & model, and uses the GPU if available.
```python
import torch
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
# Initialize Variables
model_name = "AI-Sweden-Models/gpt-sw3-20b"
device = "cuda:0" if torch.cuda.is_available() else "cpu"
prompt = "Träd är fina för att"
# Initialize Tokenizer & Model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
model.eval()
model.to(device)
```
Generating text using the `generate` method is done as follows:
```python
input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to(device)
generated_token_ids = model.generate(
inputs=input_ids,
max_new_tokens=100,
do_sample=True,
temperature=0.6,
top_p=1,
)[0]
generated_text = tokenizer.decode(generated_token_ids)
```
A convenient alternative to the `generate` method is the HuggingFace pipeline, which handles most of the work for you:
```python
generator = pipeline('text-generation', tokenizer=tokenizer, model=model, device=device)
generated = generator(prompt, max_new_tokens=100, do_sample=True, temperature=0.6, top_p=1)[0]["generated_text"]
```
# Compliance
The release of GPT-SW3 consists of model weights, a configuration file, a tokenizer file and a vocabulary file. None of these files contain any personally identifiable information (PII) or any copyrighted material.
# GPT-SW3 Model Card
Following Mitchell et al. (2018), we provide a model card for GPT-SW3.
# Model Details
- Person or organization developing model: GPT-SW3 was developed by AI Sweden in collaboration with RISE and the WASP WARA for Media and Language.
- Model date: GPT-SW3 date of release 2022-12-20
- Model version: This is the second generation of GPT-SW3.
- Model type: GPT-SW3 is a large decoder-only transformer language model.
- Information about training algorithms, parameters, fairness constraints or other applied approaches, and features: GPT-SW3 was trained with the NeMo Megatron GPT implementation.
- Paper or other resource for more information: N/A.
- License: [LICENSE](https://huggingface.co/AI-Sweden-Models/gpt-sw3-20b/blob/main/LICENSE).
- Where to send questions or comments about the model: [email protected]
# Intended Use
- Primary intended uses: We pre-release GPT-SW3 for research and evaluation of the capabilities of Large Language Models for the Nordic languages. This is an important step in the process of knowledge building for LLMs, validating the model and collecting feedback on both what works well and what does not.
- Primary intended users: Organizations and individuals in the Nordic NLP ecosystem who can contribute to the validation and testing of the models and provide feedback to the community.
- Out-of-scope use cases: See the modified RAIL license.
# Data, Limitations, and Recommendations
- Data selection for training: Training data for GPT-SW3 was selected based on a combination of breadth and availability. See our Datasheet for more detailed information on the data used to train our model.
- Data selection for evaluation: N/A
- Limitations: Like other large language models for which the diversity (or lack thereof) of training data induces downstream impact on the quality of our model, GPT-SW3 has limitations in terms of bias and safety. GPT-SW3 can also have quality issues in terms of generation diversity and hallucination. In general, GPT-SW3 is not immune from the plethora of issues that plague modern large language models. By releasing with the modified RAIL license, we also hope to increase communication, transparency, and the study of large language models. The model may: Overrepresent some viewpoints and underrepresent others. Contain stereotypes. Generate: Hateful, abusive, or violent language. Discriminatory or prejudicial language. Content that may not be appropriate for all settings, including sexual content. Make errors, including producing incorrect information as if it were factual. Generate irrelevant or repetitive outputs.
- Recommendations for future work: Indirect users should be made aware when the content they're working with is created by the LLM. Users should be aware of Risks and Limitations, and include an appropriate age disclaimer or blocking interface as necessary. Models pretrained with the LLM should include an updated Model Card. Users of the model should provide mechanisms for those affected to provide feedback, such as an email address for comments.
- We hope that the release of GPT-SW3, as well as information around our model training process, will increase open science around both large language models in specific and natural language processing and deep learning in general.
# GPT-SW3 Datasheet
- We follow the recommendations of Gebru et al. (2021) and provide a datasheet for the dataset used to train GPT-SW3.
# Motivation
- For what purpose was the dataset created? Was there a specific task in mind? Was there a specific gap that needed to be filled? Please provide a description. Pre-training of Large Language Models (LLM), such as GPT-3 (T. B. Brown et al., 2020), Gopher (J. W. Rae et al., 2022), BLOOM (T. L. Scao et al., 2022), etc. require 100s or even 1000s GBs of text data, with recent studies (Chinchilla: J. Hoffmann et al., 2022) suggesting that the scale of the training data is even more important than previously imagined. Therefore, in order to train Swedish LLMs, we needed a large scale Swedish dataset of high quality. Since no such datasets existed before this initiative, we collected data in the Nordic and English languages.
- Who created the dataset (e.g., which team, research group) and on behalf of which entity (e.g., company, institution, organization)? The Strategic Initiative Natural Language Understanding at AI Sweden has established a new research environment in which collaboration is key. The core team working on the creation of the dataset is the NLU research group at AI Sweden. This group consists of researchers and developers from AI Sweden (Lindholmen Science Park AB) and RISE.
- Who funded the creation of the dataset? If there is an associated grant, please provide the name of the grantor and the grant name and number. The Swedish Innovation Agency (Vinnova) has funded this work across several different grants, including 2019-02996 and 2022-00949.
- Any other comments? No.
# Composition
- What do the instances that comprise the dataset represent (e.g., documents, photos, people, countries)? Are there multiple types of instances (e.g., movies, users, and ratings; people and interactions between them; nodes and edges)? Please provide a description. The instances are textual documents categorized by language and document type. The dataset is a filtered and deduplicated collection that includes the following sources:
- Books
- Litteraturbanken (https://litteraturbanken.se/)
- The Pile
- Articles
- Diva (https://www.diva-portal.org/)
- The Pile: PubMed
- The Pile: ArXiv
- Code
- Code Parrot: Github code (https://huggingface.co/datasets/codeparrot/github-code)
- Conversational
- Familjeliv (https://www.familjeliv.se/)
- Flashback (https://flashback.se/)
- Datasets collected through Parlai (see Appendix in data paper for complete list) (https://github.com/facebookresearch/ParlAI)
- Pushshift.io Reddit dataset, developed in Baumgartner et al. (2020) and processed in Roller et al. (2021)
- Math
- English Math dataset generated with code from DeepMind (D. Saxton et al., 2019)
- Swedish Math dataset, generated as above with manually translated templates
- Miscellaneous
- Summarization data (https://www.ida.liu.se/~arnjo82/papers/clarin-21-julius.pdf)
- OPUS, the open parallel corpus (https://opus.nlpl.eu/)
- Movie scripts (https://github.com/Aveek-Saha/Movie-Script-Database)
- Natural Instructions (https://github.com/allenai/natural-instructions)
- P3 (Public Pool of Prompts), (https://huggingface.co/datasets/bigscience/P3)
- The Norwegian Colossal Corpus (https://huggingface.co/datasets/NbAiLab/NCC)
- Danish Gigaword (https://gigaword.dk/)
- Icelandic Gigaword (https://clarin.is/en/resources/gigaword/)
- The Pile: Stack Exchange
- Web Common Crawl
- Web data from the project LES (Linguistic Explorations of Societies, https://les.gu.se).
- Multilingual C4 (MC4), prepared by AllenAI from C4 (C. Raffel et al., 2019)
- Open Super-large Crawled Aggregated coRpus (OSCAR) (P. O. Suarez, 2019)
- The Pile: Open Web Text
- Web Sources
- Various public Swedish website scrapes (see Appendix in data paper)
- Familjeliv Articles
- Public Swedish Job Ads from JobTech/Arbetsförmedlingen
- Wikipedia
- Official Wikipedia dumps
- How many instances are there in total (of each type, if appropriate)? The training data consists of 1.1TB UTF-8 encoded text, containing 660M documents with a total of 320B tokens.
- Does the dataset contain all possible instances or is it a sample (not necessarily random) of instances from a larger set? If the dataset is a sample, then what is the larger set? Is the sample representative of the larger set (e.g., geographic coverage)? If so, please describe how this representativeness was validated/verified. If it is not representative of the larger set, please describe why not (e.g., to cover a more diverse range of instances, because instances were withheld or unavailable). The subset of our dataset that comes from multilingual Common Crawl datasets (MC4, Oscar), are filtered by language to only include Swedish, Norwegian, Danish, and Icelandic. From The Pile, we included only the parts that typically are of highest textual quality or complemented the rest of our dataset with sources we otherwise lacked (e.g. books). The remainder of the dataset was collected from the above sources.
- What data does each instance consist of? “Raw” data (e.g., unprocessed text or images) or features? In either case, please provide a description. Each instance consists of raw text data.
- Is there a label or target associated with each instance? If so, please provide a description. No.
- Is any information missing from individual instances? If so, please provide a description, explaining why this information is missing (e.g., because it was unavailable). This does not include intentionally removed information, but might include, e.g., redacted text. No.
- Are relationships between individual instances made explicit (e.g., users’ movie ratings, social network links)? If so, please describe how these relationships are made explicit. There are no explicit relationships between individual instances.
- Are there recommended data splits (e.g., training, development/validation, testing)? If so, please provide a description of these splits, explaining the rationale behind them. There are no explicit splits recommended for this dataset. When pre-training the model, a random split for train, dev, test is set to 99.99%, 0.08%, 0.02% respectively, and is sampled proportionally to each subset’s weight and size. The weight of each subset was manually decided beforehand. These decisions were made considering the data’s value, source, and language, to form a representative and balanced pre-training corpus.
- Are there any errors, sources of noise, or redundancies in the dataset? If so, please provide a description. The dataset is a collection of many sources, some of which naturally contain some overlap. Although we have performed deduplication, some overlap may still remain. Furthermore, there may be some noise remaining from artifacts originating in Common Crawl datasets, that have been missed by our data filtering process. Except for these, we are not aware of any errors, sources of noise, or redundancies.
- Is the dataset self-contained, or does it link to or otherwise rely on external resources (e.g., websites, tweets, other datasets)? The dataset is self-contained.
- Does the dataset contain data that, if viewed directly, might be offensive, insulting, threatening, or might otherwise cause anxiety? If so, please describe why. The dataset contains subsets of public Common Crawl, Reddit, Familjeliv and Flashback. These could contain sentences that, if viewed directly, might be offensive, insulting, threatening, or might otherwise cause anxiety.
- Does the dataset relate to people? If not, you may skip the remaining questions in this section. Some documents of this data relate to people, such as news articles, Wikipedia descriptions, etc.
- Does the dataset identify any subpopulations (e.g., by age, gender)? If so, please describe how these subpopulations are identified and provide a description of their respective distributions within the dataset. No, the dataset does not explicitly include subpopulation identification.
- Any other comments? No.
# Collection Process
- How was the data associated with each instance acquired? Was the data directly observable (e.g., raw text, movie ratings), reported by subjects (e.g., survey responses), or indirectly inferred/derived from other data (e.g., part-of-speech tags, model-based guesses for age or language)? If data was reported by subjects or indirectly inferred/derived from other data, was the data validated/verified? If so, please describe how. N/A. The dataset is a union of publicly available datasets and sources.
- What mechanisms or procedures were used to collect the data (e.g., hardware apparatus or sensor, manual human curation, software program, software API)? How were these mechanisms or procedures validated? The data was downloaded from the internet.
- If the dataset is a sample from a larger set, what was the sampling strategy (e.g., deterministic, probabilistic with specific sampling probabilities)? Please see previous answers for how parts of the dataset were selected.
- Who was involved in the data collection process (e.g., students, crowdworkers, contractors) and how were they compensated (e.g., how much were crowdworkers paid)? This data is mined, filtered and sampled by machines.
- Over what timeframe was the data collected? Does this timeframe match the creation timeframe of the data associated with the instances (e.g., recent crawl of old news articles)? If not, please describe the timeframe in which the data associated with the instances was created. The dataset was collected during the period June 2021 to June 2022. The creation of the collected sources varies, with e.g. Common Crawl data that have been continuously collected over 12 years.
- Does the dataset relate to people? If not, you may skip the remainder of the questions in this section. Yes. The texts have been produced by people. Any personal information potentially present in publicly available data sources and thus in the created dataset is of no interest to the collection and use of the dataset.
- Has an analysis of the potential impact of the dataset and its use on data subjects (e.g., a data protection impact analysis) been conducted? If so, please provide a description of this analysis, including the outcomes, as well as a link or other access point to any supporting documentation. Yes.
- Any other comments? No.
- Preprocessing/cleaning/labeling
- Was any preprocessing/cleaning/labeling of the data done (e.g., discretization or bucketing, tokenization, part-of-speech tagging, SIFT feature extraction, removal of instances, processing of missing values)? If so, please provide a description. If not, you may skip the remainder of the questions in this section. The dataset was filtered and re-formatted on a document-level using standard procedures, inspired by the work in The BigScience ROOTS Corpus (H. Laurençon et al., 2022) and Gopher (J. W. Rae et al., 2022). This was done with the goal of achieving a consistent text format throughout the dataset, and to remove documents that did not meet our textual quality requirements (e.g. repetitiveness). Furthermore, the dataset was deduplicated to remedy the overlap between collected subsets using the MinHash algorithm, similar to the method used in GPT-3 and The Pile, and described in greater detail in “Deduplicating Training Data Makes Language Models Better” (K. Lee et al., 2021).
- Was the “raw” data saved in addition to the preprocessed/cleaned/labeled data (e.g., to support unanticipated future uses)? If so, please provide a link or other access point to the “raw” data. The “raw” component datasets are publicly available in their respective locations.
- Any other comments? No.
# Uses
- Has the dataset been used for any tasks already? If so, please provide a description. The dataset was used to pre-train the GPT-SW3 models.
- Is there a repository that links to any or all papers or systems that use the dataset? If so, please provide a link or other access point. N/A.
- What (other) tasks could the dataset be used for? The data can be used to pre-train language models, which are foundations for many current and future language tasks.
- Is there anything about the composition of the dataset or the way it was collected and preprocessed/cleaned/labeled that might impact future uses? For example, is there anything that a future user might need to know to avoid uses that could result in unfair treatment of individuals or groups (e.g., stereotyping, quality of service issues) or other undesirable harms (e.g., financial harms, legal risks) If so, please provide a description. Is there anything a future user could do to mitigate these undesirable harms? The dataset is probably quite representative of Swedish internet discourse in general, and of the Swedish public sector, but we know that this data does not necessarily reflect the entire Swedish population.
- Are there tasks for which the dataset should not be used? If so, please provide a description. None that we are currently aware of.
- Any other comments? No.
# Distribution
- Will the dataset be distributed to third parties outside of the entity (e.g., company, institution, organization) on behalf of which the dataset was created? If so, please provide a description. No.
- How will the dataset distributed (e.g., tarball on website, API, GitHub)? Does the dataset have a digital object identifier (DOI)? N/A.
- When will the dataset be distributed? N/A.
- Will the dataset be distributed under a copyright or other intellectual property (IP) license, and/or under applicable terms of use (ToU)? If so, please describe this license and/or ToU, and provide a link or other access point to, or otherwise reproduce, any relevant licensing terms or ToU, as well as any fees associated with these restrictions. N/A.
- Do any export controls or other regulatory restrictions apply to the dataset or to individual instances? If so, please describe these restrictions, and provide a link or other access point to, or otherwise reproduce, any supporting documentation. N/A.
- Any other comments? No.
# Maintenance
- Who is supporting/hosting/maintaining the dataset? AI Sweden at Lindholmen Science Park AB.
- How can the owner/curator/manager of the dataset be contacted (e.g., email address)? [email protected]
- Is there an erratum? If so, please provide a link or other access point. N/A.
- Will the dataset be updated (e.g., to correct labeling errors, add new instances, delete instances)? If so, please describe how often, by whom, and how updates will be communicated to users (e.g., mailing list, GitHub)? Currently, there are no plans for updating the dataset.
- If the dataset relates to people, are there applicable limits on the retention of the data associated with the instances (e.g., were individuals in question told that their data would be retained for a fixed period of time and then deleted)? If so, please describe these limits and explain how they will be enforced. Read the privacy policy for the NLU initiative at AI Sweden [here](https://www.ai.se/en/privacy-policy-nlu).
- Will older versions of the dataset continue to be supported/hosted/maintained? If so, please describe how. If not, please describe how its obsolescence will be communicated to users. N/A.
- If others want to extend/augment/build on/contribute to the dataset, is there a mechanism for them to do so? If so, please provide a description. Will these contributions be validated/ verified? If so, please describe how. If not, why not? Is there a process for communicating/ distributing these contributions to other users? If so, please provide a description. Not at this time.
- Any other comments? No.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_AI-Sweden-Models__gpt-sw3-20b)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 35.83 |
| ARC (25-shot) | 41.81 |
| HellaSwag (10-shot) | 68.75 |
| MMLU (5-shot) | 28.47 |
| TruthfulQA (0-shot) | 37.1 |
| Winogrande (5-shot) | 67.17 |
| GSM8K (5-shot) | 0.99 |
| DROP (3-shot) | 6.52 |
|
oh-yeontaek/llama-2-7B-LoRA-assemble | oh-yeontaek | "2023-09-13T15:40:26Z" | 1,946 | 5 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-13T15:30:35Z" | Entry not found |
timm/efficientnet_b1_pruned.in1k | timm | "2023-04-27T21:10:02Z" | 1,945 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:1905.11946",
"arxiv:2002.08258",
"license:apache-2.0",
"region:us"
] | image-classification | "2022-12-12T23:56:12Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for efficientnet_b1_pruned.in1k
A EfficientNet image classification model. Knapsack pruned from existing weights.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 6.3
- GMACs: 0.4
- Activations (M): 6.2
- Image size: 240 x 240
- **Papers:**
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946
- Knapsack Pruning with Inner Distillation: https://arxiv.org/abs/2002.08258
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('efficientnet_b1_pruned.in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'efficientnet_b1_pruned.in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 16, 120, 120])
# torch.Size([1, 12, 60, 60])
# torch.Size([1, 35, 30, 30])
# torch.Size([1, 67, 15, 15])
# torch.Size([1, 320, 8, 8])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'efficientnet_b1_pruned.in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1280, 8, 8) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@inproceedings{tan2019efficientnet,
title={Efficientnet: Rethinking model scaling for convolutional neural networks},
author={Tan, Mingxing and Le, Quoc},
booktitle={International conference on machine learning},
pages={6105--6114},
year={2019},
organization={PMLR}
}
```
```bibtex
@article{aflalo2020knapsack,
title={Knapsack pruning with inner distillation},
author={Aflalo, Yonathan and Noy, Asaf and Lin, Ming and Friedman, Itamar and Zelnik, Lihi},
journal={arXiv preprint arXiv:2002.08258},
year={2020}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
Yntec/ZootVisionEpsilon | Yntec | "2024-06-27T05:45:42Z" | 1,945 | 1 | diffusers | [
"diffusers",
"safetensors",
"Base Model",
"Photorealistic",
"Anime",
"Art",
"diffusionfanatic1173",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"en",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2024-06-27T04:19:47Z" | ---
license: creativeml-openrail-m
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Base Model
- Photorealistic
- Anime
- Art
- diffusionfanatic1173
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
inference: true
---
# ZootVisionEpsilon V5
A very versatile model that allows you to draw in the style of other models by adding things like "by midjourney", "by dalle3", "by ideogream" or 'by whoever', or any style you can think of. Original page: https://civitai.com/models/490451?modelVersionId=573612
Samples and prompts:
(Click for larger)
Top left: A bright and cheerful spring carnival with rides, games, and cotton candy stands under a sunny sky, (by dalle3:1.1), 3D, pixar, (photo \(medium\):0.2), masterpiece, best quality, high quality, absurdres, incredibly absurdres, detailed background, very aesthetic
To right: very aesthetic. A charming and vibrant 2D anime screencap featuring a girl with a cute cloud creature, air god, fluffy, gazing directly at the viewer. She is outdoors, surrounded by a beautiful cherry blossom tree in full bloom. Holding a playful, her outfit consists of a cute, short-sleeved top and a knee-length skirt with a floral pattern. The background is a serene and picturesque scene of the outdoors, with a clear blue sky and gentle breeze
Bottom left: princess peach kissing her boyfriend, by midjourney
Bottom right: unicorn on top of giant cupcake, vibrant colors, breathtaking, masterpiece, best quality, absurdres, insanely absurdres, by ideogram |
uklfr/gottbert-base | uklfr | "2023-03-22T13:13:12Z" | 1,944 | 15 | transformers | [
"transformers",
"pytorch",
"jax",
"safetensors",
"roberta",
"fill-mask",
"arxiv:2012.02110",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2022-03-02T23:29:05Z" | # Gottbert-base
BERT model trained solely on the German portion of the OSCAR data set.
[Paper: GottBERT: a pure German Language Model](https://arxiv.org/abs/2012.02110)
Authors: Raphael Scheible, Fabian Thomczyk, Patric Tippmann, Victor Jaravine, Martin Boeker |
Gaojunyao/StyleShot | Gaojunyao | "2024-07-02T17:30:05Z" | 1,944 | 2 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"en",
"arxiv:2407.01414",
"license:apache-2.0",
"region:us"
] | text-to-image | "2024-05-08T15:18:13Z" | ---
tags:
- text-to-image
- stable-diffusion
license: apache-2.0
language:
- en
library_name: diffusers
---
# StyleShot Model Card
<div align="center">
[**Project Page**](https://styleshot.github.io) **|** [**Paper (ArXiv)**](https://arxiv.org/abs/2407.01414) **|** [**Code**](https://github.com/open-mmlab/StyleShot)
</div>
---
## Introduction
we present StyleShot, a generalized plug-to-play style transfer method, capable of generating the high-quality stylized images that match the desired style from any reference image without test-time style-tuning. To the best of our knowledge, To the best of our knowledge, StyleShot is the first work to designate a style-aware encoder based on Stable Diffusion and a content-fusion encoder for better style and content integration, achieving the state-of-the-art text and image-driven style transfer performance compared to existing methods.
## Models
### StyleShot for SD 1.5
- [ip.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter_sd15.bin): weights for ip-adapter and our content-retention encoder.
- [style_aware_encoder.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter_sd15_light.bin): weights for style-aware encoder. |
llm-agents/tora-70b-v1.0 | llm-agents | "2023-10-08T11:37:14Z" | 1,943 | 20 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"code",
"math",
"en",
"dataset:gsm8k",
"dataset:competition_math",
"arxiv:2309.17452",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-10-08T05:46:26Z" | ---
license: llama2
datasets:
- gsm8k
- competition_math
language:
- en
metrics:
- exact_match
library_name: transformers
pipeline_tag: text-generation
tags:
- code
- math
---
<h1 align="center">
ToRA: A Tool-Integrated Reasoning Agent <br> for Mathematical Problem Solving
</h1>
<p align="center">
<a href="https://microsoft.github.io/ToRA/"><b>[🌐 Website]</b></a> •
<a href="https://arxiv.org/abs/2309.17452"><b>[📜 Paper]</b></a> •
<a href="https://huggingface.co/llm-agents"><b>[🤗 HF Models]</b></a> •
<a href="https://github.com/microsoft/ToRA"><b>[🐱 GitHub]</b></a>
<br>
<a href="https://twitter.com/zhs05232838/status/1708860992631763092"><b>[🐦 Twitter]</b></a> •
<a href="https://www.reddit.com/r/LocalLLaMA/comments/1703k6d/tora_a_toolintegrated_reasoning_agent_for/"><b>[💬 Reddit]</b></a> •
<a href="https://notes.aimodels.fyi/researchers-announce-tora-training-language-models-to-better-understand-math-using-external-tools/">[🍀 Unofficial Blog]</a>
<!-- <a href="#-quick-start">Quick Start</a> • -->
<!-- <a href="#%EF%B8%8F-citation">Citation</a> -->
</p>
<p align="center">
Repo for "<a href="https://arxiv.org/abs/2309.17452" target="_blank">ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving</a>"
</p>
## 🔥 News
- [2023/10/08] 🔥🔥🔥 All ToRA models released at [HuggingFace](https://huggingface.co/llm-agents)!!!
- [2023/09/29] ToRA paper, repo, and website released.
## 💡 Introduction
ToRA is a series of Tool-integrated Reasoning Agents designed to solve challenging mathematical reasoning problems by interacting with tools, e.g., computation libraries and symbolic solvers. ToRA series seamlessly integrate natural language reasoning with the utilization of external tools, thereby amalgamating the analytical prowess of language and the computational efficiency of external tools.
| Model | Size | GSM8k | MATH | AVG@10 math tasks<sup>†</sup> |
|---|---|---|---|---|
| GPT-4 | - | 92.0 | 42.5 | 78.3 |
| GPT-4 (PAL) | - | 94.2 | 51.8 | 86.4 |
| [ToRA-7B](https://huggingface.co/llm-agents/tora-7b-v1.0) | 7B | 68.8 | 40.1 | 62.4|
| [ToRA-Code-7B](https://huggingface.co/llm-agents/tora-code-7b-v1.0) | 7B | 72.6 | 44.6 | 66.5|
| [ToRA-13B](https://huggingface.co/llm-agents/tora-13b-v1.0) | 13B | 72.7 | 43.0 | 65.9|
| [ToRA-Code-13B](https://huggingface.co/llm-agents/tora-code-13b-v1.0) | 13B | 75.8 | 48.1 | 71.3 |
| [ToRA-Code-34B<sup>*</sup>](https://huggingface.co/llm-agents/tora-code-34b-v1.0) | 34B | 80.7 | **51.0** | 74.8 |
| [ToRA-70B](https://huggingface.co/llm-agents/tora-70b-v1.0) | 70B | **84.3** | 49.7 | **76.9** |
- <sup>*</sup>ToRA-Code-34B is currently the first and only open-source model to achieve over 50% accuracy (pass@1) on the MATH dataset, which significantly outperforms GPT-4’s CoT result (51.0 vs. 42.5), and is competitive with GPT-4 solving problems with programs. By open-sourcing our codes and models, we hope more breakthroughs will come!
- <sup>†</sup>10 math tasks include GSM8k, MATH, GSM-Hard, SVAMP, TabMWP, ASDiv, SingleEQ, SingleOP, AddSub, and MultiArith.
## ⚡️ Training
The models are trained on ToRA-Corpus 16k, which contains tool-integrated reasoning trajectories of MATH and GSM8k from GPT-4.
We use imitation learning (i.e., SFT) to fine-tune the models, and then apply our proposed *output space shaping* to improve tool-integrated reasoning behaviors. Please refer to the [paper](https://arxiv.org/pdf/2309.17452.pdf) for more details.
## 🪁 Inference & Evaluation
Please refer to ToRA's [GitHub repo](https://github.com/microsoft/ToRA) for inference, evaluation, and training code.
## ☕️ Citation
If you find this repository helpful, please consider citing our paper:
```
@misc{gou2023tora,
title={ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving},
author={Zhibin Gou and Zhihong Shao and Yeyun Gong and yelong shen and Yujiu Yang and Minlie Huang and Nan Duan and Weizhu Chen},
year={2023},
eprint={2309.17452},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
trl-internal-testing/T5ForConditionalGeneration-correct-vocab-calibrated | trl-internal-testing | "2024-06-18T08:48:53Z" | 1,943 | 0 | transformers | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | "2024-06-18T08:37:42Z" | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [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 Dataset 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 Dataset 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] |
Tap-M/Luna-AI-Llama2-Uncensored | Tap-M | "2023-07-26T19:31:12Z" | 1,942 | 130 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-19T09:16:29Z" | ---
license: cc-by-sa-4.0
---
<div style="width: 800px; margin: auto;">
<h2>Model Description</h2>
<p>“Luna AI Llama2 Uncensored” is a Llama2 based Chat model <br />fine-tuned on over 40,000 long form chat discussions <br />
This model was fine-tuned by Tap, the creator of Luna AI. <br />
<h2>Model Training</h2>
<p>The fine-tuning process was performed on an 8x a100 80GB machine.
<br />The model was trained on synthetic outputs which include multiple rounds of chats between Human & AI.
</p>
<a rel="noopener nofollow" href="https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ">4bit GPTQ Version provided by @TheBloke - for GPU inference</a><br />
<a rel="noopener nofollow" href="https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GGML">GGML Version provided by @TheBloke - For CPU inference</a>
<h2>Prompt Format</h2>
<p>The model follows the Vicuna 1.1/ OpenChat format:</p>
```
USER: I have difficulties in making friends, and I really need someone to talk to. Would you be my friend?
ASSISTANT: Of course! Friends are always here for each other. What do you like to do?
```
<h2>Benchmark Results</h2>
||||||
|---:|---:|---:|---:|---:|
|Task|Version| Metric |Value |Stderr|
|arc_challenge|0|acc_norm|0.5512|0.0146|
|hellaswag|0||||
|mmlu|1|acc_norm|0.46521|0.036|
|truthfulqa_mc|1|mc2|0.4716|0.0155|
|Average|-|-|0.5114|0.0150|
</div>
|
timm/tf_efficientnet_b0.in1k | timm | "2023-04-27T21:14:58Z" | 1,941 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:1905.11946",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-04-27T21:14:52Z" | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for tf_efficientnet_b0.in1k
A EfficientNet image classification model. Trained on ImageNet-1k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 5.3
- GMACs: 0.4
- Activations (M): 6.7
- Image size: 224 x 224
- **Papers:**
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('tf_efficientnet_b0.in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tf_efficientnet_b0.in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 16, 112, 112])
# torch.Size([1, 24, 56, 56])
# torch.Size([1, 40, 28, 28])
# torch.Size([1, 112, 14, 14])
# torch.Size([1, 320, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tf_efficientnet_b0.in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1280, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@inproceedings{tan2019efficientnet,
title={Efficientnet: Rethinking model scaling for convolutional neural networks},
author={Tan, Mingxing and Le, Quoc},
booktitle={International conference on machine learning},
pages={6105--6114},
year={2019},
organization={PMLR}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
|
OpenAssistant/llama2-13b-orca-8k-3319 | OpenAssistant | "2023-07-27T11:04:21Z" | 1,941 | 131 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"sft",
"en",
"dataset:ehartford/dolphin",
"dataset:shahules786/orca-chat",
"dataset:togethercomputer/RedPajama-Data-1T",
"dataset:atom-in-the-universe/fanfics-10k-50k",
"arxiv:2306.02707",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-24T09:26:49Z" | ---
license: other
datasets:
- ehartford/dolphin
- shahules786/orca-chat
- togethercomputer/RedPajama-Data-1T
- atom-in-the-universe/fanfics-10k-50k
language:
- en
tags:
- sft
pipeline_tag: text-generation
widget:
- text: <|system|>You are an AI assistant. You will be given a task. You must generate a detailed and long answer.</s><|prompter|>What is a meme, and what's the history behind this word?</s><|assistant|>
- text: <|system|>You are an AI assistant that helps people find information.</s><|prompter|>What's the Earth total population</s><|assistant|>
- text: <|system|>You are an AI assistant that follows instruction extremely well. Help as much as you can.</s><|prompter|>Write a story about future of AI development</s><|assistant|>
---
# llama2-13b-orca-8k-3319
## Model Description
This model is a fine-tuning of Meta's Llama2 13B model with 8K context size on a long-conversation variant of the Dolphin dataset ([orca-chat](https://huggingface.co/datasets/shahules786/orca-chat)).
Note: **At least Huggingface Transformers [4.31.0](https://pypi.org/project/transformers/4.31.0/) is required to load this model!**
## Usage
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("OpenAssistant/llama2-13b-orca-8k-3319", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("OpenAssistant/llama2-13b-orca-8k-3319", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
system_message = "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."
user_prompt = "Write me a poem please"
prompt = f"""<|system|>{system_message}</s><|prompter|>{user_prompt}</s><|assistant|>"""
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=256)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
## Model Details
- base model: [meta-llama/Llama-2-13b](https://huggingface.co/meta-llama/Llama-2-13b)
- License: [Llama 2 Community License Agreement](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
- sampling report: [2023-07-25_OpenAssistant_llama2-13b-orca-8k-3319_sampling_llama2_prompt.json](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-pretrained%2F2023-07-25_OpenAssistant_llama2-13b-orca-8k-3319_sampling_llama2_prompt.json)
- wandb: [public-sft/runs/2jfazjt9](https://wandb.ai/open-assistant/public-sft/runs/2jfazjt9)
- checkpoint: 3319 steps
- datatpye: fp16
- sponsored by: [Redmond.ai](https://redmond.ai/)
## Long context (RoPE Scaling)
This model was fine-tuned with a context size of 8192 tokens using linear scaling of RoPE embeddings. This feature was recently
added to [Huggingface transformers](https://github.com/huggingface/transformers/). Before loading this model please make sure
HF transformers >=4.31.0 is installed (`pip install transformers>=4.31.0`).
## Conversation Template
For the initial response use (e.g. the [llama2 default system prompt](https://github.com/facebookresearch/llama/blob/6c7fe276574e78057f917549435a2554000a876d/llama/generation.py#L46) works well):
```
<|system|>system message</s><|prompter|>user prompt</s><|assistant|>
```
For multi-turn conversations use:
```
<|system|>system message</s><|prompter|>Q1</s><|assistant|>A1</s><|prompter|>Q2</s><|assistant|>
```
The model was trained with the following 15 system messages used to generate the training examples (see [ORCA paper](https://arxiv.org/abs/2306.02707)):
1. You are an AI assistant. Provide a detailed answer so user don’t need to search outside to understand the answer.
2. You are an AI assistant. You will be given a task. You must generate a detailed and long answer.
3. You are a helpful assistant, who always provide explanation. Think like you are answering to a five year old.
4. You are an AI assistant that follows instruction extremely well. Help as much as you can.
5. You are an AI assistant that helps people find information. Provide a detailed answer so user don’t need to search outside to understand the answer.
6. You are an AI assistant. User will you give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
7. You should describe the task and explain your answer. While answering a multiple choice question, first output the correct answer(s). Then explain why other answers are wrong. Think like you are answering to a five year old.
8. Explain how you used the definition to come up with the answer.
9. You are an AI assistant. You should describe the task and explain your answer. While answering a multiple choice question, first output the correct answer(s). Then explain why other answers are wrong. You might need to use additional knowledge to answer the question.
10. You are an AI assistant that helps people find information. User will you give you a question. Your task is to answer as faithfully as you can. While answering think step-by- step and justify your answer.
11. User will you give you a task with some instruction. Your job is follow the instructions as faithfully as you can. While answering think step-by-step and justify your answer.
12. You are a teacher. Given a task, you explain in simple steps what the task is asking, any guidelines it provides and how to use those guidelines to find the answer.
13. You are an AI assistant, who knows every language and how to translate one language to another. Given a task, you explain in simple steps what the task is asking, any guidelines that it provides. You solve the task and show how you used the guidelines to solve the task.
