Search is not available for this dataset
pipeline_tag
stringclasses 48
values | library_name
stringclasses 205
values | text
stringlengths 0
18.3M
| metadata
stringlengths 2
1.07B
| id
stringlengths 5
122
| last_modified
null | tags
listlengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
|
|---|---|---|---|---|---|---|---|---|
null | null |
{}
|
Anshulmango/Mistral_7B_0.2_Chat_finetuned_DS_v8_no_quantization
| null |
[
"region:us"
] | null |
2024-04-24T15:18:22+00:00
|
|
null | null |
{"license": "apache-2.0"}
|
Toniscas/MyModel
| null |
[
"license:apache-2.0",
"region:us"
] | null |
2024-04-24T15:18:46+00:00
|
|
null | null |
{}
|
21bce239/question-answering-squad
| null |
[
"region:us"
] | null |
2024-04-24T15:18:51+00:00
|
|
text-classification
|
setfit
|
# SetFit with sentence-transformers/paraphrase-mpnet-base-v2
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 2 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:---------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| negative | <ul><li>'stale and uninspired . '</li><li>"the film 's considered approach to its subject matter is too calm and thoughtful for agitprop , and the thinness of its characterizations makes it a failure as straight drama . ' "</li><li>"that their charm does n't do a load of good "</li></ul> |
| positive | <ul><li>"broomfield is energized by volletta wallace 's maternal fury , her fearlessness "</li><li>'flawless '</li><li>'insightfully written , delicately performed '</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.8575 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("setfit_model_id")
# Run inference
preds = model("a fast , funny , highly enjoyable movie . ")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:--------|:----|
| Word count | 2 | 11.4375 | 33 |
| Label | Training Sample Count |
|:---------|:----------------------|
| negative | 8 |
| positive | 8 |
### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (4, 4)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: True
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:-------:|:------:|:-------------:|:---------------:|
| 0.1111 | 1 | 0.2054 | - |
| 1.0 | 9 | - | 0.2199 |
| 2.0 | 18 | - | 0.1788 |
| **3.0** | **27** | **-** | **0.1717** |
| 4.0 | 36 | - | 0.1738 |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.11.5
- SetFit: 1.0.3
- Sentence Transformers: 2.2.2
- Transformers: 4.39.3
- PyTorch: 2.2.0+cpu
- Datasets: 2.18.0
- Tokenizers: 0.15.2
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->
|
{"library_name": "setfit", "tags": ["setfit", "sentence-transformers", "text-classification", "generated_from_setfit_trainer"], "metrics": ["accuracy"], "base_model": "sentence-transformers/paraphrase-mpnet-base-v2", "widget": [{"text": "this is a story of two misfits who do n't stand a chance alone , but together they are magnificent . "}, {"text": "it does n't believe in itself , it has no sense of humor ... it 's just plain bored . "}, {"text": "the band 's courage in the face of official repression is inspiring , especially for aging hippies ( this one included ) . "}, {"text": "a fast , funny , highly enjoyable movie . "}, {"text": "the movie achieves as great an impact by keeping these thoughts hidden as ... ( quills ) did by showing them . "}], "pipeline_tag": "text-classification", "inference": true, "model-index": [{"name": "SetFit with sentence-transformers/paraphrase-mpnet-base-v2", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "Unknown", "type": "unknown", "split": "test"}, "metrics": [{"type": "accuracy", "value": 0.8575129533678757, "name": "Accuracy"}]}]}]}
|
Christina0824/setfit-test
| null |
[
"setfit",
"safetensors",
"mpnet",
"sentence-transformers",
"text-classification",
"generated_from_setfit_trainer",
"arxiv:2209.11055",
"base_model:sentence-transformers/paraphrase-mpnet-base-v2",
"model-index",
"region:us"
] | null |
2024-04-24T15:19:05+00:00
|
null | null |
{}
|
yzhuang/Meta-Llama-3-8B-Instruct_fictional_Korean_v3
| null |
[
"region:us"
] | null |
2024-04-24T15:19:48+00:00
|
|
text-generation
|
transformers
|
{}
|
Weni/WeniGPT-Agents-Mistral-1.0.15-SFT-AWQ
| null |
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null |
2024-04-24T15:20:08+00:00
|
|
text-generation
|
peft
|
### Model Description
- **Developed by:** [Microsoft]
- **Model type:** [Text Generation]
- **Finetuned from model** [microsoft/phi-1_5]
## How to Use
Phi-1.5 has been integrated in the transformers version 4.30.0. ensure that you are doing the following:
* When loading the model, ensure that trust_remote_code=True is passed as an argument of the from_pretrained() function.