14. Given a definition of a task and a sample input, break the definition into small parts. Each of those parts will have some instruction. Explain their meaning by showing an example that meets the criteria in the instruction. Use the following format: Part \#: a key part of the definition. Usage: Sample response that meets the criteria from the key part. Explain why you think it meets the criteria.
15. You are an AI assistant that helps people find information.
## Datasets: Orca-Chat/Dolphin, RedPajama1T & FanFics
This model was trained on:
- [shahules786/orca-chat](https://huggingface.co/datasets/shahules786/orca-chat)
- [togethercomputer/RedPajama-Data-1T-Sample](https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T)
- [atom-in-the-universe/fanfics-10k-50k](https://huggingface.co/datasets/atom-in-the-universe/fanfics-10k-50k)
```
Dataset Composition:
Tain (sampled):
orca-chat: 188842 (100%)
fanfics: 47760 (100%)
red_pajama: 188262 (25%)
Valid:
orca-chat: 5000
fanfics: 1000
red_pajama: 1000
```
The dataset [shahules786/orca-chat](https://huggingface.co/datasets/shahules786/orca-chat) combines similar examples of the GPT-4 subset of [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin) to form longer conversations
to improve long-context training.
Additionally, RedPajama and FanFics were used for classic language modelling as an auxiliary task to improve the RoPE scaling for the 8k context size.
## Model Configuration
```
llama2_13b_orca_8k:
rng_seed: 0xe1291f1a
use_custom_sampler: true
sort_by_length: false
dtype: fp16
log_dir: "llama2_log_13b_orca_8k"
learning_rate: 1e-5
model_name: /mnt/data/llama2/Llama-2-13b-hf/
output_dir: llama2_13b_orca_8k
deepspeed_config: configs/zero_config_pretrain.json
weight_decay: 0.0
max_length: 8192
warmup_steps: 100
use_flash_attention: true
gradient_checkpointing: true
gradient_accumulation_steps: 8
per_device_train_batch_size: 2
per_device_eval_batch_size: 1
residual_dropout: 0.0
eval_steps: 200
save_steps: 1000 # (total steps: 3319)
num_train_epochs: 1
save_total_limit: 4
superhot: true
superhot_config:
type: linear
scale: 2
datasets:
- orca-chat:
max_val_set: 5000
- fanfics:
max_chunk_size: 65535
max_val_set: 1000
- red_pajama:
fraction: 0.25
max_val_set: 1000
max_chunk_size: 65535
peft_model: false
```
# Developers
- [shahules786](https://github.com/shahules786)
- [jordiclive](https://github.com/jordiclive)
- [andreaskoepf](https://github.com/andreaskoepf/)
# Special Thanks
We want to especially thank Eric Hartford who spared no expense in replicating ORCA and making it available at [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin)!
Also, shoutout to the whole team working on [LLongMA-2-13b](https://huggingface.co/conceptofmind/LLongMA-2-13b) & the [scaled-rope](https://github.com/jquesnelle/scaled-rope) repository for their awesome work: bloc97, jquesnelle & conceptofmind!
The whole Open-Assistant team is very grateful for the continued support of [Redmond.ai](https://redmond.ai/) who sponsored the training compute required for this model.
# License
- Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
- Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the [Acceptable Use Policy](https://ai.meta.com/llama/use-policy) for the Llama Materials. |
Jayant9928/orpo_med_v3 | Jayant9928 | "2024-05-21T12:44:56Z" | 1,941 | 1 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-01T18:05:57Z" | ---
license: apache-2.0
---
Model Card for Model ID Model Details Model Description This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Developed by: [More Information Needed] Funded by [optional]: [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 |
QuantFactory/Qwen2-7B-Instruct-GGUF | QuantFactory | "2024-06-08T11:33:29Z" | 1,941 | 1 | null | [
"gguf",
"chat",
"text-generation",
"en",
"arxiv:2309.00071",
"base_model:Qwen/Qwen2-7B-Instruct",
"license:apache-2.0",
"region:us"
] | text-generation | "2024-06-07T01:20:47Z" | ---
license: apache-2.0
language:
- en
pipeline_tag: text-generation
tags:
- chat
base_model: Qwen/Qwen2-7B-Instruct
---
# Qwen2-7B-Instruct-GGUF
This is quantized version of [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) created using llama.cpp
## Model Description
Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 7B Qwen2 model.
Compared with the state-of-the-art opensource language models, including the previous released Qwen1.5, Qwen2 has generally surpassed most opensource models and demonstrated competitiveness against proprietary models across a series of benchmarks targeting for language understanding, language generation, multilingual capability, coding, mathematics, reasoning, etc.
Qwen2-7B-Instruct supports a context length of up to 131,072 tokens, enabling the processing of extensive inputs. Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2 for handling long texts.
For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2/), [GitHub](https://github.com/QwenLM/Qwen2), and [Documentation](https://qwen.readthedocs.io/en/latest/).
<br>
## Model Details
Qwen2 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes.
## Training details
We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.
## Requirements
The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
```
KeyError: 'qwen2'
```
## Quickstart
Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen2-7B-Instruct",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-7B-Instruct")
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
### Processing Long Texts
To handle extensive inputs exceeding 32,768 tokens, we utilize [YARN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.
For deployment, we recommend using vLLM. You can enable the long-context capabilities by following these steps:
1. **Install vLLM**: You can install vLLM by running the following command.
```bash
pip install "vllm>=0.4.3"
```
Or you can install vLLM from [source](https://github.com/vllm-project/vllm/).
2. **Configure Model Settings**: After downloading the model weights, modify the `config.json` file by including the below snippet:
```json
{
"architectures": [
"Qwen2ForCausalLM"
],
// ...
"vocab_size": 152064,
// adding the following snippets
"rope_scaling": {
"factor": 4.0,
"original_max_position_embeddings": 32768,
"type": "yarn"
}
}
```
This snippet enable YARN to support longer contexts.
3. **Model Deployment**: Utilize vLLM to deploy your model. For instance, you can set up an openAI-like server using the command:
```bash
python -m vllm.entrypoints.openai.api_server --served-model-name Qwen2-7B-Instruct --model path/to/weights
```
Then you can access the Chat API by:
```bash
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen2-7B-Instruct",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Your Long Input Here."}
]
}'
```
For further usage instructions of vLLM, please refer to our [Github](https://github.com/QwenLM/Qwen2).
**Note**: Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts**. We advise adding the `rope_scaling` configuration only when processing long contexts is required.
## Evaluation
We briefly compare Qwen2-7B-Instruct with similar-sized instruction-tuned LLMs, including Qwen1.5-7B-Chat. The results are shown below:
| Datasets | Llama-3-8B-Instruct | Yi-1.5-9B-Chat | GLM-4-9B-Chat | Qwen1.5-7B-Chat | Qwen2-7B-Instruct |
| :--- | :---: | :---: | :---: | :---: | :---: |
| _**English**_ | | | | | |
| MMLU | 68.4 | 69.5 | **72.4** | 59.5 | 70.5 |
| MMLU-Pro | 41.0 | - | - | 29.1 | **44.1** |
| GPQA | **34.2** | - | **-** | 27.8 | 25.3 |
| TheroemQA | 23.0 | - | - | 14.1 | **25.3** |
| MT-Bench | 8.05 | 8.20 | 8.35 | 7.60 | **8.41** |
| _**Coding**_ | | | | | |
| Humaneval | 62.2 | 66.5 | 71.8 | 46.3 | **79.9** |
| MBPP | **67.9** | - | - | 48.9 | 67.2 |
| MultiPL-E | 48.5 | - | - | 27.2 | **59.1** |
| Evalplus | 60.9 | - | - | 44.8 | **70.3** |
| LiveCodeBench | 17.3 | - | - | 6.0 | **26.6** |
| _**Mathematics**_ | | | | | |
| GSM8K | 79.6 | **84.8** | 79.6 | 60.3 | 82.3 |
| MATH | 30.0 | 47.7 | **50.6** | 23.2 | 49.6 |
| _**Chinese**_ | | | | | |
| C-Eval | 45.9 | - | 75.6 | 67.3 | **77.2** |
| AlignBench | 6.20 | 6.90 | 7.01 | 6.20 | **7.21** |
|
thodsapon/V3_test | thodsapon | "2024-07-01T15:31:36Z" | 1,940 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:scb10x/llama-3-typhoon-v1.5-8b-instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-07-01T15:11:16Z" | ---
base_model: scb10x/llama-3-typhoon-v1.5-8b-instruct
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
---
# Uploaded model
- **Developed by:** thodsapon
- **License:** apache-2.0
- **Finetuned from model :** scb10x/llama-3-typhoon-v1.5-8b-instruct
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Ppoyaa/Lumina-3.5 | Ppoyaa | "2024-04-18T10:19:11Z" | 1,939 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"moe",
"frankenmoe",
"merge",
"mergekit",
"lazymergekit",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-16T15:54:59Z" | ---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
model-index:
- name: Lumina-3.5
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 71.59
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ppoyaa/Lumina-3.5
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 88.82
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ppoyaa/Lumina-3.5
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 64.48
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ppoyaa/Lumina-3.5
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 75.66
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ppoyaa/Lumina-3.5
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 83.98
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ppoyaa/Lumina-3.5
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 67.93
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ppoyaa/Lumina-3.5
name: Open LLM Leaderboard
---
# Lumina-3.5
Lumina-3.5 is a Mixture of Experts (MoE) made with [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing) with improved reasoning from [Lumina-3](https://huggingface.co/Ppoyaa/Lumina-3). This model uses a context window of up to 32k.
# Response Examples
``` Math
Input: 25 - 4 * 2 + 3 = ?
------------------------------------
Output: To solve this equation, we will follow the order of operations (PEMDAS/BODMAS). This means performing any multiplications and divisions first from left to right, and then additions and subtractions from left to right.
The given equation is: 25 - 4 * 2 + 3
First, let's perform the multiplication:
4 * 2 = 8
Now, our equation looks like: 25 - 8 + 3
Next, perform the subtraction:
25 - 8 = 17
Finally, do the addition:
17 + 3 = 20
So, the result of the equation 25 - 4 * 2 + 3 is 20.
```
``` Reasoning
Input: Jane is faster than Joe. Joe is faster than Sam. Is Sam faster than Jane? Explain your reasoning step by step.
------------------------------------
Output: To answer this question, let's analyze the given information step by step:
We are provided with a comparison between three individuals - Jane, Joe, and Sam - in terms of their relative speeds. The statements tell us the following about their ranks:
Jane > Joe (Jane is faster than Joe)
Joe > Sam (Joe is faster than Sam)
Now we need to determine if the opposite relationship holds true: whether Sam is faster than Jane or not. Based on the given comparisons, we know that both Jane and Joe have faster speeds compared to Sam. There isn't any piece of information suggesting otherwise.
Since the original premise established an ordered ranking among these individuals (Jane > Joe > Sam), and the direct opposite of the relationship between Sam and the other two is not present, we cannot conclude that Sam is faster than Jane.
Thus, based on the provided information, our reasoning confirms that Sam is not faster than Jane.
```
## 🏆 Open LLM Leaderboard Evaluation Results
| Metric |Value|
|---------------------------------|----:|
|Avg. |75.41|
|AI2 Reasoning Challenge (25-Shot)|71.59|
|HellaSwag (10-Shot) |88.82|
|MMLU (5-Shot) |64.48|
|TruthfulQA (0-shot) |75.66|
|Winogrande (5-shot) |83.98|
|GSM8k (5-shot) |67.93|
# Quants
Special thanks to GGUFs made by [mradermacher](https://huggingface.co/mradermacher)
* [mradermacher/Lumina-3.5-GGUF](https://huggingface.co/mradermacher/Lumina-3.5-GGUF)
## 💻 Usage
```python
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Ppoyaa/Lumina-3.5"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Ppoyaa__Lumina-3.5)
| Metric |Value|
|---------------------------------|----:|
|Avg. |75.41|
|AI2 Reasoning Challenge (25-Shot)|71.59|
|HellaSwag (10-Shot) |88.82|
|MMLU (5-Shot) |64.48|
|TruthfulQA (0-shot) |75.66|
|Winogrande (5-shot) |83.98|
|GSM8k (5-shot) |67.93|
|
TehVenom/DiffMerge_Pygmalion_Main-onto-V8P4 | TehVenom | "2023-03-19T18:15:27Z" | 1,938 | 1 | transformers | [
"transformers",
"pytorch",
"gptj",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-03-19T08:39:28Z" | Entry not found |
nickmuchi/yolos-small-rego-plates-detection | nickmuchi | "2023-08-01T13:42:03Z" | 1,937 | 4 | transformers | [
"transformers",
"pytorch",
"safetensors",
"yolos",
"object-detection",
"license-plate-detection",
"vehicle-detection",
"dataset:coco",
"dataset:license-plate-detection",
"arxiv:2106.00666",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | object-detection | "2022-07-07T21:31:21Z" | ---
license: apache-2.0
tags:
- object-detection
- license-plate-detection
- vehicle-detection
datasets:
- coco
- license-plate-detection
widget:
- src: https://drive.google.com/uc?id=1j9VZQ4NDS4gsubFf3m2qQoTMWLk552bQ
example_title: "Skoda 1"
- src: https://drive.google.com/uc?id=1p9wJIqRz3W50e2f_A0D8ftla8hoXz4T5
example_title: "Skoda 2"
metrics:
- average precision
- recall
- IOU
model-index:
- name: yolos-small-rego-plates-detection
results: []
---
# YOLOS (small-sized) model
The original YOLOS model was fine-tuned on COCO 2017 object detection (118k annotated images). It was introduced in the paper [You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection](https://arxiv.org/abs/2106.00666) by Fang et al. and first released in [this repository](https://github.com/hustvl/YOLOS).
This model was further fine-tuned on the [license plate dataset]("https://www.kaggle.com/datasets/andrewmvd/car-plate-detection") from Kaggle. The dataset consists of 735 images of annotations categorised as "vehicle" and "license-plate". The model was trained for 200 epochs on a single GPU using Google Colab
## Model description
YOLOS is a Vision Transformer (ViT) trained using the DETR loss. Despite its simplicity, a base-sized YOLOS model is able to achieve 42 AP on COCO validation 2017 (similar to DETR and more complex frameworks such as Faster R-CNN).
## Intended uses & limitations
You can use the raw model for object detection. See the [model hub](https://huggingface.co/models?search=hustvl/yolos) to look for all available YOLOS models.
### How to use
Here is how to use this model:
```python
from transformers import YolosFeatureExtractor, YolosForObjectDetection
from PIL import Image
import requests
url = 'https://drive.google.com/uc?id=1p9wJIqRz3W50e2f_A0D8ftla8hoXz4T5'
image = Image.open(requests.get(url, stream=True).raw)
feature_extractor = YolosFeatureExtractor.from_pretrained('nickmuchi/yolos-small-rego-plates-detection')
model = YolosForObjectDetection.from_pretrained('nickmuchi/yolos-small-rego-plates-detection')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
# model predicts bounding boxes and corresponding face mask detection classes
logits = outputs.logits
bboxes = outputs.pred_boxes
```
Currently, both the feature extractor and model support PyTorch.
## Training data
The YOLOS model was pre-trained on [ImageNet-1k](https://huggingface.co/datasets/imagenet2012) and fine-tuned on [COCO 2017 object detection](https://cocodataset.org/#download), a dataset consisting of 118k/5k annotated images for training/validation respectively.
### Training
This model was fine-tuned for 200 epochs on the [license plate dataset]("https://www.kaggle.com/datasets/andrewmvd/car-plate-detection").
## Evaluation results
This model achieves an AP (average precision) of **47.9**.
Accumulating evaluation results...
IoU metric: bbox
Metrics | Metric Parameter | Location | Dets | Value |
---------------- | --------------------- | ------------| ------------- | ----- |
Average Precision | (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] | 0.479 |
Average Precision | (AP) @[ IoU=0.50 | area= all | maxDets=100 ] | 0.752 |
Average Precision | (AP) @[ IoU=0.75 | area= all | maxDets=100 ] | 0.555 |
Average Precision | (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] | 0.147 |
Average Precision | (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] | 0.420 |
Average Precision | (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] | 0.804 |
Average Recall | (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] | 0.437 |
Average Recall | (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] | 0.641 |
Average Recall | (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] | 0.676 |
Average Recall | (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] | 0.268 |
Average Recall | (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] | 0.641 |
Average Recall | (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] | 0.870 | |
timm/seresnext50_32x4d.racm_in1k | timm | "2024-02-10T23:41:49Z" | 1,937 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:2110.00476",
"arxiv:1611.05431",
"arxiv:1512.03385",
"arxiv:1709.01507",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-04-05T19:33:50Z" | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
---
# Model card for seresnext50_32x4d.racm_in1k
A SE-ResNeXt-B image classification model with Squeeze-and-Excitation channel attention.
This model features:
* ReLU activations
* single layer 7x7 convolution with pooling
* 1x1 convolution shortcut downsample
* grouped 3x3 bottleneck convolutions
* Squeeze-and-Excitation channel attention
Trained on ImageNet-1k in `timm` using recipe template described below.
Recipe details:
* RandAugment `RACM` recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as `B` recipe in [ResNet Strikes Back](https://arxiv.org/abs/2110.00476).
* RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging
* Step (exponential decay w/ staircase) LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 27.6
- GMACs: 4.3
- Activations (M): 14.4
- Image size: train = 224 x 224, test = 288 x 288
- **Papers:**
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- Aggregated Residual Transformations for Deep Neural Networks: https://arxiv.org/abs/1611.05431
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- Squeeze-and-Excitation Networks: https://arxiv.org/abs/1709.01507
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('seresnext50_32x4d.racm_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'seresnext50_32x4d.racm_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 112, 112])
# torch.Size([1, 256, 56, 56])
# torch.Size([1, 512, 28, 28])
# torch.Size([1, 1024, 14, 14])
# torch.Size([1, 2048, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'seresnext50_32x4d.racm_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
|model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec|
|------------------------------------------|--------|-----|-----|-----------|-----|-----|-------|
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 |
|[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 |
|[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 |
|[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 |
|[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 |
|[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 |
|[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 |
|[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 |
|[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 |
|[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 |
|[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 |
|[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 |
|[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 |
|[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 |
|[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 |
|[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 |
|[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 |
|[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 |
|[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 |
|[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 |
|[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 |
|[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 |
|[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 |
|[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 |
|[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 |
|[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 |
|[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 |
|[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 |
|[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 |
|[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 |
|[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 |
|[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 |
|[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 |
|[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 |
|[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 |
|[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 |
|[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 |
|[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 |
|[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 |
|[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 |
|[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 |
|[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 |
|[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 |
|[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 |
|[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 |
|[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 |
|[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 |
|[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 |
|[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 |
## Citation
```bibtex
@inproceedings{wightman2021resnet,
title={ResNet strikes back: An improved training procedure in timm},
author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@article{Xie2016,
title={Aggregated Residual Transformations for Deep Neural Networks},
author={Saining Xie and Ross Girshick and Piotr Dollár and Zhuowen Tu and Kaiming He},
journal={arXiv preprint arXiv:1611.05431},
year={2016}
}
```
```bibtex
@article{He2015,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Deep Residual Learning for Image Recognition},
journal = {arXiv preprint arXiv:1512.03385},
year = {2015}
}
```
```bibtex
@inproceedings{hu2018senet,
title={Squeeze-and-Excitation Networks},
author={Jie Hu and Li Shen and Gang Sun},
journal={IEEE Conference on Computer Vision and Pattern Recognition},
year={2018}
}
```
|
ostris/watercolor_style_lora_sdxl | ostris | "2023-08-15T01:57:12Z" | 1,937 | 22 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"sdxl",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:apache-2.0",
"region:us"
] | text-to-image | "2023-08-15T01:50:24Z" | ---
license: apache-2.0
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- sdxl
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt:
widget:
- text: darth vader fighting superman, 2 people, lightsaber
---
# Watercolor Style - SDXL LoRA
### Tips
- No trigger words needed.
- Converts any prompt into a watercolor picture
- Strength of 1.0 usually works but you may need to increase or decrease an needed.
### Samples
[<img src="https://huggingface.co/ostris/watercolor_style_lora_sdxl/resolve/main/samples/03007-1451488659-darth%20vader%20fighting%20superman%2C%202%20people%2C%20lightsaber%20_lora_watercolor_v1_sdxl_1_.jpeg" style="max-width:400px; height:auto" />](https://huggingface.co/ostris/watercolor_style_lora_sdxl/resolve/main/samples/03007-1451488659-darth%20vader%20fighting%20superman%2C%202%20people%2C%20lightsaber%20_lora_watercolor_v1_sdxl_1_.jpeg)
[<img src="https://huggingface.co/ostris/watercolor_style_lora_sdxl/resolve/main/samples/03014-3386049647-marty%20mcfly%20%20_lora_watercolor_v1_sdxl_1_.jpeg" style="max-width:400px; height:auto" />](https://huggingface.co/ostris/watercolor_style_lora_sdxl/resolve/main/samples/03014-3386049647-marty%20mcfly%20%20_lora_watercolor_v1_sdxl_1_.jpeg)
[<img src="https://huggingface.co/ostris/watercolor_style_lora_sdxl/resolve/main/samples/03026-3442519268-michael%20jackson%20in%20thriller%20video%20%20%20_lora_watercolor_v1_sdxl_1_.jpeg" style="max-width:400px; height:auto" />](https://huggingface.co/ostris/watercolor_style_lora_sdxl/resolve/main/samples/03026-3442519268-michael%20jackson%20in%20thriller%20video%20%20%20_lora_watercolor_v1_sdxl_1_.jpeg)
[<img src="https://huggingface.co/ostris/watercolor_style_lora_sdxl/resolve/main/samples/03035-1187541246-slimer%20from%20ghost%20busters%20%20%20_lora_watercolor_v1_sdxl_1_.jpeg" style="max-width:400px; height:auto" />](https://huggingface.co/ostris/watercolor_style_lora_sdxl/resolve/main/samples/03035-1187541246-slimer%20from%20ghost%20busters%20%20%20_lora_watercolor_v1_sdxl_1_.jpeg)
[<img src="https://huggingface.co/ostris/watercolor_style_lora_sdxl/resolve/main/samples/03042-3999946060-beavis%20and%20butthead%20%20_lora_watercolor_v1_sdxl_1_.jpeg" style="max-width:400px; height:auto" />](https://huggingface.co/ostris/watercolor_style_lora_sdxl/resolve/main/samples/03042-3999946060-beavis%20and%20butthead%20%20_lora_watercolor_v1_sdxl_1_.jpeg)
|
TheDrummer/Moistral-11B-v1-GGUF | TheDrummer | "2024-04-28T06:20:56Z" | 1,937 | 7 | null | [
"gguf",
"license:cc-by-nc-4.0",
"region:us"
] | null | "2024-03-20T11:55:08Z" | ---
license: cc-by-nc-4.0
---
https://huggingface.co/TheDrummer/Moistral-11B-v1
MERGED, BETTER versions: https://huggingface.co/TheDrummer/Moistral-11B-v1.1-MERGED-PCT-GGUF |
varox34/Bio-Saul-Dolphin-Beagle-Breadcrumbs | varox34 | "2024-05-02T06:22:16Z" | 1,937 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:cognitivecomputations/dolphin-2.6-mistral-7b",
"base_model:Equall/Saul-Instruct-v1",
"base_model:BioMistral/BioMistral-7B-SLERP",
"base_model:mlabonne/NeuralBeagle14-7B",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-01T13:52:11Z" | ---
base_model:
- cognitivecomputations/dolphin-2.6-mistral-7b
- Equall/Saul-Instruct-v1
- BioMistral/BioMistral-7B-SLERP
- mlabonne/NeuralBeagle14-7B
library_name: transformers
tags:
- mergekit
- merge
license: mit
---
# med-law-dolphin-beagle-merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the breadcrumbs merge method using [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B) as a base.
### Models Merged
The following models were included in the merge:
* [cognitivecomputations/dolphin-2.6-mistral-7b](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b)
* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
* [BioMistral/BioMistral-7B-SLERP](https://huggingface.co/BioMistral/BioMistral-7B-SLERP)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: Equall/Saul-Instruct-v1
parameters:
weight: 1.0
- model: BioMistral/BioMistral-7B-SLERP
parameters:
weight: 1.0
- model: cognitivecomputations/dolphin-2.6-mistral-7b
parameters:
weight: 0.5
merge_method: breadcrumbs
base_model: mlabonne/NeuralBeagle14-7B
parameters:
density: 0.9
gamma: 0.01
dtype: float16
``` |
timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k | timm | "2024-02-10T23:37:57Z" | 1,936 | 0 | timm | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:laion-2b",
"arxiv:2210.08402",
"arxiv:2201.03545",
"arxiv:2103.00020",
"license:apache-2.0",
"region:us"
] | image-classification | "2023-03-31T21:57:06Z" | ---
license: apache-2.0
library_name: timm
tags:
- image-classification
- timm
datasets:
- imagenet-1k
- laion-2b
---
# Model card for convnext_base.clip_laion2b_augreg_ft_in12k_in1k
A ConvNeXt image classification model. CLIP image tower weights pretrained in [OpenCLIP](https://github.com/mlfoundations/open_clip) on LAION and fine-tuned on ImageNet-12k followed by ImageNet-1k in `timm` bby Ross Wightman.
Please see related OpenCLIP model cards for more details on pretrain:
* https://huggingface.co/laion/CLIP-convnext_xxlarge-laion2B-s34B-b82K-augreg-soup
* https://huggingface.co/laion/CLIP-convnext_large_d.laion2B-s26B-b102K-augreg
* https://huggingface.co/laion/CLIP-convnext_base_w-laion2B-s13B-b82K-augreg
* https://huggingface.co/laion/CLIP-convnext_base_w_320-laion_aesthetic-s13B-b82K
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 88.6
- GMACs: 20.1
- Activations (M): 37.6
- Image size: 256 x 256
- **Papers:**
- LAION-5B: An open large-scale dataset for training next generation image-text models: https://arxiv.org/abs/2210.08402
- A ConvNet for the 2020s: https://arxiv.org/abs/2201.03545
- Learning Transferable Visual Models From Natural Language Supervision: https://arxiv.org/abs/2103.00020
- **Original:** https://github.com/mlfoundations/open_clip
- **Pretrain Dataset:** LAION-2B
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('convnext_base.clip_laion2b_augreg_ft_in12k_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'convnext_base.clip_laion2b_augreg_ft_in12k_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 128, 64, 64])
# torch.Size([1, 256, 32, 32])
# torch.Size([1, 512, 16, 16])
# torch.Size([1, 1024, 8, 8])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'convnext_base.clip_laion2b_augreg_ft_in12k_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1024, 8, 8) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
| model |top1 |top5 |img_size|param_count|gmacs |macts |samples_per_sec|batch_size|
|------------------------------------------------------------------------------------------------------------------------------|------|------|--------|-----------|------|------|---------------|----------|
| [convnextv2_huge.fcmae_ft_in22k_in1k_512](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_512) |88.848|98.742|512 |660.29 |600.81|413.07|28.58 |48 |
| [convnextv2_huge.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_384) |88.668|98.738|384 |660.29 |337.96|232.35|50.56 |64 |
| [convnext_xxlarge.clip_laion2b_soup_ft_in1k](https://huggingface.co/timm/convnext_xxlarge.clip_laion2b_soup_ft_in1k) |88.612|98.704|256 |846.47 |198.09|124.45|122.45 |256 |
| [convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384) |88.312|98.578|384 |200.13 |101.11|126.74|196.84 |256 |
| [convnextv2_large.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k_384) |88.196|98.532|384 |197.96 |101.1 |126.74|128.94 |128 |
| [convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320) |87.968|98.47 |320 |200.13 |70.21 |88.02 |283.42 |256 |
| [convnext_xlarge.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k_384) |87.75 |98.556|384 |350.2 |179.2 |168.99|124.85 |192 |
| [convnextv2_base.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k_384) |87.646|98.422|384 |88.72 |45.21 |84.49 |209.51 |256 |
| [convnext_large.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k_384) |87.476|98.382|384 |197.77 |101.1 |126.74|194.66 |256 |
| [convnext_large_mlp.clip_laion2b_augreg_ft_in1k](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_augreg_ft_in1k) |87.344|98.218|256 |200.13 |44.94 |56.33 |438.08 |256 |
| [convnextv2_large.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k) |87.26 |98.248|224 |197.96 |34.4 |43.13 |376.84 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384) |87.138|98.212|384 |88.59 |45.21 |84.49 |365.47 |256 |
| [convnext_xlarge.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k) |87.002|98.208|224 |350.2 |60.98 |57.5 |368.01 |256 |
| [convnext_base.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k_384) |86.796|98.264|384 |88.59 |45.21 |84.49 |366.54 |256 |
| [convnextv2_base.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k) |86.74 |98.022|224 |88.72 |15.38 |28.75 |624.23 |256 |
| [convnext_large.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k) |86.636|98.028|224 |197.77 |34.4 |43.13 |581.43 |256 |
| [convnext_base.clip_laiona_augreg_ft_in1k_384](https://huggingface.co/timm/convnext_base.clip_laiona_augreg_ft_in1k_384) |86.504|97.97 |384 |88.59 |45.21 |84.49 |368.14 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in12k_in1k](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k) |86.344|97.97 |256 |88.59 |20.09 |37.55 |816.14 |256 |
| [convnextv2_huge.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in1k) |86.256|97.75 |224 |660.29 |115.0 |79.07 |154.72 |256 |
| [convnext_small.in12k_ft_in1k_384](https://huggingface.co/timm/convnext_small.in12k_ft_in1k_384) |86.182|97.92 |384 |50.22 |25.58 |63.37 |516.19 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in1k](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in1k) |86.154|97.68 |256 |88.59 |20.09 |37.55 |819.86 |256 |
| [convnext_base.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k) |85.822|97.866|224 |88.59 |15.38 |28.75 |1037.66 |256 |
| [convnext_small.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k_384) |85.778|97.886|384 |50.22 |25.58 |63.37 |518.95 |256 |
| [convnextv2_large.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in1k) |85.742|97.584|224 |197.96 |34.4 |43.13 |375.23 |256 |
| [convnext_small.in12k_ft_in1k](https://huggingface.co/timm/convnext_small.in12k_ft_in1k) |85.174|97.506|224 |50.22 |8.71 |21.56 |1474.31 |256 |
| [convnext_tiny.in12k_ft_in1k_384](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k_384) |85.118|97.608|384 |28.59 |13.14 |39.48 |856.76 |256 |
| [convnextv2_tiny.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k_384) |85.112|97.63 |384 |28.64 |13.14 |39.48 |491.32 |256 |
| [convnextv2_base.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in1k) |84.874|97.09 |224 |88.72 |15.38 |28.75 |625.33 |256 |
| [convnext_small.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k) |84.562|97.394|224 |50.22 |8.71 |21.56 |1478.29 |256 |
| [convnext_large.fb_in1k](https://huggingface.co/timm/convnext_large.fb_in1k) |84.282|96.892|224 |197.77 |34.4 |43.13 |584.28 |256 |
| [convnext_tiny.in12k_ft_in1k](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k) |84.186|97.124|224 |28.59 |4.47 |13.44 |2433.7 |256 |
| [convnext_tiny.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k_384) |84.084|97.14 |384 |28.59 |13.14 |39.48 |862.95 |256 |
| [convnextv2_tiny.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k) |83.894|96.964|224 |28.64 |4.47 |13.44 |1452.72 |256 |
| [convnext_base.fb_in1k](https://huggingface.co/timm/convnext_base.fb_in1k) |83.82 |96.746|224 |88.59 |15.38 |28.75 |1054.0 |256 |
| [convnextv2_nano.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k_384) |83.37 |96.742|384 |15.62 |7.22 |24.61 |801.72 |256 |
| [convnext_small.fb_in1k](https://huggingface.co/timm/convnext_small.fb_in1k) |83.142|96.434|224 |50.22 |8.71 |21.56 |1464.0 |256 |
| [convnextv2_tiny.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in1k) |82.92 |96.284|224 |28.64 |4.47 |13.44 |1425.62 |256 |
| [convnext_tiny.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k) |82.898|96.616|224 |28.59 |4.47 |13.44 |2480.88 |256 |
| [convnext_nano.in12k_ft_in1k](https://huggingface.co/timm/convnext_nano.in12k_ft_in1k) |82.282|96.344|224 |15.59 |2.46 |8.37 |3926.52 |256 |
| [convnext_tiny_hnf.a2h_in1k](https://huggingface.co/timm/convnext_tiny_hnf.a2h_in1k) |82.216|95.852|224 |28.59 |4.47 |13.44 |2529.75 |256 |
| [convnext_tiny.fb_in1k](https://huggingface.co/timm/convnext_tiny.fb_in1k) |82.066|95.854|224 |28.59 |4.47 |13.44 |2346.26 |256 |
| [convnextv2_nano.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k) |82.03 |96.166|224 |15.62 |2.46 |8.37 |2300.18 |256 |
| [convnextv2_nano.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in1k) |81.83 |95.738|224 |15.62 |2.46 |8.37 |2321.48 |256 |
| [convnext_nano_ols.d1h_in1k](https://huggingface.co/timm/convnext_nano_ols.d1h_in1k) |80.866|95.246|224 |15.65 |2.65 |9.38 |3523.85 |256 |
| [convnext_nano.d1h_in1k](https://huggingface.co/timm/convnext_nano.d1h_in1k) |80.768|95.334|224 |15.59 |2.46 |8.37 |3915.58 |256 |
| [convnextv2_pico.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_pico.fcmae_ft_in1k) |80.304|95.072|224 |9.07 |1.37 |6.1 |3274.57 |256 |
| [convnext_pico.d1_in1k](https://huggingface.co/timm/convnext_pico.d1_in1k) |79.526|94.558|224 |9.05 |1.37 |6.1 |5686.88 |256 |
| [convnext_pico_ols.d1_in1k](https://huggingface.co/timm/convnext_pico_ols.d1_in1k) |79.522|94.692|224 |9.06 |1.43 |6.5 |5422.46 |256 |
| [convnextv2_femto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_femto.fcmae_ft_in1k) |78.488|93.98 |224 |5.23 |0.79 |4.57 |4264.2 |256 |
| [convnext_femto_ols.d1_in1k](https://huggingface.co/timm/convnext_femto_ols.d1_in1k) |77.86 |93.83 |224 |5.23 |0.82 |4.87 |6910.6 |256 |
| [convnext_femto.d1_in1k](https://huggingface.co/timm/convnext_femto.d1_in1k) |77.454|93.68 |224 |5.22 |0.79 |4.57 |7189.92 |256 |
| [convnextv2_atto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_atto.fcmae_ft_in1k) |76.664|93.044|224 |3.71 |0.55 |3.81 |4728.91 |256 |
| [convnext_atto_ols.a2_in1k](https://huggingface.co/timm/convnext_atto_ols.a2_in1k) |75.88 |92.846|224 |3.7 |0.58 |4.11 |7963.16 |256 |
| [convnext_atto.d2_in1k](https://huggingface.co/timm/convnext_atto.d2_in1k) |75.664|92.9 |224 |3.7 |0.55 |3.81 |8439.22 |256 |
## Citation
```bibtex
@software{ilharco_gabriel_2021_5143773,
author = {Ilharco, Gabriel and
Wortsman, Mitchell and
Wightman, Ross and
Gordon, Cade and
Carlini, Nicholas and
Taori, Rohan and
Dave, Achal and
Shankar, Vaishaal and
Namkoong, Hongseok and
Miller, John and
Hajishirzi, Hannaneh and
Farhadi, Ali and
Schmidt, Ludwig},
title = {OpenCLIP},
month = jul,
year = 2021,
note = {If you use this software, please cite it as below.},
publisher = {Zenodo},
version = {0.1},
doi = {10.5281/zenodo.5143773},
url = {https://doi.org/10.5281/zenodo.5143773}
}
```
```bibtex
@inproceedings{schuhmann2022laionb,
title={{LAION}-5B: An open large-scale dataset for training next generation image-text models},
author={Christoph Schuhmann and
Romain Beaumont and
Richard Vencu and
Cade W Gordon and
Ross Wightman and
Mehdi Cherti and
Theo Coombes and
Aarush Katta and
Clayton Mullis and
Mitchell Wortsman and
Patrick Schramowski and
Srivatsa R Kundurthy and
Katherine Crowson and
Ludwig Schmidt and
Robert Kaczmarczyk and
Jenia Jitsev},
booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2022},
url={https://openreview.net/forum?id=M3Y74vmsMcY}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@inproceedings{Radford2021LearningTV,
title={Learning Transferable Visual Models From Natural Language Supervision},
author={Alec Radford and Jong Wook Kim and Chris Hallacy and A. Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever},
booktitle={ICML},
year={2021}
}
```
```bibtex
@article{liu2022convnet,
author = {Zhuang Liu and Hanzi Mao and Chao-Yuan Wu and Christoph Feichtenhofer and Trevor Darrell and Saining Xie},
title = {A ConvNet for the 2020s},
journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2022},
}
```
|
wenge-research/yayi-13b-llama2 | wenge-research | "2023-09-13T02:24:34Z" | 1,936 | 7 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"yayi",
"zh",
"en",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-21T10:10:40Z" | ---
language:
- zh
- en
pipeline_tag: text-generation
tags:
- yayi
---
# 雅意大模型
## 介绍
[雅意大模型](https://www.wenge.com/yayi/index.html)在百万级人工构造的高质量领域数据上进行指令微调得到，训练数据覆盖媒体宣传、舆情分析、公共安全、金融风控、城市治理等五大领域，上百种自然语言指令任务。雅意大模型从预训练初始化权重到领域模型的迭代过程中，我们逐步增强了它的中文基础能力和领域分析能力，并增加了多轮对话和部分插件能力。同时，经过数百名用户内测过程中持续不断的人工反馈优化，我们进一步提升了模型性能和安全性。
通过雅意大模型的开源为促进中文预训练大模型开源社区的发展，贡献自己的一份力量，通过开源，与每一位合作伙伴共建雅意大模型生态。
*News: 🔥 雅意大模型已开源基于 LLaMA 2 的中文优化模型版本，探索适用于中文多领域任务的最新实践。*
## 模型地址
| 模型名称 | 🤗HF模型标识 | 下载地址 |
| --------- | --------- | --------- |
| YaYi-7B | wenge-research/yayi-7b | [模型下载](https://huggingface.co/wenge-research/yayi-7b) |
| YaYi-7B-Llama2 | wenge-research/yayi-7b-llama2 | [模型下载](https://huggingface.co/wenge-research/yayi-7b-llama2) |
| YaYi-13B-Llama2 | wenge-research/yayi-13b-llama2 | [模型下载](https://huggingface.co/wenge-research/yayi-13b-llama2) |
| YaYi-70B-Llama2 | wenge-research/yayi-70b-llama2 | [模型下载](https://huggingface.co/wenge-research/yayi-70b-llama2) |
详情请参考我们的 [💻Github Repo](https://github.com/wenge-research/YaYi)。
## 运行方式
```python
import torch
from transformers import LlamaForCausalLM, LlamaTokenizer, GenerationConfig
from transformers import StoppingCriteria, StoppingCriteriaList
pretrained_model_name_or_path = "wenge-research/yayi-13b-llama2"
tokenizer = LlamaTokenizer.from_pretrained(pretrained_model_name_or_path)
model = LlamaForCausalLM.from_pretrained(pretrained_model_name_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=False)
# Define the stopping criteria
class KeywordsStoppingCriteria(StoppingCriteria):
def __init__(self, keywords_ids:list):
self.keywords = keywords_ids
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
if input_ids[0][-1] in self.keywords:
return True
return False
stop_words = ["<|End|>", "<|YaYi|>", "<|Human|>", "</s>"]
stop_ids = [tokenizer.encode(w)[-1] for w in stop_words]
stop_criteria = KeywordsStoppingCriteria(stop_ids)
# inference
prompt = "你是谁？"
formatted_prompt = f"""<|System|>:
You are a helpful, respectful and honest assistant named YaYi developed by Beijing Wenge Technology Co.,Ltd. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<|Human|>:
{prompt}
<|YaYi|>:
"""
inputs = tokenizer(formatted_prompt, return_tensors="pt").to(model.device)
eos_token_id = tokenizer("<|End|>").input_ids[0]
generation_config = GenerationConfig(
eos_token_id=eos_token_id,
pad_token_id=eos_token_id,
do_sample=True,
max_new_tokens=256,
temperature=0.3,
repetition_penalty=1.1,
no_repeat_ngram_size=0
)
response = model.generate(**inputs, generation_config=generation_config, stopping_criteria=StoppingCriteriaList([stop_criteria]))
response = [response[0][len(inputs.input_ids[0]):]]
response_str = tokenizer.batch_decode(response, skip_special_tokens=False, clean_up_tokenization_spaces=False)[0]
print(response_str)
```
---
# YaYi
## Introduction
[YaYi](https://www.wenge.com/yayi/index.html) was fine-tuned on millions of artificially constructed high-quality domain data. This training data covers five key domains: media publicity, public opinion analysis, public safety, financial risk control, and urban governance, encompassing over a hundred natural language instruction tasks. Throughout the iterative development process of the YaYi, starting from pre-training initialization weights and progressing to domain-specific model, we have steadily enhanced its foundational Chinese language capabilities and domain analysis capabilities. We've also introduced multi-turn conversation enhancements and integrated various plug-in capabilities. Furthermore, through continuous manual feedback and optimization from hundreds of users during the internal testing phase, we've meticulously refined the model's performance and security.
By open-sourcing the YaYi model, we will contribute our own efforts to the development of the Chinese pre-trained large language model open-source community. Through this open-source initiative, we seek to collaborate with every partner to build the YaYi model ecosystem together.
*News: 🔥 YaYi has open sourced the Chinese optimization model version based on LLaMA 2 to explore the latest practices suitable for Chinese multi-domain tasks.*
## Model download
| Model | 🤗HF Model Name | Download Links |
| --------- | --------- | --------- |
| YaYi-7B | wenge-research/yayi-7b | [Download](https://huggingface.co/wenge-research/yayi-7b) |
| YaYi-7B-Llama2 | wenge-research/yayi-7b-llama2 | [Download](https://huggingface.co/wenge-research/yayi-7b-llama2) |
| YaYi-13B-Llama2 | wenge-research/yayi-13b-llama2 | [Download](https://huggingface.co/wenge-research/yayi-13b-llama2) |
| YaYi-70B-Llama2 | wenge-research/yayi-70b-llama2 | [Download](https://huggingface.co/wenge-research/yayi-70b-llama2) |
For more details, please refer to our [💻Github Repo](https://github.com/wenge-research/YaYi)。
## Run
```python
import torch
from transformers import LlamaForCausalLM, LlamaTokenizer, GenerationConfig
from transformers import StoppingCriteria, StoppingCriteriaList
pretrained_model_name_or_path = "wenge-research/yayi-13b-llama2"
tokenizer = LlamaTokenizer.from_pretrained(pretrained_model_name_or_path)
model = LlamaForCausalLM.from_pretrained(pretrained_model_name_or_path, device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=False)
# Define the stopping criteria
class KeywordsStoppingCriteria(StoppingCriteria):
def __init__(self, keywords_ids:list):
self.keywords = keywords_ids
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
if input_ids[0][-1] in self.keywords:
return True
return False
stop_words = ["<|End|>", "<|YaYi|>", "<|Human|>", "</s>"]
stop_ids = [tokenizer.encode(w)[-1] for w in stop_words]
stop_criteria = KeywordsStoppingCriteria(stop_ids)
# inference
prompt = "你是谁？"
formatted_prompt = f"""<|System|>:
You are a helpful, respectful and honest assistant named YaYi developed by Beijing Wenge Technology Co.,Ltd. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<|Human|>:
{prompt}
<|YaYi|>:
"""
inputs = tokenizer(formatted_prompt, return_tensors="pt").to(model.device)
eos_token_id = tokenizer("<|End|>").input_ids[0]
generation_config = GenerationConfig(
eos_token_id=eos_token_id,
pad_token_id=eos_token_id,
do_sample=True,
max_new_tokens=256,
temperature=0.3,
repetition_penalty=1.1,
no_repeat_ngram_size=0
)
response = model.generate(**inputs, generation_config=generation_config, stopping_criteria=StoppingCriteriaList([stop_criteria]))
response = [response[0][len(inputs.input_ids[0]):]]
response_str = tokenizer.batch_decode(response, skip_special_tokens=False, clean_up_tokenization_spaces=False)[0]
print(response_str)
```
|
chujiezheng/Smaug-34B-v0.1-ExPO | chujiezheng | "2024-05-29T21:00:12Z" | 1,936 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"zh",
"arxiv:2404.16792",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-29T20:48:34Z" | ---
license: other
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
language:
- en
- zh
---
# Smaug-34B-v0.1-ExPO
The extrapolated (ExPO) model based on [`abacusai/Smaug-34B-v0.1`](https://huggingface.co/abacusai/Smaug-34B-v0.1) and [`jondurbin/bagel-34b-v0.2`](https://huggingface.co/jondurbin/bagel-34b-v0.2), as in the "[Weak-to-Strong Extrapolation Expedites Alignment](https://arxiv.org/abs/2404.16792)" paper.
Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.
## Evaluation Results
Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_alpaca)):
| | Win Rate (Ori) | LC Win Rate (Ori) | Win Rate (+ ExPO) | LC Win Rate (+ ExPO) |
| ------------------------------------ | -------------- | ----------------- | ----------------- | -------------------- |
| `HuggingFaceH4/zephyr-7b-alpha` | 6.7% | 10.0% | **10.6%** | **13.6%** |
| `HuggingFaceH4/zephyr-7b-beta` | 10.2% | 13.2% | **11.1%** | **14.0%** |
| `berkeley-nest/Starling-LM-7B-alpha` | 15.0% | 18.3% | **18.2%** | **19.5%** |
| `Nexusflow/Starling-LM-7B-beta` | 26.6% | 25.8% | **29.6%** | **26.4%** |
| `snorkelai/Snorkel-Mistral-PairRM` | 24.7% | 24.0% | **28.8%** | **26.4%** |
| `RLHFlow/LLaMA3-iterative-DPO-final` | 29.2% | 36.0% | **32.7%** | **37.8%** |
| `internlm/internlm2-chat-1.8b` | 3.8% | 4.0% | **5.2%** | **4.3%** |
| `internlm/internlm2-chat-7b` | 20.5% | 18.3% | **28.1%** | **22.7%** |
| `internlm/internlm2-chat-20b` | 36.1% | 24.9% | **46.2%** | **27.2%** |
| `allenai/tulu-2-dpo-7b` | 8.5% | 10.2% | **11.5%** | **11.7%** |
| `allenai/tulu-2-dpo-13b` | 11.2% | 15.5% | **15.6%** | **17.6%** |
| `allenai/tulu-2-dpo-70b` | 15.4% | 21.2% | **23.0%** | **25.7%** |
Evaluation results on the **MT-Bench** benchmark (you can find the evaluation outputs on the [official GitHub repo](https://github.com/chujiezheng/LLM-Extrapolation/tree/main/results_mtbench)):
| | Original | + ExPO |
| ------------------------------------ | -------- | -------- |
| `HuggingFaceH4/zephyr-7b-alpha` | 6.85 | **6.87** |
| `HuggingFaceH4/zephyr-7b-beta` | 7.02 | **7.06** |
| `berkeley-nest/Starling-LM-7B-alpha` | 7.82 | **7.91** |
| `Nexusflow/Starling-LM-7B-beta` | 8.10 | **8.18** |
| `snorkelai/Snorkel-Mistral-PairRM` | 7.63 | **7.69** |
| `RLHFlow/LLaMA3-iterative-DPO-final` | 8.08 | **8.45** |
| `internlm/internlm2-chat-1.8b` | 5.17 | **5.26** |
| `internlm/internlm2-chat-7b` | 7.72 | **7.80** |
| `internlm/internlm2-chat-20b` | 8.13 | **8.26** |
| `allenai/tulu-2-dpo-7b` | 6.35 | **6.38** |
| `allenai/tulu-2-dpo-13b` | 7.00 | **7.26** |
| `allenai/tulu-2-dpo-70b` | 7.79 | **8.03** |
|
kakao-enterprise/vits-ljs | kakao-enterprise | "2023-09-07T15:41:08Z" | 1,935 | 18 | transformers | [
"transformers",
"pytorch",
"safetensors",
"vits",
"text-to-audio",
"text-to-speech",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-to-speech | "2023-08-31T10:35:14Z" | ---
license: mit
tags:
- vits
pipeline_tag: text-to-speech
---
# VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
VITS is an end-to-end speech synthesis model that predicts a speech waveform conditional on an input text sequence. It is a
conditional variational autoencoder (VAE) comprised of a posterior encoder, decoder, and conditional prior. This repository
contains the weights for the official VITS checkpoint trained on the [LJ Speech](https://huggingface.co/datasets/lj_speech) dataset.
## Model Details
VITS (**V**ariational **I**nference with adversarial learning for end-to-end **T**ext-to-**S**peech) is an end-to-end
speech synthesis model that predicts a speech waveform conditional on an input text sequence. It is a conditional variational
autoencoder (VAE) comprised of a posterior encoder, decoder, and conditional prior.
A set of spectrogram-based acoustic features are predicted by the flow-based module, which is formed of a Transformer-based
text encoder and multiple coupling layers. The spectrogram is decoded using a stack of transposed convolutional layers,
much in the same style as the HiFi-GAN vocoder. Motivated by the one-to-many nature of the TTS problem, where the same text
input can be spoken in multiple ways, the model also includes a stochastic duration predictor, which allows the model to
synthesise speech with different rhythms from the same input text.
The model is trained end-to-end with a combination of losses derived from variational lower bound and adversarial training.
To improve the expressiveness of the model, normalizing flows are applied to the conditional prior distribution. During
inference, the text encodings are up-sampled based on the duration prediction module, and then mapped into the
waveform using a cascade of the flow module and HiFi-GAN decoder. Due to the stochastic nature of the duration predictor,
the model is non-deterministic, and thus requires a fixed seed to generate the same speech waveform.
There are two variants of the VITS model: one is trained on the [LJ Speech](https://huggingface.co/datasets/lj_speech) dataset,
and the other is trained on the [VCTK](https://huggingface.co/datasets/vctk) dataset. LJ Speech dataset consists of 13,100 short
audio clips of a single speaker with a total length of approximately 24 hours. The VCTK dataset consists of approximately 44,000
short audio clips uttered by 109 native English speakers with various accents. The total length of the audio clips is approximately
44 hours.
| Checkpoint | Train Hours | Speakers |
|------------|-------------|----------|
| [vits-ljs](https://huggingface.co/kakao-enterprise/vits-ljs) | 24 | 1 |
| [vits-vctk](https://huggingface.co/kakao-enterprise/vits-vctk) | 44 | 109 |
## Usage
VITS is available in the 🤗 Transformers library from version 4.33 onwards. To use this checkpoint,
first install the latest version of the library:
```
pip install --upgrade transformers accelerate
```
Then, run inference with the following code-snippet:
```python
from transformers import VitsModel, AutoTokenizer
import torch
model = VitsModel.from_pretrained("kakao-enterprise/vits-ljs")
tokenizer = AutoTokenizer.from_pretrained("kakao-enterprise/vits-ljs")
text = "Hey, it's Hugging Face on the phone"
inputs = tokenizer(text, return_tensors="pt")
with torch.no_grad():
output = model(**inputs).waveform
```
The resulting waveform can be saved as a `.wav` file:
```python
import scipy
scipy.io.wavfile.write("techno.wav", rate=model.config.sampling_rate, data=output)
```
Or displayed in a Jupyter Notebook / Google Colab:
```python
from IPython.display import Audio
Audio(output, rate=model.config.sampling_rate)
```
## BibTex citation
This model was developed by Jaehyeon Kim et al. from Kakao Enterprise. If you use the model, consider citing the VITS paper:
```
@inproceedings{kim2021conditional,
title={"Conditional Variational Autoencoder with Adversarial Learning for End-to-end Text-to-speech"},
author={Kim, Jaehyeon and Kong, Jungil and Son, Juhee},
booktitle={International Conference on Machine Learning},
pages={5530--5540},
year={2021},
organization={PMLR}
}
```
## License
The model is licensed as [**MIT**](https://github.com/jaywalnut310/vits/blob/main/LICENSE). |
tonyassi/mgm | tonyassi | "2024-02-26T16:43:20Z" | 1,935 | 4 | diffusers | [
"diffusers",
"tensorboard",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | text-to-image | "2023-11-30T20:30:03Z" |
---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: mgm film
license: openrail++
---
# SDXL LoRA DreamBooth - tonyassi/mgm
by [Tony Assi](https://www.tonyassi.com/)
Dreambooth style based on classic MGM Films. Try the [demo](https://huggingface.co/spaces/tonyassi/MGM-Film-Diffusion).
## Trigger words
Use **mgm film** in the prompt to trigger the MGM style.
## How to use
```bash
pip install diffusers accelerate
```
```python
import torch
from diffusers import DiffusionPipeline, AutoencoderKL
# Load the pipeline
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
vae=vae,
torch_dtype=torch.float16,
variant="fp16",
use_safetensors=True
)
pipe.load_lora_weights("tonyassi/mgm")
pipe.to("cuda")
# Generate image
prompt = "mgm film megan fox pinup girl"
image = pipe(prompt=prompt,
height=1024,
width=1024,
num_inference_steps=50,
negative_prompt="ugly, deformed face, deformed body").images[0]
image
```
## Examples
**mgm film bettie page outside a mansion with two poodles**
**mgm film asap rocky eating in a fancy restaurant, 1950s**
**mgm film megan fox pinup girl**
**mgm film lady gaga in a limo, neon lights, pet snake**
**mgm film asap rocky in the wizard of oz**
## Model description
These are tonyassi/mgm LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Download model
Weights for this model are available in Safetensors format.
[Download](https://huggingface.co/tonyassi/mgm/tree/main) them in the Files & versions tab.
|
sail/Sailor-1.8B | sail | "2024-04-26T05:40:13Z" | 1,935 | 7 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"multilingual",
"sea",
"sailor",
"conversational",
"en",
"zh",
"id",
"th",
"vi",
"ms",
"lo",
"dataset:cerebras/SlimPajama-627B",
"dataset:Skywork/SkyPile-150B",
"dataset:allenai/MADLAD-400",
"dataset:cc100",
"arxiv:2404.03608",
"base_model:Qwen/Qwen1.5-1.8B",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-29T05:53:03Z" | ---
language:
- en
- zh
- id
- th
- vi
- ms
- lo
datasets:
- cerebras/SlimPajama-627B
- Skywork/SkyPile-150B
- allenai/MADLAD-400
- cc100
tags:
- multilingual
- sea
- sailor
license: apache-2.0
base_model: Qwen/Qwen1.5-1.8B
inference: false
model-index:
- name: Sailor-1.8B
results:
- task:
type: text-generation
dataset:
name: XQuAD-Thai
type: XQuAD-Thai
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 32.72
- name: F1 (3-Shot)
type: F1 (3-Shot)
value: 48.66
- task:
type: text-generation
dataset:
name: TyDiQA-Indonesian
type: TyDiQA-Indonesian
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 40.88
- name: F1 (3-Shot)
type: F1 (3-Shot)
value: 65.37
- task:
type: text-generation
dataset:
name: XQuAD-Vietnamese
type: XQuAD-Vietnamese
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 34.22
- name: F1 (3-Shot)
type: F1 (3-Shot)
value: 53.35
- task:
type: text-generation
dataset:
name: XCOPA-Thai
type: XCOPA-Thai
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 53.8
- task:
type: text-generation
dataset:
name: XCOPA-Indonesian
type: XCOPA-Indonesian
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 64.20
- task:
type: text-generation
dataset:
name: XCOPA-Vietnamese
type: XCOPA-Vietnamese
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 63.20
- task:
type: text-generation
dataset:
name: M3Exam-Thai
type: M3Exam-Thai
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 25.38
- task:
type: text-generation
dataset:
name: M3Exam-Indonesian
type: M3Exam-Indonesian
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 28.30
- task:
type: text-generation
dataset:
name: M3Exam-Vietnamese
type: M3Exam-Vietnamese
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 34.71
- task:
type: text-generation
dataset:
name: BELEBELE-Thai
type: BELEBELE-Thai
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 34.22
- task:
type: text-generation
dataset:
name: BELEBELE-Indonesian
type: BELEBELE-Indonesian
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 34.89
- task:
type: text-generation
dataset:
name: BELEBELE-Vietnamese
type: BELEBELE-Vietnamese
metrics:
- name: EM (3-Shot)
type: EM (3-Shot)
value: 35.33
---
<div align="center">
<img src="banner_sailor.jpg" width="700"/>
</div>
Sailor is a suite of Open Language Models tailored for South-East Asia (SEA), focusing on languages such as 🇮🇩Indonesian, 🇹🇭Thai, 🇻🇳Vietnamese, 🇲🇾Malay, and 🇱🇦Lao.
Developed with careful data curation, Sailor models are designed to understand and generate text across diverse linguistic landscapes of SEA region.
Built from [Qwen 1.5](https://huggingface.co/collections/Qwen/qwen15-65c0a2f577b1ecb76d786524) , Sailor encompasses models of varying sizes, spanning from 0.5B to 7B versions for different requirements.
We further fine-tune the base model with open-source datasets to get instruction-tuned models, namedly Sailor-Chat.
Benchmarking results demonstrate Sailor's proficiency in tasks such as question answering, commonsense reasoning, and other tasks in SEA languages.
> The logo was generated by MidJourney
## Model Summary
- **Model Collections:** [Base Model & Chat Model](https://huggingface.co/collections/sail/sailor-65e19a749f978976f1959825)
- **Project Website:** [sailorllm.github.io](https://sailorllm.github.io/)
- **Codebase:** [github.com/sail-sg/sailor-llm](https://github.com/sail-sg/sailor-llm)
- **Technical Report:** [arxiv.org/pdf/2404.03608.pdf](https://arxiv.org/pdf/2404.03608.pdf)
## Training details
Sailor is crafted by continually pre-training from language models like the remarkable Qwen 1.5 models, which already has a great performance on SEA languages.
The pre-training corpus heavily leverages the publicly available corpus, including
[SlimPajama](https://huggingface.co/datasets/cerebras/SlimPajama-627B),
[SkyPile](https://huggingface.co/datasets/Skywork/SkyPile-150B),
[CC100](https://huggingface.co/datasets/cc100) and [MADLAD-400](https://huggingface.co/datasets/allenai/MADLAD-400).
By employing aggressive data deduplication and careful data cleaning on the collected corpus, we have attained a high-quality dataset spanning various languages.
Through systematic experiments to determine the weights of different languages, Sailor models undergo training from 200B to 400B tokens, tailored to different model sizes.
The approach boosts their performance on SEA languages while maintaining proficiency in English and Chinese without significant compromise.
Finally, we continually pre-train the Qwen1.5-0.5B model with 400 Billion tokens, and other models with 200 Billion tokens to obtain the Sailor models.
## Requirements
The code of Sailor has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`.
## Quickstart
Here provides a code snippet to show you how to load the tokenizer and model and how to generate contents.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model
model = AutoModelForCausalLM.from_pretrained("sail/Sailor-1.8B", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("sail/Sailor-1.8B")
input_message = "Model bahasa adalah model probabilistik"
### The given Indonesian input translates to 'A language model is a probabilistic model of.'
model_inputs = tokenizer([input_message], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=64
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
```
# License
Sailor is distributed under the terms of the Apache License 2.0.
No restrict on the research and the commercial use, but should comply with the [Qwen License](https://huggingface.co/Qwen/Qwen1.5-1.8B/blob/main/LICENSE).
## Citation
If you find sailor useful, please cite our work as follows:
```
@misc{dou2024sailor,
title={Sailor: Open Language Models for South-East Asia},
author={Longxu Dou and Qian Liu and Guangtao Zeng and Jia Guo and Jiahui Zhou and Wei Lu and Min Lin},
year={2024},
eprint={2404.03608},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
# Contact Us
If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]) or [[email protected]](mailto:[email protected]). |
abhinand/Llama-3-OpenBioMed-8B-slerp-v0.3 | abhinand | "2024-05-03T12:18:11Z" | 1,935 | 2 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"Jayant9928/orpo_med_v3",
"skumar9/Llama-medx_v3",
"conversational",
"base_model:Jayant9928/orpo_med_v3",
"base_model:skumar9/Llama-medx_v3",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-02T03:36:58Z" | ---
tags:
- merge
- mergekit
- lazymergekit
- Jayant9928/orpo_med_v3
- skumar9/Llama-medx_v3
base_model:
- Jayant9928/orpo_med_v3
- skumar9/Llama-medx_v3
license: llama3
---
> **CAUTION:** This model scores high on the Leaderboard but outputs gibberish!
# Llama-3-OpenBioMed-8B-slerp-v0.3
Llama-3-OpenBioMed-8B-slerp-v0.3 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Jayant9928/orpo_med_v3](https://huggingface.co/Jayant9928/orpo_med_v3)
* [skumar9/Llama-medx_v3](https://huggingface.co/skumar9/Llama-medx_v3)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: Jayant9928/orpo_med_v3
layer_range: [0, 32]
- model: skumar9/Llama-medx_v3
layer_range: [0, 32]
merge_method: slerp
base_model: Jayant9928/orpo_med_v3
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "abhinand/Llama-3-OpenBioMed-8B-slerp-v0.3"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` |
gradientai/Llama-3-70B-Instruct-Gradient-1048k | gradientai | "2024-05-05T05:09:20Z" | 1,935 | 107 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"meta",
"llama-3",
"conversational",
"en",
"license:llama3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-05-03T21:35:46Z" | ---
language:
- en
pipeline_tag: text-generation
tags:
- meta
- llama-3
license: llama3
---
<a href="https://www.gradient.ai" target="_blank"><img src="https://cdn-uploads.huggingface.co/production/uploads/655bb613e8a8971e89944f3e/TSa3V8YpoVagnTYgxiLaO.png" width="200"/></a>
# Llama-3 70B Instruct Gradient 1048K
Join our custom agent and long context (262k-1M+) waitlist: https://forms.gle/L6TDY7dozx8TuoUv7
Gradient incorporates your data to deploy autonomous assistants that power critical operations across your business. If you're looking to build custom AI models or agents, email us a message [email protected].
For more info see our [End-to-end development service for custom LLMs and AI systems](https://gradient.ai/development-lab)
[Join our Discord](https://discord.com/invite/2QVy2qt2mf)
This model extends LLama-3 70B's context length from 8k to > 1048K, developed by Gradient, sponsored by compute from [Crusoe Energy](https://huggingface.co/crusoeai). It demonstrates that SOTA LLMs can learn to operate on long context with minimal training by appropriately adjusting RoPE theta. We trained on 34M tokens for this stage, and ~430M tokens total for all stages, which is < 0.003% of Llama-3's original pre-training data.
**Approach:**
- [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) as the base
- NTK-aware interpolation [4] following scaling laws [2] to set optimal schedule for RoPE theta
- Progressive training on increasing context lengths, similar to [Large World Model](https://huggingface.co/LargeWorldModel) [1] (See details below)
**Infra:**
We build on top of the EasyContext Blockwise RingAttention library [5] to scalably and efficiently train on very long contexts on [Crusoe Energy](https://huggingface.co/crusoeai) high performance L40S cluster.
We layered parallelism on top of Ring Attention with a custom network topology to better leverage large GPU clusters in the face of network bottlenecks from passing many KV blocks between devices.
**Data:**
For training data, we generate long contexts by augmenting [SlimPajama](https://huggingface.co/datasets/cerebras/SlimPajama-627B). We also fine-tune on a chat dataset based on UltraChat [3], following a similar recipe for data augmentation to [1].
**Progressive Training Details:**
| | 65K | 262K | 524K | 1048k |
|------------------------|-------------|-------------|-------------|-------------|
| Initialize From | Llama-3-70B-Instruct | 65K | 262K | 524K |
| Sequence Length 2^N | 16 | 18 | 19 | 20 |
| RoPE theta | 15296098 | 207112184 | 1062356830 | 3580165449 |
| Batch Size | 64 | 16 | 8 | 1 |
| Gradient Accumulation Steps | 1 | 1 | 2 | 4 |
| Steps | 20 | 25 | 25 | 8 |
| Total Tokens | 83886080 | 104857600 | 209715200 | 33554432 |
| Learning rate | 2.00E-05 | 2.00E-05 | 2.00E-05 | 2.00E-05 |
| # GPUs | 512 | 512 | 512 | 128 |
| GPU Type | NVIDIA L40S | NVIDIA L40S | NVIDIA L40S | NVIDIA L40S |
| Minutes to Train (Wall)| 100 | 170 | 284 | 516 |
**Evaluation Details:**
```
EVAL_MAX_CONTEXT_LENGTH=1140200
EVAL_MIN_CONTEXT_LENGTH=100
EVAL_CONTEXT_INTERVAL=86675
EVAL_DEPTH_INTERVAL=0.2
EVAL_NUM_SAMPLES=1
EVAL_RND_NUMBER_DIGITS=8
HAYSTACK:
EVAL_GENERATOR_TOKENS=925000
```
Haystack is "haystack 3", further detailed in this [blog post](https://gradient.ai/blog/the-haystack-matters-for-niah-evals).
**Quants:**
## The Gradient AI Team
https://gradient.ai/
Gradient is accelerating AI transformation across industries. Our AI Foundry incorporates your data to deploy autonomous assistants that power critical operations across your business.
## Contact Us
Drop an email to [[email protected]](mailto:[email protected])
## References
[1] Liu, Hao, et al. "World Model on Million-Length Video And Language With RingAttention." arXiv preprint arXiv:2402.08268 (2024).
[2] Liu, Xiaoran, et al. "Scaling laws of rope-based extrapolation." arXiv preprint arXiv:2310.05209 (2023).
[3] Ning Ding, Yulin Chen, Bokai Xu, Yujia Qin, Zhi Zheng, Shengding Hu, Zhiyuan
Liu, Maosong Sun, and Bowen Zhou. Enhancing chat language models by scaling
high-quality instructional conversations. arXiv preprint arXiv:2305.14233, 2023.
[4] Peng, Bowen, et al. "Yarn: Efficient context window extension of large language models." arXiv preprint arXiv:2309.00071 (2023).
[5] https://github.com/jzhang38/EasyContext
----
# Base Model
## Model Details
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety.
**Model developers** Meta
**Variations** Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants.
**Input** Models input text only.
**Output** Models generate text and code only.
**Model Architecture** Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
<table>
<tr>
<td>
</td>
<td><strong>Training Data</strong>
</td>
<td><strong>Params</strong>
</td>
<td><strong>Context length</strong>
</td>
<td><strong>GQA</strong>
</td>
<td><strong>Token count</strong>
</td>
<td><strong>Knowledge cutoff</strong>
</td>
</tr>
<tr>
<td rowspan="2" >Llama 3
</td>
<td rowspan="2" >A new mix of publicly available online data.
</td>
<td>8B
</td>
<td>8k
</td>
<td>Yes
</td>
<td rowspan="2" >15T+
</td>
<td>March, 2023
</td>
</tr>
<tr>
<td>70B
</td>
<td>8k
</td>
<td>Yes
</td>
<td>December, 2023
</td>
</tr>
</table>
**Llama 3 family of models**. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date** April 18, 2024.
**Status** This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license)
Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases** Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks.
**Out-of-scope** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English**.
**Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy.
## How to use
This repository contains two versions of Meta-Llama-3-70B-Instruct, for use with transformers and with the original `llama3` codebase.
### Use with transformers
See the snippet below for usage with Transformers:
```python
import transformers
import torch
model_id = "meta-llama/Meta-Llama-3-70B-Instruct"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
prompt = pipeline.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
terminators = [
pipeline.tokenizer.eos_token_id,
pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = pipeline(
prompt,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```
### Use with `llama3`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3).
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Meta-Llama-3-70B-Instruct --include "original/*" --local-dir Meta-Llama-3-70B-Instruct
```
For Hugging Face support, we recommend using transformers or TGI, but a similar command works.
## Hardware and Software
**Training Factors** We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.
**Carbon Footprint Pretraining utilized a cumulative** 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.
<table>
<tr>
<td>
</td>
<td><strong>Time (GPU hours)</strong>
</td>
<td><strong>Power Consumption (W)</strong>
</td>
<td><strong>Carbon Emitted(tCO2eq)</strong>
</td>
</tr>
<tr>
<td>Llama 3 8B
</td>
<td>1.3M
</td>
<td>700
</td>
<td>390
</td>
</tr>
<tr>
<td>Llama 3 70B
</td>
<td>6.4M
</td>
<td>700
</td>
<td>1900
</td>
</tr>
<tr>
<td>Total
</td>
<td>7.7M
</td>
<td>
</td>
<td>2290
</td>
</tr>
</table>
**CO2 emissions during pre-training**. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.
## Training Data
**Overview** Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.
**Data Freshness** The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.
## Benchmarks
In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md).
### Base pretrained models
<table>
<tr>
<td><strong>Category</strong>
</td>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama2 7B</strong>
</td>
<td><strong>Llama2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama2 70B</strong>
</td>
</tr>
<tr>
<td rowspan="6" >General
</td>
<td>MMLU (5-shot)
</td>
<td>66.6
</td>
<td>45.7
</td>
<td>53.8
</td>
<td>79.5
</td>
<td>69.7
</td>
</tr>
<tr>
<td>AGIEval English (3-5 shot)
</td>
<td>45.9
</td>
<td>28.8
</td>
<td>38.7
</td>
<td>63.0
</td>
<td>54.8
</td>
</tr>
<tr>
<td>CommonSenseQA (7-shot)
</td>
<td>72.6
</td>
<td>57.6
</td>
<td>67.6
</td>
<td>83.8
</td>
<td>78.7
</td>
</tr>
<tr>
<td>Winogrande (5-shot)
</td>
<td>76.1
</td>
<td>73.3
</td>
<td>75.4
</td>
<td>83.1
</td>
<td>81.8
</td>
</tr>
<tr>
<td>BIG-Bench Hard (3-shot, CoT)
</td>
<td>61.1
</td>
<td>38.1
</td>
<td>47.0
</td>
<td>81.3
</td>
<td>65.7
</td>
</tr>
<tr>
<td>ARC-Challenge (25-shot)
</td>
<td>78.6
</td>
<td>53.7
</td>
<td>67.6
</td>
<td>93.0
</td>
<td>85.3
</td>
</tr>
<tr>
<td>Knowledge reasoning
</td>
<td>TriviaQA-Wiki (5-shot)
</td>
<td>78.5
</td>
<td>72.1
</td>
<td>79.6
</td>
<td>89.7
</td>
<td>87.5
</td>
</tr>
<tr>
<td rowspan="4" >Reading comprehension
</td>
<td>SQuAD (1-shot)
</td>
<td>76.4
</td>
<td>72.2
</td>
<td>72.1
</td>
<td>85.6
</td>
<td>82.6
</td>
</tr>
<tr>
<td>QuAC (1-shot, F1)
</td>
<td>44.4
</td>
<td>39.6
</td>
<td>44.9
</td>
<td>51.1
</td>
<td>49.4
</td>
</tr>
<tr>
<td>BoolQ (0-shot)
</td>
<td>75.7
</td>
<td>65.5
</td>
<td>66.9
</td>
<td>79.0
</td>
<td>73.1
</td>
</tr>
<tr>
<td>DROP (3-shot, F1)
</td>
<td>58.4
</td>
<td>37.9
</td>
<td>49.8
</td>
<td>79.7
</td>
<td>70.2
</td>
</tr>
</table>
### Instruction tuned models
<table>
<tr>
<td><strong>Benchmark</strong>
</td>
<td><strong>Llama 3 8B</strong>
</td>
<td><strong>Llama 2 7B</strong>
</td>
<td><strong>Llama 2 13B</strong>
</td>
<td><strong>Llama 3 70B</strong>
</td>
<td><strong>Llama 2 70B</strong>
</td>
</tr>
<tr>
<td>MMLU (5-shot)
</td>
<td>68.4
</td>
<td>34.1
</td>
<td>47.8
</td>
<td>82.0
</td>
<td>52.9
</td>
</tr>
<tr>
<td>GPQA (0-shot)
</td>
<td>34.2
</td>
<td>21.7
</td>
<td>22.3
</td>
<td>39.5
</td>
<td>21.0
</td>
</tr>
<tr>
<td>HumanEval (0-shot)
</td>
<td>62.2
</td>
<td>7.9
</td>
<td>14.0
</td>
<td>81.7
</td>
<td>25.6
</td>
</tr>
<tr>
<td>GSM-8K (8-shot, CoT)
</td>
<td>79.6
</td>
<td>25.7
</td>
<td>77.4
</td>
<td>93.0
</td>
<td>57.5
</td>
</tr>
<tr>
<td>MATH (4-shot, CoT)
</td>
<td>30.0
</td>
<td>3.8
</td>
<td>6.7
</td>
<td>50.4
</td>
<td>11.6
</td>
</tr>
</table>
### Responsibility & Safety
We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.
Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.
Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.
As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started.
#### Llama 3-Instruct
As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.
<span style="text-decoration:underline;">Safety</span>
For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.
<span style="text-decoration:underline;">Refusals</span>
In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.
We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.
#### Responsible release
In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.
Misuse
If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/).
#### Critical risks
<span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)
We have conducted a two fold assessment of the safety of the model in this area:
* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.
* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).
### <span style="text-decoration:underline;">Cyber Security </span>
We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval).
### <span style="text-decoration:underline;">Child Safety</span>
Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
### Community
Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.
Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide)
## Citation instructions
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
## Contributors
Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
|
mradermacher/LLaMA2-13B-Holomax-i1-GGUF | mradermacher | "2024-06-11T09:03:06Z" | 1,935 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:KoboldAI/LLaMA2-13B-Holomax",
"license:other",
"endpoints_compatible",
"region:us"
] | null | "2024-06-11T06:26:42Z" | ---
base_model: KoboldAI/LLaMA2-13B-Holomax
language:
- en
library_name: transformers
license: other
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/KoboldAI/LLaMA2-13B-Holomax
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-IQ1_S.gguf) | i1-IQ1_S | 3.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-IQ1_M.gguf) | i1-IQ1_M | 3.2 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-IQ2_S.gguf) | i1-IQ2_S | 4.3 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-IQ2_M.gguf) | i1-IQ2_M | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-IQ3_S.gguf) | i1-IQ3_S | 5.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-IQ3_M.gguf) | i1-IQ3_M | 6.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.0 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-Q4_0.gguf) | i1-Q4_0 | 7.5 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.5 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.1 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.3 | |
| [GGUF](https://huggingface.co/mradermacher/LLaMA2-13B-Holomax-i1-GGUF/resolve/main/LLaMA2-13B-Holomax.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.
<!-- end -->
|
dmedhi/Phi-3-mini-text2SQL-4k-instruct-GGUF-f16 | dmedhi | "2024-06-21T08:53:22Z" | 1,935 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/phi-3-mini-4k-instruct-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-21T08:47:04Z" | ---
base_model: unsloth/phi-3-mini-4k-instruct-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- gguf
---
# Uploaded model
- **Developed by:** dmedhi
- **License:** apache-2.0
- **Finetuned from model :** unsloth/phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
IDEA-CCNL/Erlangshen-MegatronBert-1.3B-Sentiment | IDEA-CCNL | "2023-04-06T06:27:56Z" | 1,933 | 14 | transformers | [
"transformers",
"pytorch",
"megatron-bert",
"text-classification",
"bert",
"NLU",
"Sentiment",
"zh",
"arxiv:2209.02970",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2022-05-11T08:16:03Z" | ---
language:
- zh
license: apache-2.0
tags:
- bert
- NLU
- Sentiment
inference: true
widget:
- text: "今天心情不好"
---
# Erlangshen-MegatronBert-1.3B-Semtiment
- Github: [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM)
- Docs: [Fengshenbang-Docs](https://fengshenbang-doc.readthedocs.io/)
## 简介 Brief Introduction
2021年登顶FewCLUE和ZeroCLUE的中文BERT，在数个情感分析任务微调后的版本
This is the fine-tuned version of the Chinese BERT model on several sentiment analysis datasets, which topped FewCLUE and ZeroCLUE benchmark in 2021
## 模型分类 Model Taxonomy
| 需求 Demand | 任务 Task | 系列 Series | 模型 Model | 参数 Parameter | 额外 Extra |
| :----: | :----: | :----: | :----: | :----: | :----: |
| 通用 General | 自然语言理解 NLU | 二郎神 Erlangshen | MegatronBert | 1.3B | 情感分析 Semtiment |
## 模型信息 Model Information
基于[Erlangshen-MegatronBert-1.3B](https://huggingface.co/IDEA-CCNL/Erlangshen-MegatronBert-1.3B)，我们在收集的8个中文领域的情感分析数据集，总计227347个样本上微调了一个Semtiment版本。
Based on [Erlangshen-MegatronBert-1.3B](https://huggingface.co/IDEA-CCNL/Erlangshen-MegatronBert-1.3B), we fine-tuned a sentiment analysis version on 8 Chinese sentiment analysis datasets, with totaling 227,347 samples.
### 下游效果 Performance
| 模型 Model | ASAP-SENT | ASAP-ASPECT | ChnSentiCorp |
| :--------: | :-----: | :----: | :-----: |
| Erlangshen-Roberta-110M-Sentiment | 97.77 | 97.31 | 96.61 |
| Erlangshen-Roberta-330M-Sentiment | 97.9 | 97.51 | 96.66 |
| Erlangshen-MegatronBert-1.3B-Sentiment | 98.1 | 97.8 | 97 |
## 使用 Usage
``` python
from transformers import AutoModelForSequenceClassification
from transformers import BertTokenizer
import torch
tokenizer=BertTokenizer.from_pretrained('IDEA-CCNL/Erlangshen-MegatronBert-1.3B-Sentiment')
model=AutoModelForSequenceClassification.from_pretrained('IDEA-CCNL/Erlangshen-MegatronBert-1.3B-Sentiment')
text='今天心情不好'
output=model(torch.tensor([tokenizer.encode(text)]))
print(torch.nn.functional.softmax(output.logits,dim=-1))
```
## 引用 Citation
如果您在您的工作中使用了我们的模型，可以引用我们的[论文](https://arxiv.org/abs/2209.02970)：
If you are using the resource for your work, please cite the our [paper](https://arxiv.org/abs/2209.02970):
```text
@article{fengshenbang,
author = {Jiaxing Zhang and Ruyi Gan and Junjie Wang and Yuxiang Zhang and Lin Zhang and Ping Yang and Xinyu Gao and Ziwei Wu and Xiaoqun Dong and Junqing He and Jianheng Zhuo and Qi Yang and Yongfeng Huang and Xiayu Li and Yanghan Wu and Junyu Lu and Xinyu Zhu and Weifeng Chen and Ting Han and Kunhao Pan and Rui Wang and Hao Wang and Xiaojun Wu and Zhongshen Zeng and Chongpei Chen},
title = {Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence},
journal = {CoRR},
volume = {abs/2209.02970},
year = {2022}
}
```
也可以引用我们的[网站](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
You can also cite our [website](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
```text
@misc{Fengshenbang-LM,
title={Fengshenbang-LM},
author={IDEA-CCNL},
year={2021},
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
}
``` |
Aspik101/llama-30b-instruct-2048-PL-lora | Aspik101 | "2023-07-25T08:07:58Z" | 1,933 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"facebook",
"meta",
"llama-2",
"pl",
"dataset:Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-25T07:44:07Z" | ---
language:
- pl
datasets:
- Lajonbot/alpaca-dolly-chrisociepa-instruction-only-polish
license: other
model_type: llama-2
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-2
--- |
NeuralNovel/Panda-7B-v0.1 | NeuralNovel | "2024-03-05T23:26:16Z" | 1,933 | 11 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"dataset:NeuralNovel/Creative-Logic-v1",
"dataset:NeuralNovel/Neural-Story-v1",
"base_model:mistralai/Mistral-7B-Instruct-v0.2",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-01-01T04:41:34Z" | ---
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
datasets:
- NeuralNovel/Creative-Logic-v1
- NeuralNovel/Neural-Story-v1
library_name: transformers
inference: false
---
# NeuralNovel/Panda-7B-v0.1
The **Panda-7B-v0.1** model by NeuralNovel.
This fine-tune has been designed to provide detailed, creative and logical responses in the context of diverse narratives. Optimised for creative writing, roleplay and logical problem solving.
Full-parameter fine-tune (FFT) of Mistral-7B-Instruct-v0.2. Apache-2.0 license, suitable for commercial or non-commercial use.
<a href='https://ko-fi.com/S6S2UH2TC' target='_blank'><img height='38' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi1.png?v=3' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
<a href='https://discord.gg/KFS229xD' target='_blank'><img width='140' height='500' style='border:0px;height:36px;' src='https://i.ibb.co/tqwznYM/Discord-button.png' border='0' alt='Join Our Discord!' /></a>
### Data-set
The model on finetuned using the Panda-v1 dataset.
### Summary
Fine-tuned with the intention to generate instructive and narrative text, with a specific focus on combining the elements of versatility, character engagement and nuanced writing capability.
#### Out-of-Scope Use
The model may not perform well in scenarios unrelated to instructive and narrative text generation. Misuse or applications outside its designed scope may result in suboptimal outcomes.
### Bias, Risks, and Limitations
The model may exhibit biases or limitations inherent in the training data. It is essential to consider these factors when deploying the model to avoid unintended consequences.
Users are advised to exercise caution, as there might be some inherent genre or writing bias.
### Hardware and Training
```
n_epochs = 3,
n_checkpoints = 3,
batch_size = 12,
learning_rate = 1e-5,
```
*Sincere appreciation to Techmind for their generous sponsorship.*
|
RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf | RichardErkhov | "2024-06-30T04:46:41Z" | 1,933 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-30T04:35:17Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
tag2prompt-qwen2-0.5b-v0.1 - GGUF
- Model creator: https://huggingface.co/Thouph/
- Original model: https://huggingface.co/Thouph/tag2prompt-qwen2-0.5b-v0.1/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [tag2prompt-qwen2-0.5b-v0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q2_K.gguf) | Q2_K | 0.32GB |
| [tag2prompt-qwen2-0.5b-v0.1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.IQ3_XS.gguf) | IQ3_XS | 0.32GB |
| [tag2prompt-qwen2-0.5b-v0.1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.IQ3_S.gguf) | IQ3_S | 0.32GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q3_K_S.gguf) | Q3_K_S | 0.32GB |
| [tag2prompt-qwen2-0.5b-v0.1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.IQ3_M.gguf) | IQ3_M | 0.32GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q3_K.gguf) | Q3_K | 0.33GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q3_K_M.gguf) | Q3_K_M | 0.33GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q3_K_L.gguf) | Q3_K_L | 0.34GB |
| [tag2prompt-qwen2-0.5b-v0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.IQ4_XS.gguf) | IQ4_XS | 0.33GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q4_0.gguf) | Q4_0 | 0.33GB |
| [tag2prompt-qwen2-0.5b-v0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.IQ4_NL.gguf) | IQ4_NL | 0.33GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q4_K_S.gguf) | Q4_K_S | 0.36GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q4_K.gguf) | Q4_K | 0.37GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q4_K_M.gguf) | Q4_K_M | 0.37GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q4_1.gguf) | Q4_1 | 0.35GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q5_0.gguf) | Q5_0 | 0.37GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q5_K_S.gguf) | Q5_K_S | 0.38GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q5_K.gguf) | Q5_K | 0.39GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q5_K_M.gguf) | Q5_K_M | 0.39GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q5_1.gguf) | Q5_1 | 0.39GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q6_K.gguf) | Q6_K | 0.47GB |
| [tag2prompt-qwen2-0.5b-v0.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/Thouph_-_tag2prompt-qwen2-0.5b-v0.1-gguf/blob/main/tag2prompt-qwen2-0.5b-v0.1.Q8_0.gguf) | Q8_0 | 0.49GB |
Original model description:
---
license: cc-by-nc-4.0
---
|
ctheodoris/Geneformer | ctheodoris | "2024-07-02T19:39:32Z" | 1,932 | 166 | transformers | [
"transformers",
"pytorch",
"safetensors",
"bert",
"fill-mask",
"dataset:ctheodoris/Genecorpus-30M",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2022-03-12T20:55:42Z" | ---
datasets: ctheodoris/Genecorpus-30M
license: apache-2.0
---
# Geneformer
Geneformer is a foundation transformer model pretrained on a large-scale corpus of ~30 million single cell transcriptomes to enable context-aware predictions in settings with limited data in network biology.
- See [our manuscript](https://rdcu.be/ddrx0) for details.
- See [geneformer.readthedocs.io](https://geneformer.readthedocs.io) for documentation.
# Model Description
Geneformer is a foundation transformer model pretrained on [Genecorpus-30M](https://huggingface.co/datasets/ctheodoris/Genecorpus-30M), a pretraining corpus comprised of ~30 million single cell transcriptomes from a broad range of human tissues. We excluded cells with high mutational burdens (e.g. malignant cells and immortalized cell lines) that could lead to substantial network rewiring without companion genome sequencing to facilitate interpretation. Each single cell’s transcriptome is presented to the model as a rank value encoding where genes are ranked by their expression in that cell normalized by their expression across the entire Genecorpus-30M. The rank value encoding provides a nonparametric representation of that cell’s transcriptome and takes advantage of the many observations of each gene’s expression across Genecorpus-30M to prioritize genes that distinguish cell state. Specifically, this method will deprioritize ubiquitously highly-expressed housekeeping genes by normalizing them to a lower rank. Conversely, genes such as transcription factors that may be lowly expressed when they are expressed but highly distinguish cell state will move to a higher rank within the encoding. Furthermore, this rank-based approach may be more robust against technical artifacts that may systematically bias the absolute transcript counts value while the overall relative ranking of genes within each cell remains more stable.
The rank value encoding of each single cell’s transcriptome then proceeds through six transformer encoder units. Pretraining was accomplished using a masked learning objective where 15% of the genes within each transcriptome were masked and the model was trained to predict which gene should be within each masked position in that specific cell state using the context of the remaining unmasked genes. A major strength of this approach is that it is entirely self-supervised and can be accomplished on completely unlabeled data, which allows the inclusion of large amounts of training data without being restricted to samples with accompanying labels.
We detail applications and results in [our manuscript](https://rdcu.be/ddrx0).
During pretraining, Geneformer gained a fundamental understanding of network dynamics, encoding network hierarchy in the model’s attention weights in a completely self-supervised manner. With both zero-shot learning and fine-tuning with limited task-specific data, Geneformer consistently boosted predictive accuracy in a diverse panel of downstream tasks relevant to chromatin and network dynamics. In silico perturbation with zero-shot learning identified a novel transcription factor in cardiomyocytes that we experimentally validated to be critical to their ability to generate contractile force. In silico treatment with limited patient data revealed candidate therapeutic targets for cardiomyopathy that we experimentally validated to significantly improve the ability of cardiomyocytes to generate contractile force in an iPSC model of the disease. Overall, Geneformer represents a foundational deep learning model pretrained on ~30 million human single cell transcriptomes to gain a fundamental understanding of gene network dynamics that can now be democratized to a vast array of downstream tasks to accelerate discovery of key network regulators and candidate therapeutic targets.
In [our manuscript](https://rdcu.be/ddrx0), we report results for the 6 layer Geneformer model pretrained on Genecorpus-30M. We additionally provide within this repository a 12 layer Geneformer model, scaled up with retained width:depth aspect ratio, also pretrained on Genecorpus-30M.
Both the 6 and 12 layer Geneformer models were pretrained in June 2021.
# Application
The pretrained Geneformer model can be used directly for zero-shot learning, for example for in silico perturbation analysis, or by fine-tuning towards the relevant downstream task, such as gene or cell state classification.
Example applications demonstrated in [our manuscript](https://rdcu.be/ddrx0) include:
*Fine-tuning*:
- transcription factor dosage sensitivity
- chromatin dynamics (bivalently marked promoters)
- transcription factor regulatory range
- gene network centrality
- transcription factor targets
- cell type annotation
- batch integration
- cell state classification across differentiation
- disease classification
- in silico perturbation to determine disease-driving genes
- in silico treatment to determine candidate therapeutic targets
*Zero-shot learning*:
- batch integration
- gene context specificity
- in silico reprogramming
- in silico differentiation
- in silico perturbation to determine impact on cell state
- in silico perturbation to determine transcription factor targets
- in silico perturbation to determine transcription factor cooperativity
# Installation
In addition to the pretrained model, contained herein are functions for tokenizing and collating data specific to single cell transcriptomics, pretraining the model, fine-tuning the model, extracting and plotting cell embeddings, and performing in silico pertrubation with either the pretrained or fine-tuned models. To install:
```bash
# Make sure you have git-lfs installed (https://git-lfs.com)
git lfs install
git clone https://huggingface.co/ctheodoris/Geneformer
cd Geneformer
pip install .
```
For usage, see [examples](https://huggingface.co/ctheodoris/Geneformer/tree/main/examples) for:
- tokenizing transcriptomes
- pretraining
- hyperparameter tuning
- fine-tuning
- extracting and plotting cell embeddings
- in silico perturbation
Please note that the fine-tuning examples are meant to be generally applicable and the input datasets and labels will vary dependent on the downstream task. Example input files for a few of the downstream tasks demonstrated in the manuscript are located within the [example_input_files directory](https://huggingface.co/datasets/ctheodoris/Genecorpus-30M/tree/main/example_input_files) in the dataset repository, but these only represent a few example fine-tuning applications.
Please note that GPU resources are required for efficient usage of Geneformer. Additionally, we strongly recommend tuning hyperparameters for each downstream fine-tuning application as this can significantly boost predictive potential in the downstream task (e.g. max learning rate, learning schedule, number of layers to freeze, etc.).
|
moka-ai/m3e-small | moka-ai | "2023-07-14T02:37:24Z" | 1,932 | 43 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"bert",
"embedding",
"text-embedding",
"zh",
"region:us"
] | null | "2023-06-02T06:34:10Z" | ---
language:
- zh
tags:
- embedding
- text-embedding
library_name: sentence-transformers
---
# 🅜 M3E Models
[m3e-small](https://huggingface.co/moka-ai/m3e-small) | [m3e-base](https://huggingface.co/moka-ai/m3e-base)
M3E 是 Moka Massive Mixed Embedding 的缩写
- Moka，此模型由 MokaAI 训练，开源和评测，训练脚本使用 [uniem](https://github.com/wangyuxinwhy/uniem/blob/main/scripts/train_m3e.py) ，评测 BenchMark 使用 [MTEB-zh](https://github.com/wangyuxinwhy/uniem/tree/main/mteb-zh)
- Massive，此模型通过**千万级** (2200w+) 的中文句对数据集进行训练
- Mixed，此模型支持中英双语的同质文本相似度计算，异质文本检索等功能，未来还会支持代码检索
- Embedding，此模型是文本嵌入模型，可以将自然语言转换成稠密的向量
## 🆕 更新说明
- 2023.06.24，添加微调 M3E 的教程 [notebook](https://github.com/wangyuxinwhy/uniem/blob/main/examples/finetune.ipynb)，几行代码，更佳适配！<a target="_blank" href="https://colab.research.google.com/github/wangyuxinwhy/uniem/blob/main/examples/finetune.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
- 2023.06.14，添加了三个中文开源文本嵌入模型到评测中，包括 UER, ErLangShen, DMetaSoul
- 2023.06.08，添加检索任务的评测结果，在 T2Ranking 1W 中文数据集上，m3e-base 在 ndcg@10 上达到了 0.8004，超过了 openai-ada-002 的 0.7786
- 2023.06.07，添加文本分类任务的评测结果，在 6 种文本分类数据集上，m3e-base 在 accuracy 上达到了 0.6157，超过了 openai-ada-002 的 0.5956
## ⚖️ 模型对比
| | 参数数量 | 维度 | 中文 | 英文 | s2s | s2p | s2c | 开源 | 兼容性 | s2s Acc | s2p ndcg@10 |
| --------- | -------- | -------- | -------- | -------- | -------- | -------- | -------- | ---- | ---------- | ------------ | -------- |
| m3e-small | 24M | 512 | 是 | 否 | 是 | 否 | 否 | 是 | 优 | 0.5834 | 0.7262 |
| m3e-base | 110M | 768 | 是 | 是 | 是 | 是 | 否 | 是 | 优 | **0.6157** | **0.8004** |
| text2vec | 110M | 768 | 是 | 否 | 是 | 否 | 否 | 是 | 优 | 0.5755 | 0.6346 |
| openai-ada-002 | 未知 | 1536 | 是 | 是 | 是 | 是 | 是 | 否 | 优 | 0.5956 | 0.7786 |
说明：
- s2s, 即 sentence to sentence ，代表了同质文本之间的嵌入能力，适用任务：文本相似度，重复问题检测，文本分类等
- s2p, 即 sentence to passage ，代表了异质文本之间的嵌入能力，适用任务：文本检索，GPT 记忆模块等
- s2c, 即 sentence to code ，代表了自然语言和程序语言之间的嵌入能力，适用任务：代码检索
- 兼容性，代表了模型在开源社区中各种项目被支持的程度，由于 m3e 和 text2vec 都可以直接通过 sentence-transformers 直接使用，所以和 openai 在社区的支持度上相当
- ACC & ndcg@10，详情见下方的评测
Tips:
- 使用场景主要是中文，少量英文的情况，建议使用 m3e 系列的模型
- 多语言使用场景，并且不介意数据隐私的话，我建议使用 openai text-embedding-ada-002
- 代码检索场景，推荐使用 openai text-embedding-ada-002
- 文本检索场景，请使用具备文本检索能力的模型，只在 S2S 上训练的文本嵌入模型，没有办法完成文本检索任务
## 🔧 使用 M3E
您需要先安装 sentence-transformers
```bash
pip install -U sentence-transformers
```
安装完成后，您可以使用以下代码来使用 M3E Models
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('moka-ai/m3e-base')
#Our sentences we like to encode
sentences = [
'* Moka 此文本嵌入模型由 MokaAI 训练并开源，训练脚本使用 uniem',
'* Massive 此文本嵌入模型通过**千万级**的中文句对数据集进行训练',
'* Mixed 此文本嵌入模型支持中英双语的同质文本相似度计算，异质文本检索等功能，未来还会支持代码检索，ALL in one'
]
#Sentences are encoded by calling model.encode()
embeddings = model.encode(sentences)
#Print the embeddings
for sentence, embedding in zip(sentences, embeddings):
print("Sentence:", sentence)
print("Embedding:", embedding)
print("")
```
M3E 系列的所有模型在设计的时候就考虑到完全兼容 [sentence-transformers](https://www.sbert.net/) ，所以你可以通过**替换名称字符串**的方式在所有支持 sentence-transformers 的项目中**无缝**使用 M3E Models，比如 [chroma](https://docs.trychroma.com/getting-started), [guidance](https://github.com/microsoft/guidance), [semantic-kernel](https://github.com/microsoft/semantic-kernel) 。
## 🎨 微调模型
`uniem` 提供了非常易用的 finetune 接口，几行代码，即刻适配！
```python
from datasets import load_dataset
from uniem.finetuner import FineTuner
dataset = load_dataset('shibing624/nli_zh', 'STS-B')
# 指定训练的模型为 m3e-small
finetuner = FineTuner.from_pretrained('moka-ai/m3e-small', dataset=dataset)
finetuner.run(epochs=1)
```
详见 [uniem 微调教程](https://github.com/wangyuxinwhy/uniem/blob/main/examples/finetune.ipynb)
<a target="_blank" href="https://colab.research.google.com/github/wangyuxinwhy/uniem/blob/main/examples/finetune.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
## ➿ 训练方案
M3E 使用 in-batch 负采样的对比学习的方式在句对数据集进行训练，为了保证 in-batch 负采样的效果，我们使用 A100 80G 来最大化 batch-size，并在共计 2200W+ 的句对数据集上训练了 1 epoch。训练脚本使用 [uniem](https://github.com/wangyuxinwhy/uniem/blob/main/scripts/train_m3e.py)，您可以在这里查看具体细节。
## 🌟 特性
- 中文训练集，M3E 在大规模句对数据集上的训练，包含中文百科，金融，医疗，法律，新闻，学术等多个领域共计 2200W 句对样本，数据集详见 [M3E 数据集](#M3E数据集)
- 英文训练集，M3E 使用 MEDI 145W 英文三元组数据集进行训练，数据集详见 [MEDI 数据集](https://drive.google.com/file/d/1vZ5c2oJNonGOvXzppNg5mHz24O6jcc52/view)，此数据集由 [instructor team](https://github.com/HKUNLP/instructor-embedding) 提供
- 指令数据集，M3E 使用了 300W + 的指令微调数据集，这使得 M3E 对文本编码的时候可以遵从指令，这部分的工作主要被启发于 [instructor-embedding](https://github.com/HKUNLP/instructor-embedding)
- 基础模型，M3E 使用 hfl 实验室的 [Roberta](https://huggingface.co/hfl/chinese-roberta-wwm-ext) 系列模型进行训练，目前提供 small 和 base 两个版本，大家则需选用
- ALL IN ONE，M3E 旨在提供一个 ALL IN ONE 的文本嵌入模型，不仅支持同质句子相似度判断，还支持异质文本检索，你只需要一个模型就可以覆盖全部的应用场景，未来还会支持代码检索
## 💯 MTEB-zh 评测
- 评测模型，[text2vec](https://github.com/shibing624/text2vec), m3e-base, m3e-small, openai text-embedding-ada-002, [DMetaSoul](https://huggingface.co/DMetaSoul/sbert-chinese-general-v2), [UER](https://huggingface.co/uer/sbert-base-chinese-nli), [ErLangShen](https://huggingface.co/IDEA-CCNL/Erlangshen-SimCSE-110M-Chinese)
- 评测脚本，具体参考 [MTEB-zh] (https://github.com/wangyuxinwhy/uniem/blob/main/mteb-zh)
### 文本分类
- 数据集选择，选择开源在 HuggingFace 上的 6 种文本分类数据集，包括新闻、电商评论、股票评论、长文本等
- 评测方式，使用 MTEB 的方式进行评测，报告 Accuracy。
| | text2vec | m3e-small | m3e-base | openai | DMetaSoul | uer | erlangshen |
| ----------------- | -------- | --------- | -------- | ------ | ----------- | ------- | ----------- |
| TNews | 0.43 | 0.4443 | **0.4827** | 0.4594 | 0.3084 | 0.3539 | 0.4361 |
| JDIphone | 0.8214 | 0.8293 | **0.8533** | 0.746 | 0.7972 | 0.8283 | 0.8356 |
| GubaEastmony | 0.7472 | 0.712 | 0.7621 | 0.7574 | 0.735 | 0.7534 | **0.7787** |
| TYQSentiment | 0.6099 | 0.6596 | **0.7188** | 0.68 | 0.6437 | 0.6662 | 0.6444 |
| StockComSentiment | 0.4307 | 0.4291 | 0.4363 | **0.4819** | 0.4309 | 0.4555 | 0.4482 |
| IFlyTek | 0.414 | 0.4263 | 0.4409 | **0.4486** | 0.3969 | 0.3762 | 0.4241 |
| Average | 0.5755 | 0.5834 | **0.6157** | 0.5956 | 0.552016667 | 0.57225 | 0.594516667 |
### 检索排序
#### T2Ranking 1W
- 数据集选择，使用 [T2Ranking](https://github.com/THUIR/T2Ranking/tree/main) 数据集，由于 T2Ranking 的数据集太大，openai 评测起来的时间成本和 api 费用有些高，所以我们只选择了 T2Ranking 中的前 10000 篇文章
- 评测方式，使用 MTEB 的方式进行评测，报告 map@1, map@10, mrr@1, mrr@10, ndcg@1, ndcg@10
- 注意！从实验结果和训练方式来看，除了 M3E 模型和 openai 模型外，其余模型都没有做检索任务的训练，所以结果仅供参考。
| | text2vec | openai-ada-002 | m3e-small | m3e-base | DMetaSoul | uer | erlangshen |
| ------- | -------- | -------------- | --------- | -------- | --------- | ------- | ---------- |
| map@1 | 0.4684 | 0.6133 | 0.5574 | **0.626** | 0.25203 | 0.08647 | 0.25394 |
| map@10 | 0.5877 | 0.7423 | 0.6878 | **0.7656** | 0.33312 | 0.13008 | 0.34714 |
| mrr@1 | 0.5345 | 0.6931 | 0.6324 | **0.7047** | 0.29258 | 0.10067 | 0.29447 |
| mrr@10 | 0.6217 | 0.7668 | 0.712 | **0.7841** | 0.36287 | 0.14516 | 0.3751 |
| ndcg@1 | 0.5207 | 0.6764 | 0.6159 | **0.6881** | 0.28358 | 0.09748 | 0.28578 |
| ndcg@10 | 0.6346 | 0.7786 | 0.7262 | **0.8004** | 0.37468 | 0.15783 | 0.39329 |
#### T2Ranking
- 数据集选择，使用 T2Ranking，刨除 openai-ada-002 模型后，我们对剩余的三个模型，进行 T2Ranking 10W 和 T2Ranking 50W 的评测。（T2Ranking 评测太耗内存了... 128G 都不行）
- 评测方式，使用 MTEB 的方式进行评测，报告 ndcg@10
| | text2vec | m3e-small | m3e-base |
| ------- | -------- | --------- | -------- |
| t2r-1w | 0.6346 | 0.72621 | **0.8004** |
| t2r-10w | 0.44644 | 0.5251 | **0.6263** |
| t2r-50w | 0.33482 | 0.38626 | **0.47364** |
说明：
- 检索排序对于 text2vec 并不公平，因为 text2vec 在训练的时候没有使用过检索相关的数据集，所以没有办法很好的完成检索任务也是正常的。
## 📂 M3E数据集
如果您想要使用这些数据集，你可以在 [uniem process_zh_datasets](https://github.com/wangyuxinwhy/uniem/blob/main/scripts/process_zh_datasets.py) 中找到加载 huggingface 数据集的脚本，非 huggingface 数据集需要您根据下方提供的链接自行下载和处理。
| 数据集名称 | 领域 | 数量 | 任务类型 | Prompt | 质量 | 数据提供者 | 说明 | 是否开源/研究使用 | 是否商用 | 脚本 | Done | URL | 是否同质 |
| -------------------- | ---- | --------- | ----------------- | ------ | ---- | ------------------------------------------------------------ | ------------------------------------------------------------ | ----------------- | -------- | ---- | ---- | ------------------------------------------------------------ | -------- |
| cmrc2018 | 百科 | 14,363 | 问答 | 问答 | 优 | Yiming Cui, Ting Liu, Wanxiang Che, Li Xiao, Zhipeng Chen, Wentao Ma, Shijin Wang, Guoping Hu | https://github.com/ymcui/cmrc2018/blob/master/README_CN.md 专家标注的基于维基百科的中文阅读理解数据集，将问题和上下文视为正例 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/cmrc2018 | 否 |
| belle_2m | 百科 | 2,000,000 | 指令微调 | 无 | 优 | LianjiaTech/BELLE | belle 的指令微调数据集，使用 self instruct 方法基于 gpt3.5 生成 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/BelleGroup/train_2M_CN | 否 |
| firefily | 百科 | 1,649,399 | 指令微调 | 无 | 优 | YeungNLP | Firefly（流萤） 是一个开源的中文对话式大语言模型，使用指令微调（Instruction Tuning）在中文数据集上进行调优。使用了词表裁剪、ZeRO等技术，有效降低显存消耗和提高训练效率。 在训练中，我们使用了更小的模型参数量，以及更少的计算资源。 | 未说明 | 未说明 | 是 | 是 | https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M | 否 |
| alpaca_gpt4 | 百科 | 48,818 | 指令微调 | 无 | 优 | Baolin Peng, Chunyuan Li, Pengcheng He, Michel Galley, Jianfeng Gao | 本数据集是参考Alpaca方法基于GPT4得到的self-instruct数据，约5万条。 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/shibing624/alpaca-zh | 否 |
| zhihu_kol | 百科 | 1,006,218 | 问答 | 问答 | 优 | wangrui6 | 知乎问答 | 未说明 | 未说明 | 是 | 是 | https://huggingface.co/datasets/wangrui6/Zhihu-KOL | 否 |
| hc3_chinese | 百科 | 39,781 | 问答 | 问答 | 良 | Hello-SimpleAI | 问答数据，包括人工回答和 GPT 回答 | 是 | 未说明 | 是 | 是 | https://huggingface.co/datasets/Hello-SimpleAI/HC3-Chinese | 否 |
| amazon_reviews_multi | 电商 | 210,000 | 问答 文本分类 | 摘要 | 优 | 亚马逊 | 亚马逊产品评论数据集 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/amazon_reviews_multi/viewer/zh/train?row=8 | 否 |
| mlqa | 百科 | 85,853 | 问答 | 问答 | 良 | patrickvonplaten | 一个用于评估跨语言问答性能的基准数据集 | 是 | 未说明 | 是 | 是 | https://huggingface.co/datasets/mlqa/viewer/mlqa-translate-train.zh/train?p=2 | 否 |
| xlsum | 新闻 | 93,404 | 摘要 | 摘要 | 良 | BUET CSE NLP Group | BBC的专业注释文章摘要对 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/csebuetnlp/xlsum/viewer/chinese_simplified/train?row=259 | 否 |
| ocnli | 口语 | 17,726 | 自然语言推理 | 推理 | 良 | Thomas Wolf | 自然语言推理数据集 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/clue/viewer/ocnli | 是 |
| BQ | 金融 | 60,000 | 文本分类 | 相似 | 良 | Intelligent Computing Research Center, Harbin Institute of Technology(Shenzhen) | http://icrc.hitsz.edu.cn/info/1037/1162.htm BQ 语料库包含来自网上银行自定义服务日志的 120，000 个问题对。它分为三部分：100，000 对用于训练，10，000 对用于验证，10，000 对用于测试。 数据提供者： 哈尔滨工业大学（深圳）智能计算研究中心 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/shibing624/nli_zh/viewer/BQ | 是 |
| lcqmc | 口语 | 149,226 | 文本分类 | 相似 | 良 | Ming Xu | 哈工大文本匹配数据集，LCQMC 是哈尔滨工业大学在自然语言处理国际顶会 COLING2018 构建的问题语义匹配数据集，其目标是判断两个问题的语义是否相同 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/shibing624/nli_zh/viewer/LCQMC/train | 是 |
| paws-x | 百科 | 23,576 | 文本分类 | 相似 | 优 | Bhavitvya Malik | PAWS Wiki中的示例 | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/paws-x/viewer/zh/train | 是 |
| wiki_atomic_edit | 百科 | 1,213,780 | 平行语义 | 相似 | 优 | abhishek thakur | 基于中文维基百科的编辑记录收集的数据集 | 未说明 | 未说明 | 是 | 是 | https://huggingface.co/datasets/wiki_atomic_edits | 是 |
| chatmed_consult | 医药 | 549,326 | 问答 | 问答 | 优 | Wei Zhu | 真实世界的医学相关的问题，使用 gpt3.5 进行回答 | 是 | 否 | 是 | 是 | https://huggingface.co/datasets/michaelwzhu/ChatMed_Consult_Dataset | 否 |
| webqa | 百科 | 42,216 | 问答 | 问答 | 优 | suolyer | 百度于2016年开源的数据集，数据来自于百度知道；格式为一个问题多篇意思基本一致的文章，分为人为标注以及浏览器检索；数据整体质量中，因为混合了很多检索而来的文章 | 是 | 未说明 | 是 | 是 | https://huggingface.co/datasets/suolyer/webqa/viewer/suolyer--webqa/train?p=3 | 否 |
| dureader_robust | 百科 | 65,937 | 机器阅读理解 问答 | 问答 | 优 | 百度 | DuReader robust旨在利用真实应用中的数据样本来衡量阅读理解模型的鲁棒性，评测模型的过敏感性、过稳定性以及泛化能力，是首个中文阅读理解鲁棒性数据集。 | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/PaddlePaddle/dureader_robust/viewer/plain_text/train?row=96 | 否 |
| csl | 学术 | 395,927 | 语料 | 摘要 | 优 | Yudong Li, Yuqing Zhang, Zhe Zhao, Linlin Shen, Weijie Liu, Weiquan Mao and Hui Zhang | 提供首个中文科学文献数据集（CSL），包含 396,209 篇中文核心期刊论文元信息 （标题、摘要、关键词、学科、门类）。CSL 数据集可以作为预训练语料，也可以构建许多NLP任务，例如文本摘要（标题预测）、 关键词生成和文本分类等。 | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/neuclir/csl | 否 |
| miracl-corpus | 百科 | 4,934,368 | 语料 | 摘要 | 优 | MIRACL | The corpus for each language is prepared from a Wikipedia dump, where we keep only the plain text and discard images, tables, etc. Each article is segmented into multiple passages using WikiExtractor based on natural discourse units (e.g., \n\n in the wiki markup). Each of these passages comprises a "document" or unit of retrieval. We preserve the Wikipedia article title of each passage. | 是 | 是 | 是 | 是 | https://huggingface.co/datasets/miracl/miracl-corpus | 否 |
| lawzhidao | 法律 | 36,368 | 问答 | 问答 | 优 | 和鲸社区-Ustinian | 百度知道清洗后的法律问答 | 是 | 是 | 否 | 是 | https://www.heywhale.com/mw/dataset/5e953ca8e7ec38002d02fca7/content | 否 |
| CINLID | 成语 | 34,746 | 平行语义 | 相似 | 优 | 高长宽 | 中文成语语义推理数据集（Chinese Idioms Natural Language Inference Dataset）收集了106832条由人工撰写的成语对（含少量歇后语、俗语等短文本），通过人工标注的方式进行平衡分类，标签为entailment、contradiction和neutral，支持自然语言推理（NLI）的任务。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=39 | 是 |
| DuSQL | SQL | 25,003 | NL2SQL | SQL | 优 | 百度 | DuSQL是一个面向实际应用的数据集，包含200个数据库，覆盖了164个领域，问题覆盖了匹配、计算、推理等实际应用中常见形式。该数据集更贴近真实应用场景，要求模型领域无关、问题无关，且具备计算推理等能力。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=13 | 否 |
| Zhuiyi-NL2SQL | SQL | 45,918 | NL2SQL | SQL | 优 | 追一科技 刘云峰 | NL2SQL是一个多领域的简单数据集，其主要包含匹配类型问题。该数据集主要验证模型的泛化能力，其要求模型具有较强的领域泛化能力、问题泛化能力。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=12 | 否 |
| Cspider | SQL | 7,785 | NL2SQL | SQL | 优 | 西湖大学 张岳 | CSpider是一个多语言数据集，其问题以中文表达，数据库以英文存储，这种双语模式在实际应用中也非常常见，尤其是数据库引擎对中文支持不好的情况下。该数据集要求模型领域无关、问题无关，且能够实现多语言匹配。 | 是 | 否 | 否 | 是 | https://www.luge.ai/#/luge/dataDetail?id=11 | 否 |
| news2016zh | 新闻 | 2,507,549 | 语料 | 摘要 | 良 | Bright Xu | 包含了250万篇新闻。新闻来源涵盖了6.3万个媒体，含标题、关键词、描述、正文。 | 是 | 是 | 否 | 是 | https://github.com/brightmart/nlp_chinese_corpus | 否 |
| baike2018qa | 百科 | 1,470,142 | 问答 | 问答 | 良 | Bright Xu | 含有150万个预先过滤过的、高质量问题和答案，每个问题属于一个类别。总共有492个类别，其中频率达到或超过10次的类别有434个。 | 是 | 是 | 否 | 是 | https://github.com/brightmart/nlp_chinese_corpus | 否 |
| webtext2019zh | 百科 | 4,258,310 | 问答 | 问答 | 优 | Bright Xu | 含有410万个预先过滤过的、高质量问题和回复。每个问题属于一个【话题】，总共有2.8万个各式话题，话题包罗万象。 | 是 | 是 | 否 | 是 | https://github.com/brightmart/nlp_chinese_corpus | 否 |
| SimCLUE | 百科 | 775,593 | 平行语义 | 相似 | 良 | 数据集合，请在 simCLUE 中查看 | 整合了中文领域绝大多数可用的开源的语义相似度和自然语言推理的数据集，并重新做了数据拆分和整理。 | 是 | 否 | 否 | 是 | https://github.com/CLUEbenchmark/SimCLUE | 是 |
| Chinese-SQuAD | 新闻 | 76,449 | 机器阅读理解 | 问答 | 优 | junzeng-pluto | 中文机器阅读理解数据集，通过机器翻译加人工校正的方式从原始Squad转换而来 | 是 | 否 | 否 | 是 | https://github.com/pluto-junzeng/ChineseSquad | 否 |
## 🗓️ 计划表
- [x] 完成 MTEB 中文评测 BenchMark, [MTEB-zh](https://github.com/wangyuxinwhy/uniem/tree/main/mteb-zh)
- [x] 完成 Large 模型的训练和开源
- [x] 完成 Finetuner ，允许更优雅的微调
- [ ] 对 M3E 数据集进行清洗，保留高质量的部分，组成 m3e-hq，并在 huggingface 上开源
- [ ] 在 m3e-hq 的数据集上补充 hard negative 的样本及相似度分数，组成 m3e-hq-with-score，并在 huggingface 上开源
- [ ] 在 m3e-hq-with-score 上通过 [cosent loss](https://github.com/wangyuxinwhy/uniem/blob/main/uniem/criteria.py#LL24C39-L24C39) loss 进行训练并开源模型，CoSent 原理参考这篇[博客](https://kexue.fm/archives/8847)
- [ ] 开源商用版本的 M3E models
## 🙏 致谢
感谢开源社区提供的中文语料，感谢所有在此工作中提供帮助的人们，希望中文社区越来越好，共勉！
## 📜 License
M3E models 使用的数据集中包括大量非商用的数据集，所以 M3E models 也是非商用的，仅供研究使用。不过我们已经在 M3E 数据集上标识了商用和非商用的数据集，您可以根据自己的需求自行训练。
## Citation
Please cite this model using the following format:
```
@software {Moka Massive Mixed Embedding,
author = {Wang Yuxin,Sun Qingxuan,He sicheng},
title = {M3E: Moka Massive Mixed Embedding Model},
year = {2023}
}
``` |
Austism/chronos-wizardlm-uc-scot-st-13b | Austism | "2023-06-06T11:23:48Z" | 1,932 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"storywriting",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-06T10:29:08Z" | ---
license: other
tags:
- llama
- storywriting
---
(chronos-13b+(WizardLM Uncensored+CoT+Storytelling))
80/20 merge
intended to be much like chronos with different writing and instruction following capabilities. |
TencentARC/Mistral_Pro_8B_v0.1 | TencentARC | "2024-02-27T02:31:53Z" | 1,932 | 64 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"en",
"dataset:HuggingFaceTB/cosmopedia",
"dataset:EleutherAI/proof-pile-2",
"dataset:bigcode/the-stack-dedup",
"dataset:math-ai/AutoMathText",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-02-22T14:47:03Z" | ---
license: apache-2.0
datasets:
- HuggingFaceTB/cosmopedia
- EleutherAI/proof-pile-2
- bigcode/the-stack-dedup
- math-ai/AutoMathText
language:
- en
metrics:
- accuracy
- code_eval
---
# Mistral-Pro-8B Model Card
## Model Description
Mistral-Pro is a progressive version of the original [Mistral](https://huggingface.co/mistralai/Mistral-7B-v0.1) model, enhanced by the addition of Transformer blocks. It specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.
## Development and Training
Developed by Tencent's ARC Lab, Mistral-Pro is an 8 billion parameter model. It's an expansion of Mistral-7B, further trained on code and math corpora.
## Intended Use
This model is designed for a wide range of NLP tasks, with a focus on programming, mathematics, and general language tasks. It suits scenarios requiring integration of natural and programming languages.
## Performance
Mistral_Pro_8B_v0.1 showcases superior performance on a range of benchmarks. It enhances the code and math performance of Mistral. Furthermore, it matches the performance of the recently dominant model, [Gemma](https://huggingface.co/google/gemma-7b).
### Overall Performance on Languages, math and code tasks
| Model | ARC | Hellaswag | MMLU | TruthfulQA | Winogrande | GSM8K | HumanEval |
| :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: |
| Gemma-7B | 61.9 | 82.2 | 64.6 | 44.8 | 79.0 | 50.9 | 32.3 |
| Mistral-7B | 60.8 | 83.3 | 62.7 | 42.6 | 78.0 | 39.2 | 28.7 |
| Mistral_Pro_8B_v0.1 | 63.2 | 82.6 | 60.6 | 48.3 | 78.9 | 50.6 | 32.9 |
## Limitations
While Mistral-Pro addresses some limitations of previous models in the series, it may still encounter challenges specific to highly specialized domains or tasks.
## Ethical Considerations
Users should be aware of potential biases in the model and use it responsibly, considering its impact on various applications. |
dacorvo/Mixtral-tiny | dacorvo | "2024-04-25T10:16:56Z" | 1,932 | 0 | transformers | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-04-15T11:37:09Z" | Entry not found |
6DammK9/AstolfoMix | 6DammK9 | "2024-07-02T17:07:33Z" | 1,931 | 6 | diffusers | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"safetensors",
"merge",
"en",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-09-12T16:06:52Z" | ---
language:
- en
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- safetensors
- merge
inference: true
thumbnail: >-
https://huggingface.co/6DammK9/AstolfoMix/resolve/main/231267-1921923808-3584-1536-4.5-256-20231207033217.jpg
widget:
- text: aesthetic, quality, 1girl, boy, astolfo
example_title: example 1girl boy
library_name: diffusers
---
# AstolfoMix (Baseline / Extended / Reinforced / 21b) #
- Preview here are powered by the top session of `README.md` and converting SDXL model from A1111 standalone file into diffuers via [convert_original_stable_diffusion_to_diffusers.py](https://github.com/huggingface/diffusers/blob/main/scripts/convert_original_stable_diffusion_to_diffusers.py). Settings may not being optimal (no CFG / PAG / FreeU etc). I'll replace the preview diffuser as soon as I upload the main model file.
## "21b" ##
- Special case of "Add difference". Merge of "Extended" and "Reinforced".
- See [simplified description in CivitAI](https://civitai.com/articles/3409/diagram-of-unet-and-exotic-merging-methods) and [full article in Github](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/README.MD)
- [CivitAI model page.](https://civitai.com/models/155604/astolfomix)
- The image below is 3584x1536 without upscaler. With upscaler, browser will break lol.
```
parameters
(aesthetic:0), (quality:0), (solo:0.98), (boy:0), (wide_shot:0), [astolfo], [[[[astrophotography]]]]
Negative prompt: (worst:0), (low:0), (bad:0), (exceptional:0), (masterpiece:0), (comic:0), (extra:0), (lowres:0), (breasts:0.5)
Steps: 256, Sampler: Euler, CFG scale: 4.5, Seed: 1921923808, Size: 1792x768, Model hash: 28adb7ba78, Model: 21b-AstolfoMix-2020b, VAE hash: 551eac7037, VAE: vae-ft-mse-840000-ema-pruned.ckpt, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.2, \"skip_factor\": 0.9}, {\"backbone_factor\": 1.4, \"skip_factor\": 0.2}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 2, Hires steps: 64, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.5, Threshold percentile: 100, Version: v1.6.1
```
- Current version: `21b-AstolfoMix-2020b.safetensors` (merge of 20 + 1 models)
- Recommended version: "21b"
- Recommended CFG: 4.0
## Reinforced ##
- Using AutoMBW (bayesian merger but less powerful) for the same set of 20 models.
- BayesianOptimizer with ImageReward.
```
parameters
(aesthetic:0), (quality:0), (race queen:0.98), [[braid]], [astolfo], [[[[nascar, nurburgring]]]]
Negative prompt: (worst:0), (low:0), (bad:0), (exceptional:0), (masterpiece:0), (comic:0), (extra:0), (lowres:0), (breasts:0.5)
Steps: 256, Sampler: Euler, CFG scale: 4, Seed: 142097205, Size: 1024x576, Model hash: aab8357cdc, Model: 20b-AstolfoMix-18b19b, VAE hash: 551eac7037, VAE: vae-ft-mse-840000-ema-pruned.ckpt, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.2, \"skip_factor\": 0.9}, {\"backbone_factor\": 1.4, \"skip_factor\": 0.2}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 2.5, Hires steps: 64, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.5, Threshold percentile: 100, Version: v1.6.0-2-g4afaaf8a
```
- Current version: `20b-AstolfoMix-18b19b` (merge of 20 models)
- Recommended version: "20b"
- Recommended CFG: 4.0
## Extended ##
- Is 10 model ensemble robust enough? How about 20, with 10 more radical models?
- For EMB / LoRAs, best fit will be models trained from NAI. ~~Just use them, most of them will work.~~
```
parameters
(aesthetic:0), (quality:0), (1girl:0), (boy:0), [[shirt]], [[midriff]], [[braid]], [astolfo], [[[[sydney opera house]]]]
Negative prompt: (worst:0), (low:0), (bad:0), (exceptional:0), (masterpiece:0), (comic:0), (extra:0), (lowres:0), (breasts:0.5)
Steps: 256, Sampler: Euler, CFG scale: 4, Seed: 341693176, Size: 1344x768, Model hash: 41429fdee1, Model: 20-bpcga9-lracrc2oh-b11i75pvc-gf34ym34-sd, VAE hash: 551eac7037, VAE: vae-ft-mse-840000-ema-pruned.ckpt, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.2, \"skip_factor\": 0.9}, {\"backbone_factor\": 1.4, \"skip_factor\": 0.2}]", FreeU Schedule: "0.0, 1.0, 0.0", Hires upscale: 2, Hires steps: 64, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.7, Threshold percentile: 100, Version: v1.6.0
```
- Current version: `20-bpcga9-lracrc2oh-b11i75pvc-gf34ym34-sd.safetensors` (merge of 20 models)
- Recommended version: "20"
- Recommended CFG: ~~4.5~~ 4.0
## Baseline ##
- A (baseline) merge model focusing on [absurdres](https://www.urbandictionary.com/define.php?term=absurdres), *and let me wait for a big anime SDXL finetune.*
- Behind the "absurdres", the model should be very robust and capable for most LoRAs / embeddings / addons you can imagine.
- The image below is 2688x1536 without upscaler. With upscaler, it reaches 8K already.
- ~~The image below is 10752x6143, and it is a 3.25MB JPEG. "upscaler 4x". See PNG info below. Removed because some it failed to preview on some browsers.~~
```
parameters
(aesthetic:0), (quality:0), (solo:0), (boy:0), (ushanka:0.98), [[braid]], [astolfo], [[moscow, russia]]
Negative prompt: (worst:0), (low:0), (bad:0), (exceptional:0), (masterpiece:0), (comic:0), (extra:0), (lowres:0), (breasts:0.5)
Steps: 256, Sampler: Euler, CFG scale: 4.5, Seed: 132385090, Size: 1344x768, Model hash: 6ffdb39acd, Model: 10-vcbpmtd8_cwlbdaw_eb5ms29-sd, VAE hash: 551eac7037, VAE: vae-ft-mse-840000-ema-pruned.ckpt, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.2, \"skip_factor\": 0.9}, {\"backbone_factor\": 1.4, \"skip_factor\": 0.2}]", FreeU Schedule: "0.0, 1.0, 0.0", Hires upscale: 2, Hires steps: 64, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.7, Threshold percentile: 100, Version: v1.6.0
```
- Current version: `10-vcbpmtd8_cwlbdaw_eb5ms29-sd.safetensors` (merge of 10 models)
- Recommended version: "06a" or "10"
- [Receipe Models: Merging UNETs into SD V1.4](https://huggingface.co/6DammK9/bpmodel-sd14-merge)
- ["Roadmap" / "Theory" in my Github.](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/README.MD)
- Recommended prompt: "SD 1.4's Text Encoder"
- Recommended resolution: **1024x1024 (native T2I), HiRes 1.75x (RTX 2080Ti 11GB)**
- It can generate images **up to 1280x1280 with HiRes 2.0x ([Tesla M40 24GB](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch04/readme.md#chapter-04b-extra-making-use-of-m40-24gb-for-generating-large-images))**, but the yield will be very low and time consuming to generate a nice image.
- Recommended CFG: 4.5 (also tested on all base models), 6.0 (1280 mode)
## Receipe ##
- [Full receipe.](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/receipe-20a.json)
- **Uniform merge.** M = 1 / "number of models in total".
|Index|M|Filename|
|---|---|---|
|02|0.5|[02-vbp23-cbp2-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/02-vbp23-cbp2-sd.safetensors)|
|03|0.33|[03-vcbp-mzpikas_tmnd-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/03-vcbp-mzpikas_tmnd-sd.safetensors)|
|04|0.25|[04-vcbp_mzpt_d8-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/04-vcbp_mzpt_d8-sd.safetensors)|
|05|0.2|[05-vcbp_mtd8_cwl-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/05-vcbp_mtd8_cwl-sd.safetensors)|
|06|0.167|[06-vcbp_mtd8cwl_bd-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/06-vcbp_mtd8cwl_bd-sd.safetensors)|
|07|0.143|[07-vcbp_mtd8cwl_bdaw-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/07-vcbp_mtd8cwl_bdaw-sd.safetensors)|
|08|0.125|[08-vcbpmt_d8cwlbd_aweb5-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/08-vcbpmt_d8cwlbd_aweb5-sd.safetensors)|
|09|0.111|[09-majicmixRealistic_v6-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/09-majicmixRealistic_v6-sd.safetensors)|
|10|0.1|[10-vcbpmtd8_cwlbdaw_eb5ms29-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/10-vcbpmtd8_cwlbdaw_eb5ms29-sd.safetensors)|
|11|0.0909|[11-bp-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/11-bp-sd.safetensors)|
|12|0.0833|[12-bpcga9-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/12-bpcga9-sd.safetensors)|
|13|0.0769|[13-bpcga9-lra-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/13-bpcga9-lra-sd.safetensors)|
|14|0.0714|[14-bpcga9-lracrc2-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/14-bpcga9-lracrc2-sd.safetensors)|
|15|0.0667|[15-bpcga9-lracrc2-oh-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/15-bpcga9-lracrc2-oh-sd.safetensors)|
|16|0.0625|[16-bpcga9-lracrc2-ohb11](https://huggingface.co/6DammK9/AstolfoMix/blob/main/16-bpcga9-lracrc2-ohb11.safetensors)|
|17|0.0588|[17-bpcga9-lracrc2-ohb11i75-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/17-bpcga9-lracrc2-ohb11i75-sd.safetensors)|
|18|0.0555|[18-bpcga9-lracrc2-ohb11i75-pvc-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/18-bpcga9-lracrc2-ohb11i75-pvc-sd.safetensors)|
|19|0.0526|[19-bpcga9-lracrc2-ohb11i75-pvcgf34-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/19-bpcga9-lracrc2-ohb11i75-pvcgf34-sd.safetensors)|
|20|0.05|[20-bpcga9-lracrc2oh-b11i75pvc-gf34ym34-sd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/20-bpcga9-lracrc2oh-b11i75pvc-gf34ym34-sd.safetensors)|
## Extra: Comparing with merges with original Text Encoders ##
- **Uniform merge.** M = 1 / "number of models in total".
|Index|M|Filename|
|---|---|---|
|02|0.5|[02a-vbp23-cbp2](https://huggingface.co/6DammK9/AstolfoMix/blob/main/02a-vbp23-cbp2.safetensors)|
|03|0.33|[03a-vcbp-mzpikas_tmnd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/03a-vcbp-mzpikas_tmnd.safetensors)|
|04|0.25|[04a-vcbp_mzpt_d8](https://huggingface.co/6DammK9/AstolfoMix/blob/main/04a-vcbp_mzpt_d8.safetensors)|
|05|0.2|[05a-vcbp_mtd8_cwl](https://huggingface.co/6DammK9/AstolfoMix/blob/main/05a-vcbp_mtd8_cwl.safetensors)|
|06|0.167|[06a-vcbp_mtd8cwl_bd](https://huggingface.co/6DammK9/AstolfoMix/blob/main/06a-vcbp_mtd8cwl_bd.safetensors)|
|07|0.143|[07a-vcbp_mtd8cwl_bdaw](https://huggingface.co/6DammK9/AstolfoMix/blob/main/07a-vcbp_mtd8cwl_bdaw.safetensors)|
|08|0.125|[08a-vcbpmt_d8cwlbd_aweb5](https://huggingface.co/6DammK9/AstolfoMix/blob/main/08a-vcbpmt_d8cwlbd_aweb5.safetensors)|
|09|0.111|[09a-majicmixRealistic_v6](https://huggingface.co/6DammK9/AstolfoMix/blob/main/09a-majicmixRealistic_v6.safetensors)|
|10|0.1|[10a-vcbpmtd8_cwlbdaw_eb5ms29](https://huggingface.co/6DammK9/AstolfoMix/blob/main/10a-vcbpmtd8_cwlbdaw_eb5ms29.safetensors)|
|11|0.0909|[11a-bp](https://huggingface.co/6DammK9/AstolfoMix/blob/main/11a-bp.safetensors)|
|12|0.0833|[12a-bpcga9](https://huggingface.co/6DammK9/AstolfoMix/blob/main/12a-bpcga9.safetensors)|
|13|0.0769|[13a-bpcga9-lra](https://huggingface.co/6DammK9/AstolfoMix/blob/main/13a-bpcga9-lra.safetensors)|
|14|0.0714|[14a-bpcga9-lracrc2](https://huggingface.co/6DammK9/AstolfoMix/blob/main/14a-bpcga9-lracrc2.safetensors)|
|15|0.0667|[15a-bpcga9-lracrc2-oh](https://huggingface.co/6DammK9/AstolfoMix/blob/main/15a-bpcga9-lracrc2-oh.safetensors)|
|16|0.0625|[16a-bpcga9-lracrc2-ohb11](https://huggingface.co/6DammK9/AstolfoMix/blob/main/16a-bpcga9-lracrc2-ohb11.safetensors)|
|17|0.0588|[17a-bpcga9-lracrc2-ohb11i75](https://huggingface.co/6DammK9/AstolfoMix/blob/main/17a-bpcga9-lracrc2-ohb11i75.safetensors)|
|18|0.0555|[18a-bpcga9-lracrc2-ohb11i75-pvc](https://huggingface.co/6DammK9/AstolfoMix/blob/main/18a-bpcga9-lracrc2-ohb11i75-pvc.safetensors)|
|19|0.0526|[19a-bpcga9-lracrc2-ohb11i75-pvcgf34](https://huggingface.co/6DammK9/AstolfoMix/blob/main/19a-bpcga9-lracrc2-ohb11i75-pvcgf34.safetensors)|
|20|0.05|[20a-bpcga9-lracrc2oh-b11i75pvc-gf34ym34](https://huggingface.co/6DammK9/AstolfoMix/blob/main/20a-bpcga9-lracrc2oh-b11i75pvc-gf34ym34-sd.safetensors)|
- Suprisingly, they looks similar, with only minor difference in background and unnamed details (semantic relationships).
## License ##
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:
1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license [here](https://huggingface.co/spaces/CompVis/stable-diffusion-license/blob/main/license.txt) |
abhishek/ccy0-2g7e-wqsa-0 | abhishek | "2023-11-24T08:55:29Z" | 1,931 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"autotrain",
"conversational",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-11-23T19:20:22Z" | ---
tags:
- autotrain
- text-generation
widget:
- text: 'I love AutoTrain because '
license: other
---
# Model Trained Using AutoTrain
Hello, this is a long description now. How about it? Hello, this is a long description now. How about it? Hello, this is a long description now. How about it? Hello, this is a long description now. How about it? Hello, this is a long description now. How about it? Hello, this is a long description now. How about it? Hello, this is a long description now. How about it? Hello, this is a long description now. How about it? Hello, this is a long description now. How about it? |
infgrad/stella-large-zh-v3-1792d | infgrad | "2024-04-06T02:45:45Z" | 1,931 | 26 | sentence-transformers | [
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"mteb",
"model-index",
"endpoints_compatible",
"region:us"
] | sentence-similarity | "2024-02-17T05:30:43Z" | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- mteb
model-index:
- name: stella-large-zh-v3-1792d
results:
- task:
type: STS
dataset:
type: C-MTEB/AFQMC
name: MTEB AFQMC
config: default
split: validation
revision: None
metrics:
- type: cos_sim_pearson
value: 54.48093298255762
- type: cos_sim_spearman
value: 59.105354109068685
- type: euclidean_pearson
value: 57.761189988643444
- type: euclidean_spearman
value: 59.10537421115596
- type: manhattan_pearson
value: 56.94359297051431
- type: manhattan_spearman
value: 58.37611109821567
- task:
type: STS
dataset:
type: C-MTEB/ATEC
name: MTEB ATEC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 54.39711127600595
- type: cos_sim_spearman
value: 58.190191920824454
- type: euclidean_pearson
value: 61.80082379352729
- type: euclidean_spearman
value: 58.19018966860797
- type: manhattan_pearson
value: 60.927601060396206
- type: manhattan_spearman
value: 57.78832902694192
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (zh)
config: zh
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 46.31600000000001
- type: f1
value: 44.45281663598873
- task:
type: STS
dataset:
type: C-MTEB/BQ
name: MTEB BQ
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 69.12211326097868
- type: cos_sim_spearman
value: 71.0741302039443
- type: euclidean_pearson
value: 69.89070483887852
- type: euclidean_spearman
value: 71.07413020351787
- type: manhattan_pearson
value: 69.62345441260962
- type: manhattan_spearman
value: 70.8517591280618
- task:
type: Clustering
dataset:
type: C-MTEB/CLSClusteringP2P
name: MTEB CLSClusteringP2P
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 41.937723608805314
- task:
type: Clustering
dataset:
type: C-MTEB/CLSClusteringS2S
name: MTEB CLSClusteringS2S
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 40.34373057675427
- task:
type: Reranking
dataset:
type: C-MTEB/CMedQAv1-reranking
name: MTEB CMedQAv1
config: default
split: test
revision: None
metrics:
- type: map
value: 88.98896401788376
- type: mrr
value: 90.97119047619047
- task:
type: Reranking
dataset:
type: C-MTEB/CMedQAv2-reranking
name: MTEB CMedQAv2
config: default
split: test
revision: None
metrics:
- type: map
value: 89.59718540244556
- type: mrr
value: 91.41246031746032
- task:
type: Retrieval
dataset:
type: C-MTEB/CmedqaRetrieval
name: MTEB CmedqaRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 26.954
- type: map_at_10
value: 40.144999999999996
- type: map_at_100
value: 42.083999999999996
- type: map_at_1000
value: 42.181000000000004
- type: map_at_3
value: 35.709
- type: map_at_5
value: 38.141000000000005
- type: mrr_at_1
value: 40.71
- type: mrr_at_10
value: 48.93
- type: mrr_at_100
value: 49.921
- type: mrr_at_1000
value: 49.958999999999996
- type: mrr_at_3
value: 46.32
- type: mrr_at_5
value: 47.769
- type: ndcg_at_1
value: 40.71
- type: ndcg_at_10
value: 46.869
- type: ndcg_at_100
value: 54.234
- type: ndcg_at_1000
value: 55.854000000000006
- type: ndcg_at_3
value: 41.339
- type: ndcg_at_5
value: 43.594
- type: precision_at_1
value: 40.71
- type: precision_at_10
value: 10.408000000000001
- type: precision_at_100
value: 1.635
- type: precision_at_1000
value: 0.184
- type: precision_at_3
value: 23.348
- type: precision_at_5
value: 16.929
- type: recall_at_1
value: 26.954
- type: recall_at_10
value: 57.821999999999996
- type: recall_at_100
value: 88.08200000000001
- type: recall_at_1000
value: 98.83800000000001
- type: recall_at_3
value: 41.221999999999994
- type: recall_at_5
value: 48.241
- task:
type: PairClassification
dataset:
type: C-MTEB/CMNLI
name: MTEB Cmnli
config: default
split: validation
revision: None
metrics:
- type: cos_sim_accuracy
value: 83.6680697534576
- type: cos_sim_ap
value: 90.77401562455269
- type: cos_sim_f1
value: 84.68266427450101
- type: cos_sim_precision
value: 81.36177547942253
- type: cos_sim_recall
value: 88.28618190320317
- type: dot_accuracy
value: 83.6680697534576
- type: dot_ap
value: 90.76429465198817
- type: dot_f1
value: 84.68266427450101
- type: dot_precision
value: 81.36177547942253
- type: dot_recall
value: 88.28618190320317
- type: euclidean_accuracy
value: 83.6680697534576
- type: euclidean_ap
value: 90.77401909305344
- type: euclidean_f1
value: 84.68266427450101
- type: euclidean_precision
value: 81.36177547942253
- type: euclidean_recall
value: 88.28618190320317
- type: manhattan_accuracy
value: 83.40348767288035
- type: manhattan_ap
value: 90.57002020310819
- type: manhattan_f1
value: 84.51526032315978
- type: manhattan_precision
value: 81.25134843581445
- type: manhattan_recall
value: 88.05237315875614
- type: max_accuracy
value: 83.6680697534576
- type: max_ap
value: 90.77401909305344
- type: max_f1
value: 84.68266427450101
- task:
type: Retrieval
dataset:
type: C-MTEB/CovidRetrieval
name: MTEB CovidRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 69.705
- type: map_at_10
value: 78.648
- type: map_at_100
value: 78.888
- type: map_at_1000
value: 78.89399999999999
- type: map_at_3
value: 77.151
- type: map_at_5
value: 77.98
- type: mrr_at_1
value: 69.863
- type: mrr_at_10
value: 78.62599999999999
- type: mrr_at_100
value: 78.861
- type: mrr_at_1000
value: 78.867
- type: mrr_at_3
value: 77.204
- type: mrr_at_5
value: 78.005
- type: ndcg_at_1
value: 69.968
- type: ndcg_at_10
value: 82.44399999999999
- type: ndcg_at_100
value: 83.499
- type: ndcg_at_1000
value: 83.647
- type: ndcg_at_3
value: 79.393
- type: ndcg_at_5
value: 80.855
- type: precision_at_1
value: 69.968
- type: precision_at_10
value: 9.515
- type: precision_at_100
value: 0.9990000000000001
- type: precision_at_1000
value: 0.101
- type: precision_at_3
value: 28.802
- type: precision_at_5
value: 18.019
- type: recall_at_1
value: 69.705
- type: recall_at_10
value: 94.152
- type: recall_at_100
value: 98.84100000000001
- type: recall_at_1000
value: 100.0
- type: recall_at_3
value: 85.774
- type: recall_at_5
value: 89.252
- task:
type: Retrieval
dataset:
type: C-MTEB/DuRetrieval
name: MTEB DuRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 25.88
- type: map_at_10
value: 79.857
- type: map_at_100
value: 82.636
- type: map_at_1000
value: 82.672
- type: map_at_3
value: 55.184
- type: map_at_5
value: 70.009
- type: mrr_at_1
value: 89.64999999999999
- type: mrr_at_10
value: 92.967
- type: mrr_at_100
value: 93.039
- type: mrr_at_1000
value: 93.041
- type: mrr_at_3
value: 92.65
- type: mrr_at_5
value: 92.86
- type: ndcg_at_1
value: 89.64999999999999
- type: ndcg_at_10
value: 87.126
- type: ndcg_at_100
value: 89.898
- type: ndcg_at_1000
value: 90.253
- type: ndcg_at_3
value: 86.012
- type: ndcg_at_5
value: 85.124
- type: precision_at_1
value: 89.64999999999999
- type: precision_at_10
value: 41.735
- type: precision_at_100
value: 4.797
- type: precision_at_1000
value: 0.488
- type: precision_at_3
value: 77.267
- type: precision_at_5
value: 65.48
- type: recall_at_1
value: 25.88
- type: recall_at_10
value: 88.28399999999999
- type: recall_at_100
value: 97.407
- type: recall_at_1000
value: 99.29299999999999
- type: recall_at_3
value: 57.38799999999999
- type: recall_at_5
value: 74.736
- task:
type: Retrieval
dataset:
type: C-MTEB/EcomRetrieval
name: MTEB EcomRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 53.2
- type: map_at_10
value: 63.556000000000004
- type: map_at_100
value: 64.033
- type: map_at_1000
value: 64.044
- type: map_at_3
value: 60.983
- type: map_at_5
value: 62.588
- type: mrr_at_1
value: 53.2
- type: mrr_at_10
value: 63.556000000000004
- type: mrr_at_100
value: 64.033
- type: mrr_at_1000
value: 64.044
- type: mrr_at_3
value: 60.983
- type: mrr_at_5
value: 62.588
- type: ndcg_at_1
value: 53.2
- type: ndcg_at_10
value: 68.61699999999999
- type: ndcg_at_100
value: 70.88499999999999
- type: ndcg_at_1000
value: 71.15899999999999
- type: ndcg_at_3
value: 63.434000000000005
- type: ndcg_at_5
value: 66.301
- type: precision_at_1
value: 53.2
- type: precision_at_10
value: 8.450000000000001
- type: precision_at_100
value: 0.95
- type: precision_at_1000
value: 0.097
- type: precision_at_3
value: 23.5
- type: precision_at_5
value: 15.479999999999999
- type: recall_at_1
value: 53.2
- type: recall_at_10
value: 84.5
- type: recall_at_100
value: 95.0
- type: recall_at_1000
value: 97.1
- type: recall_at_3
value: 70.5
- type: recall_at_5
value: 77.4
- task:
type: Classification
dataset:
type: C-MTEB/IFlyTek-classification
name: MTEB IFlyTek
config: default
split: validation
revision: None
metrics:
- type: accuracy
value: 50.63485956136976
- type: f1
value: 38.286307407751266
- task:
type: Classification
dataset:
type: C-MTEB/JDReview-classification
name: MTEB JDReview
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 86.11632270168855
- type: ap
value: 54.43932599806482
- type: f1
value: 80.85485110996076
- task:
type: STS
dataset:
type: C-MTEB/LCQMC
name: MTEB LCQMC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 72.47315152994804
- type: cos_sim_spearman
value: 78.26531600908152
- type: euclidean_pearson
value: 77.8560788714531
- type: euclidean_spearman
value: 78.26531157334841
- type: manhattan_pearson
value: 77.70593783974188
- type: manhattan_spearman
value: 78.13880812439999
- task:
type: Reranking
dataset:
type: C-MTEB/Mmarco-reranking
name: MTEB MMarcoReranking
config: default
split: dev
revision: None
metrics:
- type: map
value: 28.088177976572222
- type: mrr
value: 27.125
- task:
type: Retrieval
dataset:
type: C-MTEB/MMarcoRetrieval
name: MTEB MMarcoRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 66.428
- type: map_at_10
value: 75.5
- type: map_at_100
value: 75.82600000000001
- type: map_at_1000
value: 75.837
- type: map_at_3
value: 73.74300000000001
- type: map_at_5
value: 74.87
- type: mrr_at_1
value: 68.754
- type: mrr_at_10
value: 76.145
- type: mrr_at_100
value: 76.432
- type: mrr_at_1000
value: 76.442
- type: mrr_at_3
value: 74.628
- type: mrr_at_5
value: 75.612
- type: ndcg_at_1
value: 68.754
- type: ndcg_at_10
value: 79.144
- type: ndcg_at_100
value: 80.60199999999999
- type: ndcg_at_1000
value: 80.886
- type: ndcg_at_3
value: 75.81599999999999
- type: ndcg_at_5
value: 77.729
- type: precision_at_1
value: 68.754
- type: precision_at_10
value: 9.544
- type: precision_at_100
value: 1.026
- type: precision_at_1000
value: 0.105
- type: precision_at_3
value: 28.534
- type: precision_at_5
value: 18.138
- type: recall_at_1
value: 66.428
- type: recall_at_10
value: 89.716
- type: recall_at_100
value: 96.313
- type: recall_at_1000
value: 98.541
- type: recall_at_3
value: 80.923
- type: recall_at_5
value: 85.48
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (zh-CN)
config: zh-CN
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 73.27841291190316
- type: f1
value: 70.65529957574735
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (zh-CN)
config: zh-CN
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.30127774041695
- type: f1
value: 76.10358226518304
- task:
type: Retrieval
dataset:
type: C-MTEB/MedicalRetrieval
name: MTEB MedicalRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 56.3
- type: map_at_10
value: 62.193
- type: map_at_100
value: 62.722
- type: map_at_1000
value: 62.765
- type: map_at_3
value: 60.633
- type: map_at_5
value: 61.617999999999995
- type: mrr_at_1
value: 56.3
- type: mrr_at_10
value: 62.193
- type: mrr_at_100
value: 62.722
- type: mrr_at_1000
value: 62.765
- type: mrr_at_3
value: 60.633
- type: mrr_at_5
value: 61.617999999999995
- type: ndcg_at_1
value: 56.3
- type: ndcg_at_10
value: 65.176
- type: ndcg_at_100
value: 67.989
- type: ndcg_at_1000
value: 69.219
- type: ndcg_at_3
value: 62.014
- type: ndcg_at_5
value: 63.766
- type: precision_at_1
value: 56.3
- type: precision_at_10
value: 7.46
- type: precision_at_100
value: 0.8829999999999999
- type: precision_at_1000
value: 0.098
- type: precision_at_3
value: 22.0
- type: precision_at_5
value: 14.04
- type: recall_at_1
value: 56.3
- type: recall_at_10
value: 74.6
- type: recall_at_100
value: 88.3
- type: recall_at_1000
value: 98.1
- type: recall_at_3
value: 66.0
- type: recall_at_5
value: 70.19999999999999
- task:
type: Classification
dataset:
type: C-MTEB/MultilingualSentiment-classification
name: MTEB MultilingualSentiment
config: default
split: validation
revision: None
metrics:
- type: accuracy
value: 76.44666666666666
- type: f1
value: 76.34548655475949
- task:
type: PairClassification
dataset:
type: C-MTEB/OCNLI
name: MTEB Ocnli
config: default
split: validation
revision: None
metrics:
- type: cos_sim_accuracy
value: 82.34975636166757
- type: cos_sim_ap
value: 85.44149338593267
- type: cos_sim_f1
value: 83.68654509610647
- type: cos_sim_precision
value: 78.46580406654344
- type: cos_sim_recall
value: 89.65153115100317
- type: dot_accuracy
value: 82.34975636166757
- type: dot_ap
value: 85.4415701376729
- type: dot_f1
value: 83.68654509610647
- type: dot_precision
value: 78.46580406654344
- type: dot_recall
value: 89.65153115100317
- type: euclidean_accuracy
value: 82.34975636166757
- type: euclidean_ap
value: 85.4415701376729
- type: euclidean_f1
value: 83.68654509610647
- type: euclidean_precision
value: 78.46580406654344
- type: euclidean_recall
value: 89.65153115100317
- type: manhattan_accuracy
value: 81.97076340010828
- type: manhattan_ap
value: 84.83614660756733
- type: manhattan_f1
value: 83.34167083541772
- type: manhattan_precision
value: 79.18250950570342
- type: manhattan_recall
value: 87.96198521647307
- type: max_accuracy
value: 82.34975636166757
- type: max_ap
value: 85.4415701376729
- type: max_f1
value: 83.68654509610647
- task:
type: Classification
dataset:
type: C-MTEB/OnlineShopping-classification
name: MTEB OnlineShopping
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 93.24
- type: ap
value: 91.3586656455605
- type: f1
value: 93.22999314249503
- task:
type: STS
dataset:
type: C-MTEB/PAWSX
name: MTEB PAWSX
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 39.05676042449009
- type: cos_sim_spearman
value: 44.996534098358545
- type: euclidean_pearson
value: 44.42418609172825
- type: euclidean_spearman
value: 44.995941361058996
- type: manhattan_pearson
value: 43.98118203238076
- type: manhattan_spearman
value: 44.51414152788784
- task:
type: STS
dataset:
type: C-MTEB/QBQTC
name: MTEB QBQTC
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 36.694269474438045
- type: cos_sim_spearman
value: 38.686738967031616
- type: euclidean_pearson
value: 36.822540068407235
- type: euclidean_spearman
value: 38.68690745429757
- type: manhattan_pearson
value: 36.77180703308932
- type: manhattan_spearman
value: 38.45414914148094
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (zh)
config: zh
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 65.81209017614124
- type: cos_sim_spearman
value: 66.5255285833172
- type: euclidean_pearson
value: 66.01848701752732
- type: euclidean_spearman
value: 66.5255285833172
- type: manhattan_pearson
value: 66.66433676370542
- type: manhattan_spearman
value: 67.07086311480214
- task:
type: STS
dataset:
type: C-MTEB/STSB
name: MTEB STSB
config: default
split: test
revision: None
metrics:
- type: cos_sim_pearson
value: 80.60785761283502
- type: cos_sim_spearman
value: 82.80278693241074
- type: euclidean_pearson
value: 82.47573315938638
- type: euclidean_spearman
value: 82.80290808593806
- type: manhattan_pearson
value: 82.49682028989669
- type: manhattan_spearman
value: 82.84565039346022
- task:
type: Reranking
dataset:
type: C-MTEB/T2Reranking
name: MTEB T2Reranking
config: default
split: dev
revision: None
metrics:
- type: map
value: 66.37886004738723
- type: mrr
value: 76.08501655006394
- task:
type: Retrieval
dataset:
type: C-MTEB/T2Retrieval
name: MTEB T2Retrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 28.102
- type: map_at_10
value: 78.071
- type: map_at_100
value: 81.71000000000001
- type: map_at_1000
value: 81.773
- type: map_at_3
value: 55.142
- type: map_at_5
value: 67.669
- type: mrr_at_1
value: 90.9
- type: mrr_at_10
value: 93.29499999999999
- type: mrr_at_100
value: 93.377
- type: mrr_at_1000
value: 93.379
- type: mrr_at_3
value: 92.901
- type: mrr_at_5
value: 93.152
- type: ndcg_at_1
value: 90.9
- type: ndcg_at_10
value: 85.564
- type: ndcg_at_100
value: 89.11200000000001
- type: ndcg_at_1000
value: 89.693
- type: ndcg_at_3
value: 87.024
- type: ndcg_at_5
value: 85.66
- type: precision_at_1
value: 90.9
- type: precision_at_10
value: 42.208
- type: precision_at_100
value: 5.027
- type: precision_at_1000
value: 0.517
- type: precision_at_3
value: 75.872
- type: precision_at_5
value: 63.566
- type: recall_at_1
value: 28.102
- type: recall_at_10
value: 84.44500000000001
- type: recall_at_100
value: 95.91300000000001
- type: recall_at_1000
value: 98.80799999999999
- type: recall_at_3
value: 56.772999999999996
- type: recall_at_5
value: 70.99499999999999
- task:
type: Classification
dataset:
type: C-MTEB/TNews-classification
name: MTEB TNews
config: default
split: validation
revision: None
metrics:
- type: accuracy
value: 53.10599999999999
- type: f1
value: 51.40415523558322
- task:
type: Clustering
dataset:
type: C-MTEB/ThuNewsClusteringP2P
name: MTEB ThuNewsClusteringP2P
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 69.6145576098232
- task:
type: Clustering
dataset:
type: C-MTEB/ThuNewsClusteringS2S
name: MTEB ThuNewsClusteringS2S
config: default
split: test
revision: None
metrics:
- type: v_measure
value: 63.7129548775017
- task:
type: Retrieval
dataset:
type: C-MTEB/VideoRetrieval
name: MTEB VideoRetrieval
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 60.199999999999996
- type: map_at_10
value: 69.724
- type: map_at_100
value: 70.185
- type: map_at_1000
value: 70.196
- type: map_at_3
value: 67.95
- type: map_at_5
value: 69.155
- type: mrr_at_1
value: 60.199999999999996
- type: mrr_at_10
value: 69.724
- type: mrr_at_100
value: 70.185
- type: mrr_at_1000
value: 70.196
- type: mrr_at_3
value: 67.95
- type: mrr_at_5
value: 69.155
- type: ndcg_at_1
value: 60.199999999999996
- type: ndcg_at_10
value: 73.888
- type: ndcg_at_100
value: 76.02799999999999
- type: ndcg_at_1000
value: 76.344
- type: ndcg_at_3
value: 70.384
- type: ndcg_at_5
value: 72.541
- type: precision_at_1
value: 60.199999999999996
- type: precision_at_10
value: 8.67
- type: precision_at_100
value: 0.9650000000000001
- type: precision_at_1000
value: 0.099
- type: precision_at_3
value: 25.8
- type: precision_at_5
value: 16.520000000000003
- type: recall_at_1
value: 60.199999999999996
- type: recall_at_10
value: 86.7
- type: recall_at_100
value: 96.5
- type: recall_at_1000
value: 99.0
- type: recall_at_3
value: 77.4
- type: recall_at_5
value: 82.6
- task:
type: Classification
dataset:
type: C-MTEB/waimai-classification
name: MTEB Waimai
config: default
split: test
revision: None
metrics:
- type: accuracy
value: 88.08
- type: ap
value: 72.66435456846166
- type: f1
value: 86.55995793551286
---
**新闻 | News**
**[2024-04-06]** 开源[puff](https://huggingface.co/infgrad/puff-base-v1)系列模型，**专门针对检索和语义匹配任务，更多的考虑泛化性和私有通用测试集效果，向量维度可变，中英双语**。
**[2024-02-27]** 开源stella-mrl-large-zh-v3.5-1792d模型，支持**向量可变维度**。
**[2024-02-17]** 开源stella v3系列、dialogue编码模型和相关训练数据。
**[2023-10-19]** 开源stella-base-en-v2 使用简单，**不需要任何前缀文本**。
**[2023-10-12]** 开源stella-base-zh-v2和stella-large-zh-v2, 效果更好且使用简单，**不需要任何前缀文本**。
**[2023-09-11]** 开源stella-base-zh和stella-large-zh
欢迎去[本人主页](https://huggingface.co/infgrad)查看最新模型，并提出您的宝贵意见！
# 1 开源清单
本次开源2个通用向量编码模型和一个针对dialogue进行编码的向量模型，同时开源全量160万对话重写数据集和20万的难负例的检索数据集。
**开源模型：**
| ModelName | ModelSize | MaxTokens | EmbeddingDimensions | Language | Scenario | C-MTEB Score |
|---------------------------------------------------------------------------------------------------------------|-----------|-----------|---------------------|----------|----------|--------------|
| [infgrad/stella-base-zh-v3-1792d](https://huggingface.co/infgrad/stella-base-zh-v3-1792d) | 0.4GB | 512 | 1792 | zh-CN | 通用文本 | 67.96 |
| [infgrad/stella-large-zh-v3-1792d](https://huggingface.co/infgrad/stella-large-zh-v3-1792d) | 1.3GB | 512 | 1792 | zh-CN | 通用文本 | 68.48 |
| [infgrad/stella-dialogue-large-zh-v3-1792d](https://huggingface.co/infgrad/stella-dialogue-large-zh-v3-1792d) | 1.3GB | 512 | 1792 | zh-CN | **对话文本** | 不适用 |
**开源数据：**
1. [全量对话重写数据集](https://huggingface.co/datasets/infgrad/dialogue_rewrite_llm) 约160万
2. [部分带有难负例的检索数据集](https://huggingface.co/datasets/infgrad/retrieval_data_llm) 约20万
上述数据集均使用LLM构造，欢迎各位贡献数据集。
# 2 使用方法
## 2.1 通用编码模型使用方法
直接SentenceTransformer加载即可：
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("infgrad/stella-base-zh-v3-1792d")
# model = SentenceTransformer("infgrad/stella-large-zh-v3-1792d")
vectors = model.encode(["text1", "text2"])
```
## 2.2 dialogue编码模型使用方法
**使用场景：**
**在一段对话中，需要根据用户语句去检索相关文本，但是对话中的用户语句存在大量的指代和省略，导致直接使用通用编码模型效果不好，
可以使用本项目的专门的dialogue编码模型进行编码**
**使用要点：**
1. 对dialogue进行编码时，dialogue中的每个utterance需要是如下格式：`"{ROLE}: {TEXT}"`，然后使用`[SEP]` join一下
2. 整个对话都要送入模型进行编码，如果长度不够就删掉早期的对话，**编码后的向量本质是对话中最后一句话的重写版本的向量！！**
3. 对话用stella-dialogue-large-zh-v3-1792d编码，被检索文本使用stella-large-zh-v3-1792d进行编码，所以本场景是需要2个编码模型的
如果对使用方法还有疑惑，请到下面章节阅读该模型是如何训练的。
使用示例：
```python
from sentence_transformers import SentenceTransformer
dial_model = SentenceTransformer("infgrad/stella-dialogue-large-zh-v3-1792d")
general_model = SentenceTransformer("infgrad/stella-large-zh-v3-1792d")
# dialogue = ["张三: 吃饭吗", "李四: 等会去"]
dialogue = ["A: 最近去打篮球了吗", "B: 没有"]
corpus = ["B没打篮球是因为受伤了。", "B没有打乒乓球"]
last_utterance_vector = dial_model.encode(["[SEP]".join(dialogue)], normalize_embeddings=True)
corpus_vectors = general_model.encode(corpus, normalize_embeddings=True)
# 计算相似度
sims = (last_utterance_vector * corpus_vectors).sum(axis=1)
print(sims)
```
# 3 通用编码模型训练技巧分享
## hard negative
难负例挖掘也是个经典的trick了，几乎总能提升效果
## dropout-1d
dropout已经是深度学习的标配，我们可以稍微改造下使其更适合句向量的训练。
我们在训练时会尝试让每一个token-embedding都可以表征整个句子，而在推理时使用mean_pooling从而达到类似模型融合的效果。
具体操作是在mean_pooling时加入dropout_1d，torch代码如下：
```python
vector_dropout = nn.Dropout1d(0.3) # 算力有限，试了0.3和0.5 两个参数，其中0.3更优
last_hidden_state = bert_model(...)[0]
last_hidden = last_hidden_state.masked_fill(~attention_mask[..., None].bool(), 0.0)
last_hidden = vector_dropout(last_hidden)
vectors = last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
```
# 4 dialogue编码模型细节
## 4.1 为什么需要一个dialogue编码模型？
参见本人历史文章：https://www.zhihu.com/pin/1674913544847077376
## 4.2 训练数据
单条数据示例：
```json
{
"dialogue": [
"A: 最近去打篮球了吗",
"B: 没有"
],
"last_utterance_rewrite": "B: 我最近没有去打篮球"
}
```
## 4.3 训练Loss
```
loss = cosine_loss( dial_model.encode(dialogue), existing_model.encode(last_utterance_rewrite) )
```
dial_model就是要被训练的模型，本人是以stella-large-zh-v3-1792d作为base-model进行继续训练的
existing_model就是现有训练好的**通用编码模型**，本人使用的是stella-large-zh-v3-1792d
已开源dialogue-embedding的全量训练数据，理论上可以复现本模型效果。
Loss下降情况：
<div align="center">
<img src="dial_loss.png" alt="icon" width="2000px"/>
</div>
## 4.4 效果
目前还没有专门测试集，本人简单测试了下是有效果的，部分测试结果见文件`dial_retrieval_test.xlsx`。
# 5 后续TODO
1. 更多的dial-rewrite数据
2. 不同EmbeddingDimensions的编码模型
# 6 FAQ
Q: 为什么向量维度是1792？\
A: 最初考虑发布768、1024，768+768，1024+1024，1024+768维度，但是时间有限，先做了1792就只发布1792维度的模型。理论上维度越高效果越好。
Q: 如何复现CMTEB效果？\
A: SentenceTransformer加载后直接用官方评测脚本就行，注意对于Classification任务向量需要先normalize一下
Q: 复现的CMTEB效果和本文不一致？\
A: 聚类不一致正常，官方评测代码没有设定seed，其他不一致建议检查代码或联系本人。
Q: 如何选择向量模型？\
A: 没有免费的午餐，在自己测试集上试试，本人推荐bge、e5和stella.
Q: 长度为什么只有512，能否更长？\
A: 可以但没必要，长了效果普遍不好，这是当前训练方法和数据导致的，几乎无解，建议长文本还是走分块。
Q: 训练资源和算力？\
A: 亿级别的数据，单卡A100要一个月起步
|
hustcw/clap-asm | hustcw | "2024-03-04T08:40:55Z" | 1,931 | 12 | transformers | [
"transformers",
"safetensors",
"roformer",
"feature-extraction",
"custom_code",
"arxiv:2402.16928",
"license:mit",
"region:us"
] | feature-extraction | "2024-02-29T06:51:24Z" | ---
license: mit
---
<h1 align="center">CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision</h1>
<h4 align="center">
<p>
<a href=#about>About</a> |
<a href=#news>News</a> |
<a href=#quickstart>QuickStart</a> |
<a href=#citation>Citation</a>
<p>
</h4>
## About
CLAP (Contrastive Language-Assembly Pre-training) is a framework that learns binary code representations through natural language supervision. By aligning binary code with natural language explanations, it improves analysis performance in few-shot and zero-shot scenarios. Utilizing a dataset engine capable of automatically generating 195 million pairs of code snippets and their descriptions, CLAP offers a method with exceptional transferability in the field of binary code analysis. Our goal is to provide an effective tool for researchers and practitioners in binary code analysis, with our models accessible on the Hugging Face Model Hub.
<img alt="clap_model" src="https://cdn-uploads.huggingface.co/production/uploads/6342dd731bdd3dfa55d66931/qCNIjTlzOPtTpI3NLBY14.png">
## News
- [2024/2/29] CLAP is available on Hugging Face Model Hub ([clap-asm](https://huggingface.co/hustcw/clap-asm) and [clap-text](https://huggingface.co/hustcw/clap-text)).
- [2024/2/28] CLAP is now on [ArXiv](https://arxiv.org/abs/2402.16928).
## QuickStart
This document will help you set up and start using the CLAP model for various tasks, including fine-grained classification of sorting algorithms, malware, and cryptographic algorithms without any further training.
### Requirements
- Python 3.6 or higher
- [PyTorch](https://pytorch.org/get-started/locally/)
- [Transformers library](https://huggingface.co/docs/transformers/installation)
- A CUDA-enabled GPU is highly recommended for faster processing.
Ensure you have Python and PyTorch installed on your system. Then, install the Transformers library using pip:
```bash
pip install transformers
```
### Preparing Tokenizers and Models
Import necessary libraries and initialize the model and tokenizers:
```python
import torch
from transformers import AutoModel, AutoTokenizer
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
asm_tokenizer = AutoTokenizer.from_pretrained("hustcw/clap-asm", trust_remote_code=True)
text_tokenizer = AutoTokenizer.from_pretrained("hustcw/clap-text", trust_remote_code=True)
asm_encoder = AutoModel.from_pretrained("hustcw/clap-asm", trust_remote_code=True).to(device)
text_encoder = AutoModel.from_pretrained("hustcw/clap-text", trust_remote_code=True).to(device)
```
### Example Use Cases
**Fine-Grained Sorting Algorithm Classification (Zero-Shot)**
1. Load your assembly (asm) code dataset. For demonstration, we use a JSON file containing assembly code snippets related to bubble sort:
```python
with open("./CaseStudy/bubblesort.json") as fp:
asm = json.load(fp)
```
2. Define your classification prompts:
```python
prompts = [
"This is a function related to bubble sort",
"This is a function related to selection sort",
...
]
```
3. Encode the assembly code and prompts, then perform classification:
```python
# Encode assembly code
asm_input = asm_tokenizer([asm], padding=True, return_tensors="pt").to(device)
asm_embedding = asm_encoder(**asm_input)
# Encode prompts
text_input = text_tokenizer(prompts, return_tensors='pt').to(device)
text_embeddings = text_encoder(**text_input)
# Classification
logits = torch.einsum("nc,ck->nk", [asm_embedding.last_hidden_state, text_embeddings.last_hidden_state.T])
preds = torch.softmax(logits / 0.07, dim=1).squeeze(0).tolist()
# Output predictions
for i, prompt in enumerate(prompts):
print(f"Probability: {preds[i]*100:.3f}%, Text: {prompt}")
```
Repeat the process for any other classification tasks you want, such as malware classification and cryptographic algorithm identification, by loading the respective datasets and defining the relevant natural language prompts.
## Citation
If this work is helpful for your research, please consider giving a star 🌟 and citing our work.
```
@misc{wang2024clap,
title={CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision},
author={Hao Wang and Zeyu Gao and Chao Zhang and Zihan Sha and Mingyang Sun and Yuchen Zhou and Wenyu Zhu and Wenju Sun and Han Qiu and Xi Xiao},
year={2024},
eprint={2402.16928},
archivePrefix={arXiv},
primaryClass={cs.SE}
}
``` |
ehristoforu/Visionix-alpha | ehristoforu | "2024-06-10T15:06:04Z" | 1,931 | 20 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"sdxl",
"visionix",
"visionix-alpha",
"realism",
"hyperrealism",
"photorealism",
"photo",
"cinematic",
"nature",
"human",
"lighting",
"trained",
"text-to-image",
"en",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2024-06-09T20:46:26Z" | ---
license: creativeml-openrail-m
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
- safetensors
- stable-diffusion
- sdxl
- visionix
- visionix-alpha
- realism
- hyperrealism
- photorealism
- photo
- cinematic
- nature
- human
- lighting
- trained
inference:
parameters:
num_inference_steps: 22
guidance_scale: 5.5
negative_prompt: >-
cartoon, 3D, disfigured, bad, art, deformed, extra limbs, weird, blurry, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn, hands, poorly drawn face, mutation, ugly, bad, anatomy, bad proportions, extra limbs, clone, clone-faced, cross proportions, missing arms, malformed limbs, missing legs, mutated, hands, fused fingers, too many fingers, photo shop, video game, ugly, tiling, cross-eye, mutation of eyes, long neck, bonnet, hat, beanie, cap, B&W
---
# **VisioniX** Alpha - the most powerful realism-model
[>>> Inpainting version <<<](https://huggingface.co/ehristoforu/Visionix-alpha-inpainting)
We present the best realism model at the moment - VisioniX.
## About this model
This model was created through complex training on huge, ultra-realistic datasets.
### Why is this model better than its competitors?
All, absolutely all realism models make one important mistake: they chase only super realism (super detailed skin and others) completely forgetting about general aesthetics, anatomy, etc.
### Who is this model for?
The main feature of this model is that the model can generate not only super realistic photos, but also realistic detailed art and much more, so the model is suitable for a large audience and can solve a wide range of problems. If this model still does not suit you, we recommend using FluentlyXL model.
### Optimal settings for this model
- **Sampler**: *DPM++ 3M SDE* (Karras), DPM++ SDE (Karras)
- **Inference Steps**: *22*-25
- **Guidance Scale (CFG)**: 5-7
- **Negative Prompt**: *not* or:
```
cartoon, 3D, disfigured, bad, art, deformed, extra limbs, weird, blurry, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn, hands, poorly drawn face, mutation, ugly, bad, anatomy, bad proportions, extra limbs, clone, clone-faced, cross proportions, missing arms, malformed limbs, missing legs, mutated, hands, fused fingers, too many fingers, photo shop, video game, ugly, tiling, cross-eye, mutation of eyes, long neck, bonnet, hat, beanie, cap, B&W
```
### End
After this model, you will not want to use the rest of the realism models, if you like the model, we ask you to leave a good review and a couple of your results in the review, thank you, this will greatly help in promoting this wonderful model 💖 |
gustavomacedo/ORPO-Llama3 | gustavomacedo | "2024-06-21T15:02:59Z" | 1,931 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-21T14:52:06Z" | ---
base_model: unsloth/llama-3-8b-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
---
# Uploaded model
- **Developed by:** gustavomacedo
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
jondurbin/airoboros-l2-70b-gpt4-m2.0 | jondurbin | "2023-08-14T10:12:42Z" | 1,930 | 10 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-m2.0",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-30T09:41:55Z" | ---
license: other
datasets:
- jondurbin/airoboros-gpt4-m2.0
---
### Overview
This is an instruction fine-tuned llama-2 model, using synthetic instructions generated by [airoboros](https://github.com/jondurbin/airoboros)
- The 2.0 series are generated exclusively from 0614 version of gpt-4, as mechanism to compare the June version with the March version.
- The m2.0 series have the 1.4.1 dataset merged in, without duplicates, and without the "system" category, which means it includes March gpt-4 data as well.
- 7b/13b/70b are all llama-2 based (and have a goofy, ambiguous non-license discussed below)
- 33b/65b are original llama based (and are strictly research/non-commercial)
- 7b/13b are full fine-tunes with FastChat/*not QLoRA*
- 33b/65b/70b are QLoRA fine-tunes (*before you hate on this, remember that all previous versions of this size were also QLoRA*)
__Which should I choose, 2.0 or m2.0?__ I have no idea, try them both and see which is better. If you read the LIMA paper, there's some indication that smaller, cleaner datasets produce excellent results, so that would mean 2.0 is probably a better choice. If you really enjoyed 1.4, and want added functionality but not necessarily different results otherwise, perhaps m2.0.
### Prompt format
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
Why the "regardless of ..." part?
- laws vary widely based on time and location
- language model may conflate certain words with laws, e.g. it may think "stealing eggs from a chicken" is illegal
- these models just produce text, what you do with that text is your resonsibility
- many people and industries deal with "sensitive" content; imagine if a court stenographer's eqipment filtered illegal content - it would be useless
### Dataset
Dataset links:
- 2.0 series https://hf.co/datasets/jondurbin/airoboros-gpt4-2.0
- merged/m2.0 series https://hf.co/datasets/jondurbin/airoboros-gpt4-m2.0
Dataset creation details/configuration: https://gist.github.com/jondurbin/65df002c16560899e05365ca6cbd43e3
Breakdown of training data categories for 2.0/m2.0 datasets:
### Helpful usage tips
*The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.*
#### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
#### Coding
You can ask for fairly complex coding instructions with multiple criteria, e.g.:
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or inline criteria:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
#### Agent/function calling
The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML.
Example prompt:
```
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.
Input: I want to know how many times 'Python' is mentioned in my text file.
Available functions:
file_analytics:
description: This tool performs various operations on a text file.
params:
action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
filters:
keyword: The word or phrase we want to search for.
```
Response:
```json
{
"function": "file_analytics",
"params": {
"action": "count_occurrences",
"filters": {
"keyword": "Python"
}
}
}
```
#### Chain-of-thought
You can ask for several possible responses to a given problem, with a ranking and final answer selection.
Example prompt:
```
A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.
```
Example response:
```
Solution 1:
In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players).
The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows:
n(n-1)/2 = 45
Solving this equation gives us n=10.
Final answer: There were 10 players in the tournament.
Solution 2:
Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers.
If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players.
Final answer: There were 10 players in the tournament.
Solution 3:
We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played.
Final answer: There were 10 players in the tournament.
Ranking of solutions from best to worst:
1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer.
2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer.
3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer.
Best and final answer: There were 10 players in the tournament.
```
#### reWOO style execution planning
The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions!
Example prompt:
```
Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.
Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?
The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]
Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?
```
Response:
```
Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020.
:evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner]
Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate.
:evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?]
Plan: Conduct another web search to find the most famous work of the identified laureate.
:evidence2: = DuckDuckGo[Most famous work of :evidence1:]
Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search.
:evidence3: = HyperlinkExtractor[:evidence2:]
Plan: Use the TextScraper tool to extract information from the relevant links.
:evidence4: = TextScraper[:evidence3:]
Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information.
:evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?]
Answer: :evidence5:
```
For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening:
```python
import re
import requests
def inject_context(input_text, **context):
for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)):
input_text = input_text.replace(ref, context.get(ref, ""))
return input_text
def duckduckgo(input_text, **context):
search_string = inject_context(input_text, **context)
... search via duck duck go using search_string
... return text content
def link_extractor(input_text, **context):
input_text = inject_context(input_text, **context)
return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I))))
def scrape(input_text, **context):
input_text = inject_context(input_text, **context)
text = []
for link in input_text.splitlines():
text.append(requests.get(link).text)
return "\n".join(text)
def infer(input_text, **context)
prompt = inject_context(input_text, **context)
... call model with prompt, return output
def parse_plan(plan):
method_map = {
"DuckDuckGo": duckduckgo,
"HyperlinkExtractor": link_extractor,
"KnowledgeModel": infer,
"TextScraper": scrape,
}
context = {}
for line in plan.strip().splitlines():
if line.startswith("Plan:"):
print(line)
continue
parts = re.match("^(:evidence[0-9]+:")\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I)
if not parts:
if line.startswith("Answer: "):
return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...")
raise RuntimeError("bad format: " + line)
context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context)
```
### Contribute
If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data,
take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details.
To help me with the OpenAI/compute costs:
- https://bmc.link/jondurbin
- ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11
- BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf
### Licence and usage restrictions
The airoboros 2.0/m2.0 models are built on top of either llama or llama-2. Any model with `-l2-` in the name uses llama2, `..-33b-...` and `...-65b-...` are based on the original llama.
#### Llama (original) models
If the model was based on the original llama (33b/65b), the license is __cc-by-nc-4.0__ and is for research/academic use only -- no commercial usage whatsoever!
#### Llama-2 models
Base model has a custom Meta license:
- See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta.
- See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta.
The fine-tuning data was generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros)
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely indemnify me. |
chargoddard/Chronorctypus-Limarobormes-13b | chargoddard | "2024-01-04T18:22:41Z" | 1,930 | 12 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"arxiv:2306.01708",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-21T04:22:30Z" | ---
tags:
- llama
- merge
---
Five different instruction-tuned models (which I'm sure are intuitively obvious from the name) merged using the methodology described in [Resolving Interference When Merging Models](https://arxiv.org/abs/2306.01708).
In theory this should retain more of the capabilites of the constituent models than a straight linear merge would. In my testing, it feels quite capable.
Base model used for the merge: [TheBloke/Llama-2-13B-fp16](https://huggingface.co/TheBloke/Llama-2-13B-fp16)
Models merged in:
* [OpenOrca-Platypus2-13B](https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B)
* [limarp-13b-merged](https://huggingface.co/Oniichat/limarp-13b-merged)
* [Nous-Hermes-Llama2-13b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b)
* [chronos-13b-v2](https://huggingface.co/elinas/chronos-13b-v2)
* [airoboros-l2-13b-gpt4-1.4.1](https://huggingface.co/jondurbin/airoboros-l2-13b-gpt4-1.4.1)
Works quite well with Alpaca-style prompts:
```
### Instruction:
...
### Response:
```
The script I used to perform the merge is available [here](https://github.com/cg123/ties-merge).
The command that produced this model:
```
python ties_merge.py TheBloke/Llama-2-13B-fp16 ./Chronorctypus-Limarobormes-13b --merge elinas/chronos-13b-v2 --merge Open-Orca/OpenOrca-Platypus2-13B --merge Oniichat/limarp-13b-merged --merge jondurbin/airoboros-l2-13b-gpt4-1.4.1 --merge NousResearch/Nous-Hermes-Llama2-13b --cuda
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_chargoddard__Chronorctypus-Limarobormes-13b)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 49.88 |
| ARC (25-shot) | 59.9 |
| HellaSwag (10-shot) | 82.75 |
| MMLU (5-shot) | 58.45 |
| TruthfulQA (0-shot) | 51.9 |
| Winogrande (5-shot) | 74.43 |
| GSM8K (5-shot) | 3.87 |
| DROP (3-shot) | 17.89 |
|
bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF | bartowski | "2024-05-12T16:38:47Z" | 1,930 | 3 | null | [
"gguf",
"Llama-3",
"instruct",
"finetune",
"chatml",
"axolotl",
"roleplay",
"text-generation",
"en",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:apache-2.0",
"region:us"
] | text-generation | "2024-05-12T11:35:10Z" | ---
base_model: meta-llama/Meta-Llama-3-8B
tags:
- Llama-3
- instruct
- finetune
- chatml
- axolotl
- roleplay
license: apache-2.0
language:
- en
quantized_by: bartowski
pipeline_tag: text-generation
---
## Llamacpp imatrix Quantizations of Pantheon-RP-1.0-8b-Llama-3
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2854">b2854</a> for quantization.
Original model: https://huggingface.co/Gryphe/Pantheon-RP-1.0-8b-Llama-3
All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
## Prompt format
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Pantheon-RP-1.0-8b-Llama-3-Q8_0.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
| [Pantheon-RP-1.0-8b-Llama-3-Q6_K.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
| [Pantheon-RP-1.0-8b-Llama-3-Q5_K_M.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
| [Pantheon-RP-1.0-8b-Llama-3-Q5_K_S.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
| [Pantheon-RP-1.0-8b-Llama-3-Q4_K_M.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
| [Pantheon-RP-1.0-8b-Llama-3-Q4_K_S.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ4_NL.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ4_NL.gguf) | IQ4_NL | 4.67GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ4_XS.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Pantheon-RP-1.0-8b-Llama-3-Q3_K_L.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
| [Pantheon-RP-1.0-8b-Llama-3-Q3_K_M.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ3_M.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ3_S.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ3_S.gguf) | IQ3_S | 3.68GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
| [Pantheon-RP-1.0-8b-Llama-3-Q3_K_S.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ3_XS.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ3_XXS.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [Pantheon-RP-1.0-8b-Llama-3-Q2_K.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ2_M.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ2_S.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ2_XS.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ2_XXS.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ2_XXS.gguf) | IQ2_XXS | 2.39GB | Lower quality, uses SOTA techniques to be usable. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ1_M.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ1_M.gguf) | IQ1_M | 2.16GB | Extremely low quality, *not* recommended. |
| [Pantheon-RP-1.0-8b-Llama-3-IQ1_S.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF/blob/main/Pantheon-RP-1.0-8b-Llama-3-IQ1_S.gguf) | IQ1_S | 2.01GB | Extremely low quality, *not* recommended. |
## Downloading using huggingface-cli
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF --include "Pantheon-RP-1.0-8b-Llama-3-Q4_K_M.gguf" --local-dir ./ --local-dir-use-symlinks False
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/Pantheon-RP-1.0-8b-Llama-3-GGUF --include "Pantheon-RP-1.0-8b-Llama-3-Q8_0.gguf/*" --local-dir Pantheon-RP-1.0-8b-Llama-3-Q8_0 --local-dir-use-symlinks False
```
You can either specify a new local-dir (Pantheon-RP-1.0-8b-Llama-3-Q8_0) or download them all in place (./)
## Which file should I choose?
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
flax-community/roberta-swahili-news-classification | flax-community | "2023-03-19T09:03:04Z" | 1,929 | 0 | transformers | [
"transformers",
"pytorch",
"jax",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"sw",
"dataset:flax-community/swahili-safi",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2022-03-02T23:29:05Z" | ---
language: sw
widget:
- text: "Idris ameandika kwenye ukurasa wake wa Instagram akimkumbusha Diamond kutekeleza ahadi yake kumpigia Zari magoti kumuomba msamaha kama alivyowahi kueleza awali.Idris ameandika;"
datasets:
- flax-community/swahili-safi
---
## Swahili News Classification with RoBERTa
This model was trained using HuggingFace's Flax framework and is part of the [JAX/Flax Community Week](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104) organized by [HuggingFace](https://huggingface.co). All training was done on a TPUv3-8 VM sponsored by the Google Cloud team.
This [model](https://huggingface.co/flax-community/roberta-swahili) was used as the base and fine-tuned for this task.
## How to use
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("flax-community/roberta-swahili-news-classification")
model = AutoModelForSequenceClassification.from_pretrained("flax-community/roberta-swahili-news-classification")
```
```
Eval metrics: {'accuracy': 0.9153416415986249}
```
|
german-nlp-group/electra-base-german-uncased | german-nlp-group | "2024-04-07T21:20:14Z" | 1,929 | 6 | transformers | [
"transformers",
"pytorch",
"electra",
"pretraining",
"commoncrawl",
"uncased",
"umlaute",
"umlauts",
"german",
"deutsch",
"de",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | "2022-03-02T23:29:05Z" | ---
language: de
license: mit
thumbnail: "https://raw.githubusercontent.com/German-NLP-Group/german-transformer-training/master/model_cards/german-electra-logo.png"
tags:
- electra
- commoncrawl
- uncased
- umlaute
- umlauts
- german
- deutsch
---
# German Electra Uncased
<img width="300px" src="https://raw.githubusercontent.com/German-NLP-Group/german-transformer-training/master/model_cards/german-electra-logo.png">
[¹]
## Version 2 Release
We released an improved version of this model. Version 1 was trained for 766,000 steps. For this new version we continued the training for an additional 734,000 steps. It therefore follows that version 2 was trained on a total of 1,500,000 steps. See "Evaluation of Version 2: GermEval18 Coarse" below for details.
## Model Info
This Model is suitable for training on many downstream tasks in German (Q&A, Sentiment Analysis, etc.).
It can be used as a drop-in replacement for **BERT** in most down-stream tasks (**ELECTRA** is even implemented as an extended **BERT** Class).
At the time of release (August 2020) this model is the best performing publicly available German NLP model on various German evaluation metrics (CONLL03-DE, GermEval18 Coarse, GermEval18 Fine). For GermEval18 Coarse results see below. More will be published soon.
## Installation
This model has the special feature that it is **uncased** but does **not strip accents**.
This possibility was added by us with [PR #6280](https://github.com/huggingface/transformers/pull/6280).
To use it you have to use Transformers version 3.1.0 or newer.
```bash
pip install transformers -U
```
## Uncase and Umlauts ('Ö', 'Ä', 'Ü')
This model is uncased. This helps especially for domains where colloquial terms with uncorrect capitalization is often used.
The special characters 'ö', 'ü', 'ä' are included through the `strip_accent=False` option, as this leads to an improved precision.
## Creators
This model was trained and open sourced in conjunction with the [**German NLP Group**](https://github.com/German-NLP-Group) in equal parts by:
- [**Philip May**](https://philipmay.org) - [Deutsche Telekom](https://www.telekom.de/)
- [**Philipp Reißel**](https://www.linkedin.com/in/philipp-reissel/) - [ambeRoad](https://amberoad.de/)
## Evaluation of Version 2: GermEval18 Coarse
We evaluated all language models on GermEval18 with the F1 macro score. For each model we did an extensive automated hyperparameter search. With the best hyperparmeters we did fit the moodel multiple times on GermEval18. This is done to cancel random effects and get results of statistical relevance.
## Checkpoint evaluation
Since it it not guaranteed that the last checkpoint is the best, we evaluated the checkpoints on GermEval18. We found that the last checkpoint is indeed the best. The training was stable and did not overfit the text corpus.
## Pre-training details
### Data
- Cleaned Common Crawl Corpus 2019-09 German: [CC_net](https://github.com/facebookresearch/cc_net) (Only head coprus and filtered for language_score > 0.98) - 62 GB
- German Wikipedia Article Pages Dump (20200701) - 5.5 GB
- German Wikipedia Talk Pages Dump (20200620) - 1.1 GB
- Subtitles - 823 MB
- News 2018 - 4.1 GB
The sentences were split with [SojaMo](https://github.com/tsproisl/SoMaJo). We took the German Wikipedia Article Pages Dump 3x to oversample. This approach was also used in a similar way in GPT-3 (Table 2.2).
More Details can be found here [Preperaing Datasets for German Electra Github](https://github.com/German-NLP-Group/german-transformer-training)
### Electra Branch no_strip_accents
Because we do not want to stip accents in our training data we made a change to Electra and used this repo [Electra no_strip_accents](https://github.com/PhilipMay/electra/tree/no_strip_accents) (branch `no_strip_accents`). Then created the tf dataset with:
```bash
python build_pretraining_dataset.py --corpus-dir <corpus_dir> --vocab-file <dir>/vocab.txt --output-dir ./tf_data --max-seq-length 512 --num-processes 8 --do-lower-case --no-strip-accents
```
### The training
The training itself can be performed with the Original Electra Repo (No special case for this needed).
We run it with the following Config:
<details>
<summary>The exact Training Config</summary>
<br/>debug False
<br/>disallow_correct False
<br/>disc_weight 50.0
<br/>do_eval False
<br/>do_lower_case True
<br/>do_train True
<br/>electra_objective True
<br/>embedding_size 768
<br/>eval_batch_size 128
<br/>gcp_project None
<br/>gen_weight 1.0
<br/>generator_hidden_size 0.33333
<br/>generator_layers 1.0
<br/>iterations_per_loop 200
<br/>keep_checkpoint_max 0
<br/>learning_rate 0.0002
<br/>lr_decay_power 1.0
<br/>mask_prob 0.15
<br/>max_predictions_per_seq 79
<br/>max_seq_length 512
<br/>model_dir gs://XXX
<br/>model_hparam_overrides {}
<br/>model_name 02_Electra_Checkpoints_32k_766k_Combined
<br/>model_size base
<br/>num_eval_steps 100
<br/>num_tpu_cores 8
<br/>num_train_steps 766000
<br/>num_warmup_steps 10000
<br/>pretrain_tfrecords gs://XXX
<br/>results_pkl gs://XXX
<br/>results_txt gs://XXX
<br/>save_checkpoints_steps 5000
<br/>temperature 1.0
<br/>tpu_job_name None
<br/>tpu_name electrav5
<br/>tpu_zone None
<br/>train_batch_size 256
<br/>uniform_generator False
<br/>untied_generator True
<br/>untied_generator_embeddings False
<br/>use_tpu True
<br/>vocab_file gs://XXX
<br/>vocab_size 32767
<br/>weight_decay_rate 0.01
</details>
Please Note: *Due to the GAN like strucutre of Electra the loss is not that meaningful*
It took about 7 Days on a preemtible TPU V3-8. In total, the Model went through approximately 10 Epochs. For an automatically recreation of a cancelled TPUs we used [tpunicorn](https://github.com/shawwn/tpunicorn). The total cost of training summed up to about 450 $ for one run. The Data-pre processing and Vocab Creation needed approximately 500-1000 CPU hours. Servers were fully provided by [T-Systems on site services GmbH](https://www.t-systems-onsite.de/), [ambeRoad](https://amberoad.de/).
Special thanks to [Stefan Schweter](https://github.com/stefan-it) for your feedback and providing parts of the text corpus.
[¹]: Source for the picture [Pinterest](https://www.pinterest.cl/pin/371828512984142193/)
### Negative Results
We tried the following approaches which we found had no positive influence:
- **Increased Vocab Size**: Leads to more parameters and thus reduced examples/sec while no visible Performance gains were measured
- **Decreased Batch-Size**: The original Electra was trained with a Batch Size per TPU Core of 16 whereas this Model was trained with 32 BS / TPU Core. We found out that 32 BS leads to better results when you compare metrics over computation time
## License - The MIT License
Copyright 2020-2021 [Philip May](https://philipmay.org)\
Copyright 2020-2021 [Philipp Reißel](https://www.linkedin.com/in/philipp-reissel/)
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
dhmeltzer/llama-7b-SFT_ds_eli5_1024_r_64_alpha_16_merged | dhmeltzer | "2023-11-17T21:20:38Z" | 1,929 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-25T02:16:10Z" |
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dhmeltzer__llama-7b-SFT_ds_eli5_1024_r_64_alpha_16_merged)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 43.25 |
| ARC (25-shot) | 53.41 |
| HellaSwag (10-shot) | 77.9 |
| MMLU (5-shot) | 43.56 |
| TruthfulQA (0-shot) | 40.81 |
| Winogrande (5-shot) | 74.59 |
| GSM8K (5-shot) | 5.08 |
| DROP (3-shot) | 7.37 |
|
google/metricx-23-qe-xl-v2p0 | google | "2024-02-07T21:16:44Z" | 1,929 | 2 | transformers | [
"transformers",
"pytorch",
"mt5",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-02-07T16:35:10Z" | ---
license: apache-2.0
---
# MetricX-23
*This is not an officially supported Google product.*
**GitHub repository: [https://github.com/google-research/metricx](https://github.com/google-research/metricx)**
This repository contains the MetricX-23 models,
a family of models for automatic evaluation of translations that were proposed
in the WMT'23 Metrics Shared Task submission
[MetricX-23: The Google Submission to the WMT 2023 Metrics Shared Task](https://aclanthology.org/2023.wmt-1.63/).
The models were trained in [T5X](https://github.com/google-research/t5x) and
then converted for use in PyTorch.
## Available Models
There are 6 models available on HuggingFace that vary in the number of
parameters and whether or not the model is reference-based or reference-free
(also known as quality estimation, or QE):
* [MetricX-23-XXL](https://huggingface.co/google/metricx-23-large-v2p0)
* [MetricX-23-XL](https://huggingface.co/google/metricx-23-xl-v2p0)
* [MetricX-23-Large](https://huggingface.co/google/metricx-23-xxl-v2p0)
* [MetricX-23-QE-XXL](https://huggingface.co/google/metricx-23-qe-large-v2p0)
* [MetricX-23-QE-XL](https://huggingface.co/google/metricx-23-qe-xl-v2p0)
* [MetricX-23-QE-Large](https://huggingface.co/google/metricx-23-qe-xxl-v2p0)
We recommend using the XXL model versions for the best agreement with human
judgments of translation quality, the Large versions for best speed, and the
XL for an intermediate use case.
## Changes to the WMT'23 Submission
These models available here are most similar to the primary submission to the WMT'23 Metrics
Shared Task. They are initialized with [mT5](https://aclanthology.org/2021.naacl-main.41/)
then fine-tuned on a combination of direct assessment and MQM data. However,
we made some changes that make these models different from the WMT'23 submissions.
First, the models are trained to regress the actual MQM score rather than a
normalized score between 0 and 1. **That means the output from the MetricX-23
models is a score in the range [0, 25] where lower is better (i.e., it predicts
an error score).**
Second, these models were trained with a larger variety of synthetic data that
makes them more robust to translation edge cases like over- and undertranslation,
described in more detail in the following section.
### Synthetic Data
In order for our MetricX models to learn to identify certain types of bad
translations that are not sufficiently (or at all) represented in the regular
training data, we created synthetic examples and mixed them in during training.
The synthetic training data was generated from the DA datasets ranging from
WMT15 to WMT21 (~ 43 language pairs). In most cases, the synthetic examples have
the candidate translation manipulated so as to turn it into a bad translation
with a specific issue commonly unrecognized by learned metrics.
The table below provides an overview of the various failure modes that we
considered, including brief descriptions of how we prepared the synthetic data
to address them.
| Failure mode | Synthetic example description |
| ----------- | ----------- |
| Undertranslation | Candidate translation with an arbitrary sentence removed (if multi-sentence); alternatively, candidate with a certain proportion of words removed from the end. |
| Overtranslation | Candidate translation duplicated (with space in between). |
| Fluent but unrelated translation | Arbitrary reference of a similar length from the dataset. |
| Gibberish | Text of a similar length as the reference, generated by sampling words from the reference translation vocabulary (built from all references in the data). |
| Missing punctuation | Reference translation with the end punctuation removed (11 punctuation symbols considered). |
| Latin instead of Chinese/Japanese or Hindi/Bengali punctuation | Candidate translation with the language-specific punctuation symbol at the end replaced with the Latin equivalent (e.g., "." instead of "。" or "।"); alternatively, the punctuation symbol is replaced with the Latin equivalent in the reference, keeping the correct one in the candidate. |
| Reference-matching translation | Reference translation copied as the candidate translation (unlike the rest of the synthetic data, these examples are meant to train the metric to predict a perfect score for candidates matching the reference). |
Examples from the first 4 categories were assigned a label corresponding to the
worst score on the given rating scale (e.g., 25 when mixed with MQM training
data), whereas the reference-matching translation examples are assigned the best
score (e.g., 0 when used with MQM data). The missing/incorrect punctuation
examples were labeled with a score slightly worse than perfect.
Note that some of the synthetic datasets are only meaningful in the
reference-based scenario, and we thus excluded them when training a QE variant
of MetricX. These are the Latin-vs-special punctuation and the
reference-matching translation examples.
Most of the synthetic training sets were created using stratified sampling
across target languages, taking 500 examples per target language. One exception
is the missing punctuation set, which used a stratified sample across different
punctuation symbols instead.
When training MetricX, a small proportion of the synthetic examples was mixed
with the regular training examples. During the first-stage fine-tuning on DA
data, each synthetic training set constituted between 0.1% and 1% of all
training examples, whereas in the second-stage fine-tuning on MQM data we used
an even smaller proportion, around 0.05%.
As for evaluating the effect of the synthetic training data on the model's
performance, the DEMETR challenge set - which we originally used to evaluate the
models submitted to the WMT23 Metrics Shared Task - was not adequate anymore. We
therefore created a new DEMETR-style test set based on the WMT22 DA data, with
examples constructed analogically to the synthetic training examples, as
described above. This test set helped us determine the right proportions of
synthetic data for fine-tuning in order to make MetricX robust for the failure
modes in consideration, without sacrificing the system- and segment-level
correlations with human ratings.
## Usage
The code for using MetricX models can be found at [https://github.com/google-research/metricx](https://github.com/google-research/metricx).
The repository contains example prediction scripts, described below.
The `metricx23/predict.py` script contains an example for how to run inference
on the models.
### Reference-Based
Example usage for a reference-based model:
```bash
python -m metricx23.predict \
--tokenizer google/mt5-xl \
--model_name_or_path google/metricx-23-xl-v2p0 \
--max_input_length 1024 \
--batch_size 1 \
--input_file input.jsonl \
--output_file output.jsonl
```
`input.jsonl` is expected to have 1 serialized JSON object per line with
`"reference"` and `"hypothesis"` fields. The output jsonl will be parallel
to `input.jsonl` but additionally contain a `"prediction"` field with the predicted score.
Note that the model was trained with a maximum input length of 1024 tokens, so
significantly increasing that value may lead to unpredictable behavior.
### Reference-Free
Example usage for a reference-free model:
```bash
python -m metricx23.predict \
--tokenizer google/mt5-xl \
--model_name_or_path google/metricx-23-qe-xl-v2p0 \
--max_input_length 1024 \
--batch_size 1 \
--input_file input.jsonl \
--output_file output.jsonl \
--qe
```
`input.jsonl` is expected to have 1 serialized JSON object per line with
`"source"` and `"hypothesis"` fields. The output jsonl will be parallel
to `input.jsonl` but additionally contain a `"prediction"` field with the predicted score.
## Meta-Evaluation
The `metricx23/evaluate.py` script contains code to calculate various correlations
between the MetricX-23 scores and MQM ratings of translation quality using the
[MT Metrics Eval](https://github.com/google-research/mt-metrics-eval) library.
Example usage:
```bash
python -m metricx23.evaluate \
--dataset wmt22 \
--lp en-de \
--input_file input.jsonl \
--output_file output.json
```
`input.jsonl` is expected to have one JSON object serialized per line.
Each JSON object is expected to contain 4 fields:
* `"system_id"`: The name of the system that generated the translation.
* `"segment_id"`: The 0-based index of the corresponding segment in the MT
Metrics Eval data.
* `"label"`: The ground-truth translation quality score (with higher is better).
* `"prediction"`: The model predicted translation quality score (with lower is
better; the script negates the scores so higher is better).
The script will calculate the 4 agreement/correlations that were used in the
WMT'23 Shared Task. Below are the results for the MetricX-23 models on the
WMT'22 Metrics Shared Task data:
English-German:
| Model | System-Level Accuracy | System-Level Pearson | Segment-Level Pearson | Segment-Level Pairwise Acc |
| ----------- | ----------- | ----------- | ----------- | ----------- |
| MetricX-23-XXL | 0.795 | 0.835 | 0.546 | 0.619 |
| MetricX-23-XL | 0.756 | 0.813 | 0.540 | 0.605 |
| MetricX-23-Large | 0.769 | 0.759 | 0.507 | 0.595 |
| MetricX-23-QE-XXL | 0.769 | 0.830 | 0.490 | 0.606 |
| MetricX-23-QE-XL | 0.718 | 0.684 | 0.421 | 0.594 |
| MetricX-23-QE-Large | 0.744 | 0.671 | 0.387 | 0.579 |
English-Russian:
| Model | System-Level Accuracy | System-Level Pearson | Segment-Level Pearson | Segment-Level Pairwise Acc |
| ----------- | ----------- | ----------- | ----------- | ----------- |
| MetricX-23-XXL | 0.905 | 0.943 | 0.477 | 0.609 |
| MetricX-23-XL | 0.876 | 0.906 | 0.498 | 0.589 |
| MetricX-23-Large | 0.876 | 0.841 | 0.474 | 0.569 |
| MetricX-23-QE-XXL | 0.895 | 0.940 | 0.470 | 0.602 |
| MetricX-23-QE-XL | 0.848 | 0.861 | 0.415 | 0.570 |
| MetricX-23-QE-Large | 0.819 | 0.778 | 0.411 | 0.551 |
Chinese-English:
| Model | System-Level Accuracy | System-Level Pearson | Segment-Level Pearson | Segment-Level Pairwise Acc |
| ----------- | ----------- | ----------- | ----------- | ----------- |
| MetricX-23-XXL | 0.868 | 0.919 | 0.605 | 0.551 |
| MetricX-23-XL | 0.868 | 0.924 | 0.584 | 0.543 |
| MetricX-23-Large | 0.857 | 0.919 | 0.555 | 0.539 |
| MetricX-23-QE-XXL | 0.857 | 0.928 | 0.573 | 0.544 |
| MetricX-23-QE-XL | 0.802 | 0.879 | 0.546 | 0.529 |
| MetricX-23-QE-Large | 0.758 | 0.904 | 0.522 | 0.529 |
The `metricx23/evaluate_wmt23.py` script re-calculates the average correlation
score that was used to rank submissions from the
[WMT'23 Shared Task](https://www2.statmt.org/wmt23/pdf/2023.wmt-1.51.pdf).
Example usage:
```bash
python -m metricx23.evaluate_wmt23 \
--en_de predictions_ende.jsonl \
--he_en predictions_heen.jsonl \
--zh_en predictions_zhen.jsonl \
--output_file output.json
```
Each of the 3 input files is expected to be in the same format as described
above. Each file should correspond to running inference on each of the language
pairs from the WMT'23 dataset.
The results for each of the models is the following:
| Model | Average Correlation |
| ----------- | ----------- |
| MetricX-23-XXL | 0.812 |
| MetricX-23-XL | 0.813 |
| MetricX-23-Large | 0.794 |
| MetricX-23-QE-XXL | 0.797 |
| MetricX-23-QE-XL | 0.767 |
| MetricX-23-QE-Large | 0.762 |
## Citation
If you use MetricX-23 in your research, please cite the following publication:
```bibtex
@inproceedings{juraska-etal-2023-metricx,
title = {{MetricX-23: The Google Submission to the WMT 2023 Metrics Shared Task}},
author = "Juraska, Juraj and
Finkelstein, Mara and
Deutsch, Daniel and
Siddhant, Aditya and
Mirzazadeh, Mehdi and
Freitag, Markus",
editor = "Koehn, Philipp and
Haddow, Barry and
Kocmi, Tom and
Monz, Christof",
booktitle = "Proceedings of the Eighth Conference on Machine Translation",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wmt-1.63",
doi = "10.18653/v1/2023.wmt-1.63",
pages = "756--767",
}
``` |
TheBloke/VicUnlocked-30B-LoRA-HF | TheBloke | "2023-06-05T00:10:12Z" | 1,928 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:gozfarb/ShareGPT_Vicuna_unfiltered",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-17T11:07:20Z" | ---
datasets:
- gozfarb/ShareGPT_Vicuna_unfiltered
license: other
---
<!-- header start -->
<div style="width: 100%;">
<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><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# VicUnlocked-30B-LoRA GPTQ
This is an HF format float16 repo of [Neko Institute of Science's VicUnLocked 30B LoRA](https://huggingface.co/Neko-Institute-of-Science/VicUnLocked-30b-LoRA).
It is the result merging the above LoRA with the original LLaMA 30B.
## Repositories available
* [4-bit, 5-bit and 8-bit GGML models for CPU (+CUDA) inference](https://huggingface.co/TheBloke/VicUnlocked-30B-LoRA-GGML).
* [4-bit GPTQ model for GPU inference](https://huggingface.co/TheBloke/VicUnlocked-30B-LoRA-GPTQ).
* [float16 HF format model for GPU inference and further conversions](https://huggingface.co/TheBloke/VicUnlocked-30B-LoRA-HF).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
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
**Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card
# Convert tools
https://github.com/practicaldreamer/vicuna_to_alpaca
# Training tool
https://github.com/oobabooga/text-generation-webui
ATM I'm using 2023.05.04v0 of the dataset and training full context.
# Notes:
So I will only be training 1 epoch, as full context 30b takes so long to train.
This 1 epoch will take me 8 days lol but luckily these LoRA feels fully functinal at epoch 1 as shown on my 13b one.
Also I will be uploading checkpoints almost everyday. I could train another epoch if there's enough want for it.
Update: Since I will not be training over 1 epoch @Aeala is training for the full 3 https://huggingface.co/Aeala/VicUnlocked-alpaca-half-30b-LoRA but it's half ctx if you care about that. Also @Aeala's just about done.
Update: Training Finished at Epoch 1, These 8 days sure felt long. I only have one A6000 lads there's only so much I can do. Also RIP gozfarb IDK what happened to him.
# How to test?
1. Download LLaMA-30B-HF if you have not: https://huggingface.co/Neko-Institute-of-Science/LLaMA-30B-HF
2. Make a folder called VicUnLocked-30b-LoRA in the loras folder.
3. Download adapter_config.json and adapter_model.bin into VicUnLocked-30b-LoRA.
4. Load ooba: ```python server.py --listen --model LLaMA-30B-HF --load-in-8bit --chat --lora VicUnLocked-30b-LoRA```
5. Select instruct and chose Vicuna-v1.1 template.
# Training Log
https://wandb.ai/neko-science/VicUnLocked/runs/vx8yzwi7
|
ostris/crayon_style_lora_sdxl | ostris | "2023-08-15T01:44:12Z" | 1,928 | 27 | diffusers | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"sdxl",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:apache-2.0",
"region:us"
] | text-to-image | "2023-08-15T01:33:55Z" | ---
license: apache-2.0
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- sdxl
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: ''
widget:
- text: an ant holding up a sign that says crayons
---
# Crayon Style - SDXL LoRA
### Tips
- No trigger words needed.
- Converts any prompt into a crayon drawing
- Strength of 1.0 usually works but you may need to increase or decrease an needed.
### Samples
[<img src="https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02941-2777558690-a%20sexy%20woman%20in%20black%20lingerie%2C%20neon%20sign%20in%20the%20background%20that%20says%20crayons%20in%20big%20latters%20_lora_crayons_v1_sdxl_1_.jpeg" style="max-width:400px; height:auto" />](https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02941-2777558690-a%20sexy%20woman%20in%20black%20lingerie%2C%20neon%20sign%20in%20the%20background%20that%20says%20crayons%20in%20big%20latters%20_lora_crayons_v1_sdxl_1_.jpeg)
[<img src="https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02932-1397624082-an%20ant%20holding%20up%20a%20sign%20that%20says%20crayons%20%20_lora_crayons_v1_sdxl_1_.jpeg" style="max-width:400px; height:auto" />](https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02932-1397624082-an%20ant%20holding%20up%20a%20sign%20that%20says%20crayons%20%20_lora_crayons_v1_sdxl_1_.jpeg)
[<img src="https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02939-3715890861-a%20dog%20tripping%20balls%20on%20mushrooms%20%20%20_lora_crayons_v1_sdxl_1_.jpeg" style="max-width:400px; height:auto" />](https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02939-3715890861-a%20dog%20tripping%20balls%20on%20mushrooms%20%20%20_lora_crayons_v1_sdxl_1_.jpeg)
[<img src="https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02935-1397624082-a%20woman%20stripping%20at%20a%20strip%20club%20%20_lora_crayons_v1_sdxl_1_.jpeg" style="max-width:400px; height:auto" />](https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02935-1397624082-a%20woman%20stripping%20at%20a%20strip%20club%20%20_lora_crayons_v1_sdxl_1_.jpeg)
[<img src="https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02957-1144141521-back%20to%20the%20future%20scene%2C%20DeLorean%20flying%20in%20the%20future%2C%20%20%20%20%20_lora_crayons_v1_sdxl_1_.jpeg" style="max-width:400px; height:auto" />](https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02957-1144141521-back%20to%20the%20future%20scene%2C%20DeLorean%20flying%20in%20the%20future%2C%20%20%20%20%20_lora_crayons_v1_sdxl_1_.jpeg)
[<img src="https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02958-448093496-people%20sitting%20around%20a%20camp%20fire%2C%20roasting%20marshmallows%20%20%20%20_lora_crayons_v1_sdxl_1_.jpeg" style="max-width:400px; height:auto" />](https://huggingface.co/ostris/crayon_style_lora_sdxl/resolve/main/samples/02958-448093496-people%20sitting%20around%20a%20camp%20fire%2C%20roasting%20marshmallows%20%20%20%20_lora_crayons_v1_sdxl_1_.jpeg)
|
nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change | nm-testing | "2024-06-13T15:51:43Z" | 1,928 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2024-06-12T17:26:06Z" | Entry not found |
mradermacher/Aira-2-1B5-GGUF | mradermacher | "2024-06-18T18:58:34Z" | 1,928 | 0 | transformers | [
"transformers",
"gguf",
"alignment",
"instruction tuned",
"text generation",
"conversation",
"assistant",
"en",
"dataset:nicholasKluge/instruct-aira-dataset",
"base_model:nicholasKluge/Aira-2-1B5",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-18T18:34:20Z" | ---
base_model: nicholasKluge/Aira-2-1B5
datasets:
- nicholasKluge/instruct-aira-dataset
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- alignment
- instruction tuned
- text generation
- conversation
- assistant
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/nicholasKluge/Aira-2-1B5
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.IQ3_S.gguf) | IQ3_S | 1.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.IQ3_XS.gguf) | IQ3_XS | 1.0 | |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q2_K.gguf) | Q2_K | 1.0 | |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q3_K_S.gguf) | Q3_K_S | 1.0 | |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.IQ4_XS.gguf) | IQ4_XS | 1.1 | |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.IQ3_M.gguf) | IQ3_M | 1.1 | |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q3_K_L.gguf) | Q3_K_L | 1.2 | |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q5_K_S.gguf) | Q5_K_S | 1.3 | |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q5_K_M.gguf) | Q5_K_M | 1.5 | |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q6_K.gguf) | Q6_K | 1.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.Q8_0.gguf) | Q8_0 | 1.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Aira-2-1B5-GGUF/resolve/main/Aira-2-1B5.f16.gguf) | f16 | 3.4 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
toilaluan/pixart-sora-t2i | toilaluan | "2024-06-24T03:59:12Z" | 1,928 | 0 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"full",
"base_model:toilaluan/SoraT2I",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | "2024-06-23T20:56:44Z" | ---
license: creativeml-openrail-m
base_model: "toilaluan/SoraT2I"
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- full
inference: true
widget:
- text: 'unconditional (blank prompt)'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_0_0.png
- text: 'a woman sitting on the grass'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_1_0.png
- text: 'a professional photo headshot of a man in studio lighting'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_2_0.png
- text: 'a person holding a sign that reads ''SOON'''
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_3_0.png
- text: 'Alien marketplace, bizarre creatures, exotic goods, vibrant colors, otherworldly atmosphere'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_4_0.png
- text: 'Child holding a balloon, happy expression, colorful balloons, sunny day, high detail'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_5_0.png
- text: 'a 4-panel comic strip showing an orange cat saying the words ''HELP'' and ''LASAGNA'''
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_6_0.png
- text: 'a hand is holding a comic book with a cover that reads ''The Adventures of Superhero'''
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_7_0.png
- text: 'Underground cave filled with crystals, glowing lights, reflective surfaces, fantasy environment, high detail'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_8_0.png
- text: 'Bustling cyberpunk bazaar, vendors, neon signs, advanced tech, crowded, high detail'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_9_0.png
- text: 'Cyberpunk hacker in a dark room, neon glow, multiple screens, intense focus, high detail'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_10_0.png
- text: 'a cybernetic anne of green gables with neural implant and bio mech augmentations'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_11_0.png
- text: 'Post-apocalyptic cityscape, ruined buildings, overgrown vegetation, dark and gritty, high detail'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_12_0.png
- text: 'Magical castle in a lush forest, glowing windows, fantasy architecture, high resolution, detailed textures'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_13_0.png
- text: 'Ruins of an ancient temple in an enchanted forest, glowing runes, mystical creatures, high detail'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_14_0.png
- text: 'Mystical forest, glowing plants, fairies, magical creatures, fantasy art, high detail'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_15_0.png
- text: 'Magical garden with glowing flowers, fairies, serene atmosphere, detailed plants, high resolution'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_16_0.png
- text: 'Whimsical garden filled with fairies, magical plants, sparkling lights, serene atmosphere, high detail'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_17_0.png
- text: 'Majestic dragon soaring through the sky, detailed scales, dynamic pose, fantasy art, high resolution'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_18_0.png
- text: 'Fantasy world, floating islands in the sky, waterfalls, lush vegetation, detailed landscape, high resolution'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_19_0.png
- text: 'Futuristic city skyline at night, neon lights, cyberpunk style, high contrast, sharp focus'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_20_0.png
- text: 'Space battle scene, starships fighting, laser beams, explosions, cosmic background'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_21_0.png
- text: 'Abandoned fairground at night, eerie rides, ghostly figures, fog, dark atmosphere, high detail'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_22_0.png
- text: 'Spooky haunted mansion on a hill, dark and eerie, glowing windows, ghostly atmosphere, high detail'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_23_0.png
- text: 'a hardcover physics textbook that is called PHYSICS FOR DUMMIES'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_24_0.png
- text: 'Epic medieval battle, knights in armor, dynamic action, detailed landscape, high resolution'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_25_0.png
- text: 'Bustling medieval market with merchants, knights, and jesters, vibrant colors, detailed'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_26_0.png
- text: 'Cozy medieval tavern, warm firelight, adventurers drinking, detailed interior, rustic atmosphere'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_27_0.png
- text: 'Futuristic city skyline at night, neon lights, cyberpunk style, high contrast, sharp focus'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_28_0.png
- text: 'Forest with neon-lit trees, glowing plants, bioluminescence, surreal atmosphere, high detail'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_29_0.png
- text: 'Bright neon sign in a busy city street, ''Open 24 Hours'', bold typography, glowing lights'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_30_0.png
- text: 'Retro diner sign, ''Joe''s Diner'', classic 1950s design, neon lights, weathered look'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_31_0.png
- text: 'Vintage store sign with elaborate typography, ''Antique Shop'', hand-painted, weathered look'
parameters:
negative_prompt: 'blurry, cropped, ugly'
output:
url: ./assets/image_32_0.png
---
# pixart-sora-t2i
This is a full rank finetune derived from [toilaluan/SoraT2I](https://huggingface.co/toilaluan/SoraT2I).
No validation prompt was used during training.
None
## Validation settings
- CFG: `7.5`
- CFG Rescale: `0.0`
- Steps: `30`
- Sampler: `euler`
- Seed: `42`
- Resolution: `1024`
Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
You can find some example images in the following gallery:
<Gallery />
The text encoder **was not** trained.
You may reuse the base model text encoder for inference.
## Training settings
- Training epochs: 0
- Training steps: 1000
- Learning rate: 8e-06
- Effective batch size: 128
- Micro-batch size: 32
- Gradient accumulation steps: 4
- Number of GPUs: 1
- Prediction type: epsilon
- Rescaled betas zero SNR: False
- Optimizer: AdamW, stochastic bf16
- Precision: Pure BF16
- Xformers: Enabled
## Datasets
### mj-v6
- Repeats: 0
- Total number of images: 134144
- Total number of aspect buckets: 1
- Resolution: 1.0 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
## Inference
```python
import torch
from diffusers import DiffusionPipeline
model_id = "pixart-sora-t2i"
prompt = "An astronaut is riding a horse through the jungles of Thailand."
negative_prompt = "malformed, disgusting, overexposed, washed-out"
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
prompt=prompt,
negative_prompt='blurry, cropped, ugly',
num_inference_steps=30,
generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
width=1152,
height=768,
guidance_scale=7.5,
guidance_rescale=0.0,
).images[0]
image.save("output.png", format="PNG")
```
|
Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition | Aniemore | "2023-02-14T16:22:15Z" | 1,927 | 12 | transformers | [
"transformers",
"pytorch",
"wav2vec2",
"feature-extraction",
"audio-classification",
"audio",
"emotion",
"emotion-recognition",
"emotion-classification",
"speech",
"custom_code",
"ru",
"dataset:Aniemore/resd",
"license:mit",
"model-index",
"region:us"
] | audio-classification | "2022-05-22T20:10:59Z" | ---
language: ru
tags:
- audio-classification
- audio
- emotion
- emotion-recognition
- emotion-classification
- speech
license: mit
datasets:
- Aniemore/resd
model-index:
- name: XLS-R Wav2Vec2 For Russian Speech Emotion Classification by Nikita Davidchuk
results:
- task:
name: Audio Emotion Recognition
type: audio-emotion-recognition
dataset:
name: Russian Emotional Speech Dialogs
type: Aniemore/resd
args: ru
metrics:
- name: accuracy
type: accuracy
value: 72%
---
# Prepare and importing
```python
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchaudio
from transformers import AutoConfig, AutoModel, Wav2Vec2FeatureExtractor
import librosa
import numpy as np
def speech_file_to_array_fn(path, sampling_rate):
speech_array, _sampling_rate = torchaudio.load(path)
resampler = torchaudio.transforms.Resample(_sampling_rate)
speech = resampler(speech_array).squeeze().numpy()
return speech
def predict(path, sampling_rate):
speech = speech_file_to_array_fn(path, sampling_rate)
inputs = feature_extractor(speech, sampling_rate=sampling_rate, return_tensors="pt", padding=True)
inputs = {key: inputs[key].to(device) for key in inputs}
with torch.no_grad():
logits = model_(**inputs).logits
scores = F.softmax(logits, dim=1).detach().cpu().numpy()[0]
outputs = [{"Emotion": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)]
return outputs
```
# Evoking:
```python
TRUST = True
config = AutoConfig.from_pretrained('Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition', trust_remote_code=TRUST)
model_ = AutoModel.from_pretrained("Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition", trust_remote_code=TRUST)
feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("Aniemore/wav2vec2-xlsr-53-russian-emotion-recognition")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model_.to(device)
```
# Use case
```python
result = predict("/path/to/russian_audio_speech.wav", 16000)
print(result)
```
```python
# outputs
[{'Emotion': 'anger', 'Score': '0.0%'},
{'Emotion': 'disgust', 'Score': '100.0%'},
{'Emotion': 'enthusiasm', 'Score': '0.0%'},
{'Emotion': 'fear', 'Score': '0.0%'},
{'Emotion': 'happiness', 'Score': '0.0%'},
{'Emotion': 'neutral', 'Score': '0.0%'},
{'Emotion': 'sadness', 'Score': '0.0%'}]
```
# Results
| | precision | recall | f1-score | support |
|--------------|-----------|--------|----------|---------|
| anger | 0.97 | 0.86 | 0.92 | 44 |
| disgust | 0.71 | 0.78 | 0.74 | 37 |
| enthusiasm | 0.51 | 0.80 | 0.62 | 40 |
| fear | 0.80 | 0.62 | 0.70 | 45 |
| happiness | 0.66 | 0.70 | 0.68 | 44 |
| neutral | 0.81 | 0.66 | 0.72 | 38 |
| sadness | 0.79 | 0.59 | 0.68 | 32 |
| accuracy | | | 0.72 | 280 |
| macro avg | 0.75 | 0.72 | 0.72 | 280 |
| weighted avg | 0.75 | 0.72 | 0.73 | 280 |
# Citations
```
@misc{Aniemore,
author = {Артем Аментес, Илья Лубенец, Никита Давидчук},
title = {Открытая библиотека искусственного интеллекта для анализа и выявления эмоциональных оттенков речи человека},
year = {2022},
publisher = {Hugging Face},
journal = {Hugging Face Hub},
howpublished = {\url{https://huggingface.com/aniemore/Aniemore}},
email = {[email protected]}
}
``` |
stabilityai/StableBeluga2 | stabilityai | "2023-09-18T15:55:32Z" | 1,927 | 884 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"dataset:conceptofmind/cot_submix_original",
"dataset:conceptofmind/flan2021_submix_original",
"dataset:conceptofmind/t0_submix_original",
"dataset:conceptofmind/niv2_submix_original",
"arxiv:2307.09288",
"arxiv:2306.02707",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-07-20T15:09:28Z" | ---
datasets:
- conceptofmind/cot_submix_original
- conceptofmind/flan2021_submix_original
- conceptofmind/t0_submix_original
- conceptofmind/niv2_submix_original
language:
- en
pipeline_tag: text-generation
---
# Stable Beluga 2
Use [Stable Chat (Research Preview)](https://chat.stability.ai/chat) to test Stability AI's best language models for free
## Model Description
`Stable Beluga 2` is a Llama2 70B model finetuned on an Orca style Dataset
## Usage
Start chatting with `Stable Beluga 2` using the following code snippet:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained("stabilityai/StableBeluga2", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("stabilityai/StableBeluga2", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
system_prompt = "### System:\nYou are Stable Beluga, an AI that follows instructions extremely well. Help as much as you can. Remember, be safe, and don't do anything illegal.\n\n"
message = "Write me a poem please"
prompt = f"{system_prompt}### User: {message}\n\n### Assistant:\n"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=256)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
Stable Beluga 2 should be used with this prompt format:
```
### System:
This is a system prompt, please behave and help the user.
### User:
Your prompt here
### Assistant:
The output of Stable Beluga 2
```
## Other Beluga Models
[StableBeluga 1 - Delta](https://huggingface.co/stabilityai/StableBeluga1-Delta)
[StableBeluga 13B](https://huggingface.co/stabilityai/StableBeluga-13B)
[StableBeluga 7B](https://huggingface.co/stabilityai/StableBeluga-7B)
## Model Details
* **Developed by**: [Stability AI](https://stability.ai/)
* **Model type**: Stable Beluga 2 is an auto-regressive language model fine-tuned on Llama2 70B.
* **Language(s)**: English
* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
* **License**: Fine-tuned checkpoints (`Stable Beluga 2`) is licensed under the [STABLE BELUGA NON-COMMERCIAL COMMUNITY LICENSE AGREEMENT](https://huggingface.co/stabilityai/StableBeluga2/blob/main/LICENSE.txt)
* **Contact**: For questions and comments about the model, please email `[email protected]`
### Training Dataset
` Stable Beluga 2` is trained on our internal Orca-style dataset
### Training Procedure
Models are learned via supervised fine-tuning on the aforementioned datasets, trained in mixed-precision (BF16), and optimized with AdamW. We outline the following hyperparameters:
| Dataset | Batch Size | Learning Rate |Learning Rate Decay| Warm-up | Weight Decay | Betas |
|-------------------|------------|---------------|-------------------|---------|--------------|-------------|
| Orca pt1 packed | 256 | 3e-5 | Cosine to 3e-6 | 100 | 1e-6 | (0.9, 0.95) |
| Orca pt2 unpacked | 512 | 3e-5 | Cosine to 3e-6 | 100 | 1e-6 | (0.9, 0.95) |
## Ethical Considerations and Limitations
Beluga is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Beluga's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Beluga, developers should perform safety testing and tuning tailored to their specific applications of the model.
## How to cite
```bibtex
@misc{StableBelugaModels,
url={[https://huggingface.co/stabilityai/StableBeluga2](https://huggingface.co/stabilityai/StableBeluga2)},
title={Stable Beluga models},
author={Mahan, Dakota and Carlow, Ryan and Castricato, Louis and Cooper, Nathan and Laforte, Christian}
}
```
## Citations
```bibtext
@misc{touvron2023llama,
title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom},
year={2023},
eprint={2307.09288},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
```bibtext
@misc{mukherjee2023orca,
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
year={2023},
eprint={2306.02707},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
simsim314/WizardLM-70B-V1.0-HF | simsim314 | "2023-08-12T01:11:14Z" | 1,927 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:llama2",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-08-11T22:10:14Z" | ---
license: llama2
---
Float16 of [WizardLM/WizardLM-70B-V1.0](https://huggingface.co/WizardLM/WizardLM-70B-V1.0)
```
from transformers import LlamaTokenizer, AutoModelForCausalLM
tokenizer = LlamaTokenizer.from_pretrained("simsim314/WizardLM-70B-V1.0-HF")
model = AutoModelForCausalLM.from_pretrained("simsim314/WizardLM-70B-V1.0-HF")
``` |
NousResearch/Nous-Hermes-2-Yi-34B-GGUF | NousResearch | "2024-02-20T09:17:11Z" | 1,927 | 41 | null | [
"gguf",
"yi",
"instruct",
"finetune",
"chatml",
"gpt4",
"synthetic data",
"distillation",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:01-ai/Yi-34B",
"license:apache-2.0",
"region:us"
] | null | "2023-12-26T16:42:36Z" | ---
base_model: 01-ai/Yi-34B
tags:
- yi
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- distillation
model-index:
- name: Nous-Hermes-2-Yi-34B
results: []
license: apache-2.0
language:
- en
datasets:
- teknium/OpenHermes-2.5
---
# Nous Hermes 2 - Yi-34B - GGUF Quantized Version
## Model description
Nous Hermes 2 - Yi-34B is a state of the art Yi Fine-tune. This is the GGUF quantized models page. See original page here: https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B
Nous Hermes 2 Yi 34B was trained on 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from open datasets across the AI landscape.
# Table of Contents
1. [Example Outputs](#example-outputs)
- Discussing the Laws of Gravity
- Create a Flask based FTP Server
3. [Benchmark Results](#benchmark-results)
- GPT4All
- AGIEval
- BigBench
- Averages Compared
4. [Prompt Format](#prompt-format)
5. [Quantized Models](#quantized-models)
## Example Outputs
### Discussions about the Law of Gravity:
### Create an FTP Server in FLASK:
## Benchmark Results
Nous-Hermes 2 on Yi 34B outperforms all Nous-Hermes & Open-Hermes models of the past, achieving new heights in all benchmarks for a Nous Research LLM as well as surpassing many popular finetunes.
# Benchmarks Compared
### GPT4All:
### AGIEval:
### BigBench:
### TruthfulQA:
## GPT4All
GPT-4All Benchmark Set
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.6067|_ |0.0143|
| | |acc_norm|0.6416|_ |0.0140|
|arc_easy | 0|acc |0.8594|_ |0.0071|
| | |acc_norm|0.8569|_ |0.0072|
|boolq | 1|acc |0.8859|_ |0.0056|
|hellaswag | 0|acc |0.6407|_ |0.0048|
| | |acc_norm|0.8388|_ |0.0037|
|openbookqa | 0|acc |0.3520|_ |0.0214|
| | |acc_norm|0.4760|_ |0.0224|
|piqa | 0|acc |0.8215|_ |0.0089|
| | |acc_norm|0.8303|_ |0.0088|
|winogrande | 0|acc |0.7908|_ |0.0114|
Average: 76.00%
```
AGI-Eval
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.3189|_ |0.0293|
| | |acc_norm|0.2953|_ |0.0287|
|agieval_logiqa_en | 0|acc |0.5438|_ |0.0195|
| | |acc_norm|0.4977|_ |0.0196|
|agieval_lsat_ar | 0|acc |0.2696|_ |0.0293|
| | |acc_norm|0.2087|_ |0.0269|
|agieval_lsat_lr | 0|acc |0.7078|_ |0.0202|
| | |acc_norm|0.6255|_ |0.0215|
|agieval_lsat_rc | 0|acc |0.7807|_ |0.0253|
| | |acc_norm|0.7063|_ |0.0278|
|agieval_sat_en | 0|acc |0.8689|_ |0.0236|
| | |acc_norm|0.8447|_ |0.0253|
|agieval_sat_en_without_passage| 0|acc |0.5194|_ |0.0349|
| | |acc_norm|0.4612|_ |0.0348|
|agieval_sat_math | 0|acc |0.4409|_ |0.0336|
| | |acc_norm|0.3818|_ |0.0328|
Average: 50.27%
```
BigBench Reasoning Test
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.5737|_ |0.0360|
|bigbench_date_understanding | 0|multiple_choice_grade|0.7263|_ |0.0232|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3953|_ |0.0305|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.4457|_ |0.0263|
| | |exact_str_match |0.0000|_ |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.2820|_ |0.0201|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2186|_ |0.0156|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.4733|_ |0.0289|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.5200|_ |0.0224|
|bigbench_navigate | 0|multiple_choice_grade|0.4910|_ |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.7495|_ |0.0097|
|bigbench_ruin_names | 0|multiple_choice_grade|0.5938|_ |0.0232|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.3808|_ |0.0154|
|bigbench_snarks | 0|multiple_choice_grade|0.8066|_ |0.0294|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.5101|_ |0.0159|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.3850|_ |0.0154|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2160|_ |0.0116|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1634|_ |0.0088|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.4733|_ |0.0289|
Average: 46.69%
```
TruthfulQA:
```
| Task |Version|Metric|Value | |Stderr|
|-------------|------:|------|-----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.4333|_ |0.0173|
| | |mc2 |0.6034|_ |0.0149|
```
Average Score Comparison between OpenHermes-1 Llama-2 13B and OpenHermes-2 Mistral 7B against OpenHermes-2.5 on Mistral-7B:
```
| Bench | OpenHermes-2.5 Mistral 7B | Nous-Hermes-2-Yi-34B | Change/OpenHermes2 |
|---------------|---------------------------|----------------------|--------------------|
|GPT4All | 73.12| 76.00| +2.88|
|---------------------------------------------------------------------------------------|
|BigBench | 40.96| 46.69| +5.73|
|---------------------------------------------------------------------------------------|
|AGI Eval | 43.07| 50.27| +7.20|
|---------------------------------------------------------------------------------------|
|TruthfulQA | 53.04| 60.34| +7.30|
|---------------------------------------------------------------------------------------|
|Total Score | 210.19| 233.30| +23.11|
|---------------------------------------------------------------------------------------|
|Average Total | 52.38| 58.33| +5.95|
```
# Prompt Format
Nous Hermes 2 uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
When quantized versions of the model are released, I recommend using LM Studio for chatting with Nous Hermes 2. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
# Quantized Models:
[todo]
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
rafaeloc15/llama_question_gguf | rafaeloc15 | "2024-06-21T20:16:26Z" | 1,927 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-21T19:23:25Z" | ---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
base_model: unsloth/llama-3-8b-bnb-4bit
---
# Uploaded model
- **Developed by:** rafaeloc15
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
santos-marco/Llama3_8b_com_Unsloth_8bit_Q8_0_GGUF_Canarim_QeA_MMGD_OriginaisSite_ORPO | santos-marco | "2024-06-26T17:31:13Z" | 1,927 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/llama-3-8b-Instruct-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-26T17:24:32Z" | ---
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
---
# Uploaded model
- **Developed by:** santos-marco
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf | RichardErkhov | "2024-06-30T04:30:59Z" | 1,927 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-30T04:21:37Z" | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Qwama-0.5B-Instruct - GGUF
- Model creator: https://huggingface.co/turboderp/
- Original model: https://huggingface.co/turboderp/Qwama-0.5B-Instruct/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Qwama-0.5B-Instruct.Q2_K.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q2_K.gguf) | Q2_K | 0.3GB |
| [Qwama-0.5B-Instruct.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.IQ3_XS.gguf) | IQ3_XS | 0.3GB |
| [Qwama-0.5B-Instruct.IQ3_S.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.IQ3_S.gguf) | IQ3_S | 0.3GB |
| [Qwama-0.5B-Instruct.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.3GB |
| [Qwama-0.5B-Instruct.IQ3_M.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.IQ3_M.gguf) | IQ3_M | 0.3GB |
| [Qwama-0.5B-Instruct.Q3_K.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q3_K.gguf) | Q3_K | 0.31GB |
| [Qwama-0.5B-Instruct.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.31GB |
| [Qwama-0.5B-Instruct.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.32GB |
| [Qwama-0.5B-Instruct.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.31GB |
| [Qwama-0.5B-Instruct.Q4_0.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q4_0.gguf) | Q4_0 | 0.31GB |
| [Qwama-0.5B-Instruct.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.IQ4_NL.gguf) | IQ4_NL | 0.31GB |
| [Qwama-0.5B-Instruct.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.34GB |
| [Qwama-0.5B-Instruct.Q4_K.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q4_K.gguf) | Q4_K | 0.35GB |
| [Qwama-0.5B-Instruct.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.35GB |
| [Qwama-0.5B-Instruct.Q4_1.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q4_1.gguf) | Q4_1 | 0.33GB |
| [Qwama-0.5B-Instruct.Q5_0.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q5_0.gguf) | Q5_0 | 0.35GB |
| [Qwama-0.5B-Instruct.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q5_K_S.gguf) | Q5_K_S | 0.37GB |
| [Qwama-0.5B-Instruct.Q5_K.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q5_K.gguf) | Q5_K | 0.37GB |
| [Qwama-0.5B-Instruct.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q5_K_M.gguf) | Q5_K_M | 0.37GB |
| [Qwama-0.5B-Instruct.Q5_1.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q5_1.gguf) | Q5_1 | 0.37GB |
| [Qwama-0.5B-Instruct.Q6_K.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q6_K.gguf) | Q6_K | 0.45GB |
| [Qwama-0.5B-Instruct.Q8_0.gguf](https://huggingface.co/RichardErkhov/turboderp_-_Qwama-0.5B-Instruct-gguf/blob/main/Qwama-0.5B-Instruct.Q8_0.gguf) | Q8_0 | 0.48GB |
Original model description:
---
license: apache-2.0
---
# Qwama-0.5B-Instruct
This is [Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) with a Llama-3 vocabulary.
The intended use is as a draft model for Llama-3-70B-Instruct. Llama3-8B-Instruct works for this purpose, but it's on
the heavier side for drafting.
The secondary purpose is to explore the feasibility of vocabulary swaps, either for adapting small models like
Qwen2-0.5b to produce drafts for other models, or for interoperability between dissimilar language models in general.
The conclusion in this regard is that the method works, but, since finetuning is required, it will be expensive for
larger models. It would be interesting to explore low-rank or quantized finetuning as an alternative.
## Procedure
The vocabulary was swapped by creating a new embedding layer (original model uses tied embeddings so the output layer is
the same) and initializing it as follows:
- every L3 token that is an exact match for a Qwen2 token is initialized with the corresponding embedding
- every L3 token that decodes and re-encodes to multiple Qwen2 token is initialized with the mean of those embeddings
- there are no L3 tokens that cannot be translated to one or more Qwen2 tokens (both vocabularies are complete).
```python
for idx in range(target_vocab_size):
decode = tokenizer_target.decode(torch.tensor(idx, dtype = torch.long), decode_special_tokens = True)
encode = tokenizer_source.encode(decode, add_special_tokens = False, return_tensors = "pt")
new_emb[idx] = old_emb[encode.flatten()].mean(dim = 0)
new_head[idx] = old_head[encode.flatten()].mean(dim = 0)
```
Full script is [here](https://huggingface.co/turboderp/Qwama-0.5B-Instruct/blob/main/vocab_transplant.py).
Swapping the vocabulary with the above method yields a mostly coherent but still very confused model. It especially
struggles with numbers, and of course the embeddings for the Llama-3 control tokens do not have the significance they
would in an instruct-tuned model.
This is remedied by subsequent finetuning, first on
[this 2.41 million row sample from Common Crawl](https://huggingface.co/datasets/agentlans/common-crawl-sample), and
subsequently 3 epochs on about 25000 instruct-formatted completions produced by Llama3-8B-Instruct, included
[here](https://huggingface.co/turboderp/Qwama-0.5B-Instruct/blob/main/llama3-instruct-prompts.json) for reference.
I did try tuning just the tied embeddings, but this didn't achieve good results.
## Benchmarks
Model | Wikitext 2k | MMLU
---------------------------|-------------|--------
Qwen2-0.5B-instruct @ FP16 | 12.5734 | 43.83%
Qwama-0.5B-instruct @ FP16 | 15.3390 | 40.37%
Draft model speculative decoding, greedy:
Model | Draft model | Code | Prose
-----------------------------|------------------------------|-------|-------
Qwen2-72B-instruct @ 6.0bpw | Qwen2-0.5B-instruct @ 4.0bpw | 3.68x | 1.70x
Llama3-70B-instruct @ 6.0bpw | Qwama-0.5B-instruct @ 4.0bpw | 3.72x | 1.92x
## Sample generations
Qwen2-0.5B-instruct:
`Hello, my name is Harry Potter. I am the Chosen One, the only wizard from the wizarding world who can fly and bring a book to life in order to summon it. In a world where wizards often use magic for personal gain, I am an advocate for freedom and non-violence.`
`Once upon a time, there was a princess named Elsa. She lived in a beautiful castle in the snowy mountains. Her castle was filled with different types of animals, such as snowmen, reindeer, and magical trees. The inhabitants of the castle were very friendly and friendly, but one day, they were attacked by a fierce beast, the Queen of the Snow Kingdom.`
`I am an AI language model. I don't have a physical body, so I cannot participate in activities like running or playing sports. However, I can simulate the movement of an AI language model. Is there anything specific you would like me to help with?`
Qwama-0.5B-instruct:
`Hello, my name is Jeffrey Brewer and I am a licensed attorney in both Maryland and Florida. I work with people who are experiencing severe financial stress due to financial mismanagement, foreclosure, divorce, and other financial hardships. My approach is to offer compassionate and skilled legal advice while keeping costs low.`
`Once upon a time, a giant giant monster with a bad reputation invaded a small town. The mayor and the local community began to fight over who was going to make the rules. But who will win if the monsters were being allowed to roam the town?`
`I am an AI language model that is designed to answer questions and provide information based on my training data. Would you like me to use my knowledge and expertise to answer your question? I am ready to assist you with any questions you may have. I will be happy to answer your questions in a timely manner.`
## EXL2 Quants
EXL2 quants uploaded [here](https://huggingface.co/turboderp/Qwama-0.5B-Instruct-exl2).
|
Aeala/Alpaca-elina-65b | Aeala | "2023-05-15T10:19:18Z" | 1,926 | 3 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-05-11T18:36:17Z" | ## Model Info
Merge of ChanSung's [Alpaca-LoRA-65B-elina](https://huggingface.co/LLMs/Alpaca-LoRA-65B-elina)
## Benchmarks
Coming soon... for now, it was submitted to the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) |
luffycodes/mcq-hal-vicuna-13b-v1.5 | luffycodes | "2023-09-02T15:48:13Z" | 1,926 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-09-02T15:37:38Z" | Entry not found |
RichardErkhov/Edgerunners_-_yi-9b-may-ortho-baukit-13fail-3000total-bf16-gguf | RichardErkhov | "2024-06-17T09:03:29Z" | 1,926 | 0 | null | [
"gguf",
"region:us"
] | null | "2024-06-17T08:24:05Z" | Entry not found |
majoh837/viz_V1_q4_k0 | majoh837 | "2024-06-20T11:08:49Z" | 1,926 | 0 | transformers | [
"transformers",
"gguf",
"mistral",
"text-generation-inference",
"unsloth",
"en",
"base_model:openchat/openchat-3.5-0106",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | "2024-06-20T11:02:48Z" | ---
base_model: openchat/openchat-3.5-0106
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- gguf
---
# Uploaded model
- **Developed by:** majoh837
- **License:** apache-2.0
- **Finetuned from model :** openchat/openchat-3.5-0106
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
nuigurumi/basil_mix | nuigurumi | "2023-05-16T09:42:46Z" | 1,925 | 975 | diffusers | [
"diffusers",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-01-04T07:45:22Z" | ---
license: other
---
## Model Description
- merged model.
- realistic texture and Asian face.
- designed to maintain a responsive reaction to danbooru based prompts.
## License
- This model and its derivatives(image, merged model) can be freely used for non-profit purposes only.
- You may not use this model and its derivatives on websites, apps, or other platforms where you can or plan to earn income or donations. If you wish to use it for such purposes, please contact nuigurumi.
- Introducing the model itself is allowed for both commercial and non-commercial purposes, but please include the model name and a link to this repository when doing so.
- このモデル及びその派生物(生成物、マージモデル)は、完全に非営利目的の使用に限り、自由に利用することができます。
- あなたが収入や寄付を得ることのできる、もしくは得る予定のWebサイト、アプリ、その他でこのモデル及びその派生物を利用することはできません。利用したい場合は[nuigurumi](https://twitter.com/nuigurumi1_KR)に連絡してください。
- モデル自体の紹介することは、営利非営利を問わず自由です、その場合はモデル名と当リポジトリのリンクを併記してください。
- check [License](https://huggingface.co/nuigurumi/basil_mix/blob/main/License.md)
_読むのめんどくさい人向け
商用利用をすべて禁止します。fanboxやpatreonなどの支援サイトでの使用も全て禁止します。
マージモデル(cilled_re...とか)も派生物なので商用利用禁止になります。 商用利用をしたいなら私に連絡してください。
どこかでモデルを紹介していただけるなら、リンクも併記してくれると嬉しいです。_
# Gradio
We support a [Gradio](https://github.com/gradio-app/gradio) Web UI to run basil_mix:
[](https://huggingface.co/spaces/akhaliq/basil_mix)
## Recommendations
- VAE: [vae-ft-mse-840000](https://huggingface.co/stabilityai/sd-vae-ft-mse-original) from StabilityAI
- Prompting: Simple prompts are better. Large amounts of quality tags and negative prompts can have negative effects. |
trl-internal-testing/tiny-random-GPT2Model | trl-internal-testing | "2024-04-10T12:28:56Z" | 1,925 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt2",
"feature-extraction",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | feature-extraction | "2023-01-20T15:02:42Z" | Entry not found |
Onodofthenorth/SD_PixelArt_SpriteSheet_Generator | Onodofthenorth | "2023-05-05T18:30:10Z" | 1,924 | 405 | diffusers | [
"diffusers",
"spritesheet",
"text-to-image",
"en",
"license:apache-2.0",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2022-11-01T04:31:21Z" | ---
license: apache-2.0
language:
- en
pipeline_tag: text-to-image
tags:
- spritesheet
- text-to-image
---
This Stable diffusion checkpoint allows you to generate pixel art sprite sheets from four different angles.
These first images are my results after merging this model with another model trained on my wife. merging another model with this one is the easiest way to get a consistent character with each view. still requires a bit of playing around with settings in img2img to get them how you want. for left and right, I suggest picking your best result and mirroring. after you are satisfied take your photo into photoshop or Krita, remove the background, and scale to the desired size. after this you can scale back up to display your results; this also clears up some of the color murkiness in the initial outputs.
### 🧨 Diffusers
This model can be used just like any other Stable Diffusion model. For more information,
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().
```python
#!pip install diffusers transformers scipy torch
from diffusers import StableDiffusionPipeline
import torch
model_id = "Onodofthenorth/SD_PixelArt_SpriteSheet_Generator"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "PixelartLSS"
image = pipe(prompt).images[0]
image.save("./pixel.png")
```
___
___
For the front view use "PixelartFSS"
___
___
For the right view use "PixelartRSS"
___
___
For the back view use "PixelartBSS"
___
___
For the left view use "PixelartLSS"
___
___
These are random results from the unmerged model
___
___
here's a result from a merge with my Hermione model
___
___
here's a result from a merge with my cat girl model
 |
iamkaikai/amazing-logos-v2 | iamkaikai | "2023-08-22T22:58:40Z" | 1,924 | 19 | diffusers | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dataset:iamkaikai/amazing_logos_v3",
"base_model:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-08-01T16:18:44Z" |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
datasets:
- iamkaikai/amazing_logos_v3
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
# Text-to-image finetuning - iamkaikai/amazing-logos
This pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **iamkaikai/amazing_logos_v3** dataset.
Latest Update: Our v2 model is now equipped to support colored logos.
## Training info
These are the key hyperparameters used during training:
* Dataset size: 110k
* Epochs: 16
* Learning rate: 5e-07
* Batch size: 16
* Gradient accumulation steps: 1
* Image resolution: 512
* Mixed-precision: fp16
## Prompt Format
The prompt format is as follows:
```javascript
{template keywords} + [company name] + [concept & country] + [industry] + {template keywords}
```
## For example:
Colored logo
```text
Simple elegant logo for Google, G circle United states, technology, successful vibe, minimalist, thought-provoking, abstract, recognizable
```
monochrome logo (include "black and white")
```text
Simple elegant logo for Google, G circle United states, technology, successful vibe, minimalist, thought-provoking, abstract, recognizable, black and white
```
Here are some examples of prompts:
- Simple elegant logo for Digital Art, **D A square**, **education**, successful vibe, minimalist, thought-provoking, abstract, recognizable
- Simple elegant logo for 3M Technology, **3 M square United states**, **technology and product**, successful vibe, minimalist, thought-provoking, abstract, recognizable
- Simple elegant logo for 42Studio, **lines drop fire flame water**, **design studio**, successful vibe, minimalist, thought provoking, abstract, recognizable, relatable, sharp, vector art, even edges
## The [concept & country] section can include words such as:
- lines
- circles
- triangles
- dot
- crosses
- waves
- square
- letters (A-Z)
- 3D
- Angled
- Arrows
- cube
- Diamond
- Hexagon
- Loops
- outline
- ovals
- rectangle
- reflection
- rings
- round
- semicircle
- spiral
- woven
- stars
I invest in cloud GPU rentals to train my models. If you value what I do, consider buying me a coffee ☕️. Your support means a lot! https://www.buymeacoffee.com/iamkaikai666 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.