### Intended Uses
Given the nature of the training data, Fashion Phi-1.5 is best suited for prompts using the QA format, the chat format. Note that Fashion Phi-1.5 often produces irrelevant text following the main answer. In the following example, we've truncated the answer for illustrative purposes only.
## QA
```markdown
<human>: What can I wear with an olive green bomber jacket for a winter casual outing? Olive Male
<assistant>: Great choice! To wear with an olive green bomber jacket for a winter casual outing consider adding: 1. White or gray graphic T-shirt for a laid-back vibe. 2. Dark denim jeans or cargo pants for a rugged look. 3. High-top sneakers or combat boots for a street-style finish. 4. A plaid flannel shirt or denim jacket for added warmth. 5. A patterned scarf or beanie for a pop of color and style.
```
## How to Get Started with the Model
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'
Model = 'SSTalha/Fashion_PHI_1-5'
model = AutoModelForCausalLM.from_pretrained(Model, torch_dtype="auto", trust_remote_code=True).to(torch_device)
tokenizer = AutoTokenizer.from_pretrained(Model, trust_remote_code=True)
inputs = tokenizer('''<human>: Have black dress pants and need advice on a shirt for a semi-formal gathering. Any recommendations on colors and styles? Black Male ''', return_tensors="pt", return_attention_mask=False)
inputs = {key: value.to('cuda') for key, value in inputs.items()}
outputs = model.generate(**inputs, max_length=90)
text = tokenizer.batch_decode(outputs)[0]
print(text)
```
|
{"language": ["en"], "license": "mit", "library_name": "peft", "tags": ["nlp", "code"], "pipeline_tag": "text-generation"}
|
SSTalha/Fashion_PHI_1-5
| null |
[
"peft",
"pytorch",
"safetensors",
"mixformer-sequential",
"nlp",
"code",
"text-generation",
"custom_code",
"en",
"license:mit",
"region:us"
] | null |
2024-04-24T15:20:32+00:00
|
null |
transformers
|
# Uploaded model
- **Developed by:** manjunathshiva
- **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)
|
{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit"}
|
manjunathshiva/llama3_8b_kannada_lora_model
| null |
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:21:56+00:00
|
null | null |
{}
|
thurac2022/Phi-3-mini-128k-instruct-GGUF
| null |
[
"gguf",
"region:us"
] | null |
2024-04-24T15:22:14+00:00
|
|
null | null |
{}
|
ozguntosun/whisper-small-hi
| null |
[
"region:us"
] | null |
2024-04-24T15:22:37+00:00
|
|
null | null |
{}
|
Mohammadreza/llava-1.5-7b-hf-ft-mix-vsft
| null |
[
"region:us"
] | null |
2024-04-24T15:22:59+00:00
|
|
text-generation
|
transformers
|
# OpenELM
*Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao, Maxwell Horton, Yanzi Jin, Chenfan Sun, Iman Mirzadeh, Mahyar Najibi, Dmitry Belenko, Peter Zatloukal, Mohammad Rastegari*
We introduce **OpenELM**, a family of **Open**-source **E**fficient **L**anguage **M**odels. OpenELM uses a layer-wise scaling strategy to efficiently allocate parameters within each layer of the transformer model, leading to enhanced accuracy. We pretrained OpenELM models using the [CoreNet](https://github.com/apple/corenet) library. We release both pretrained and instruction tuned models with 270M, 450M, 1.1B and 3B parameters.
Our pre-training dataset contains RefinedWeb, deduplicated PILE, a subset of RedPajama, and a subset of Dolma v1.6, totaling approximately 1.8 trillion tokens. Please check license agreements and terms of these datasets before using them.
## Usage
We have provided an example function to generate output from OpenELM models loaded via [HuggingFace Hub](https://huggingface.co/docs/hub/) in `generate_openelm.py`.
You can try the model by running the following command:
```
python generate_openelm.py --model apple/OpenELM-1_1B --hf_access_token [HF_ACCESS_TOKEN] --prompt 'Once upon a time there was' --generate_kwargs repetition_penalty=1.2
```
Please refer to [this link](https://huggingface.co/docs/hub/security-tokens) to obtain your hugging face access token.
Additional arguments to the hugging face generate function can be passed via `generate_kwargs`. As an example, to speedup the inference, you can try [lookup token speculative generation](https://huggingface.co/docs/transformers/generation_strategies) by passing the `prompt_lookup_num_tokens` argument as follows:
```
python generate_openelm.py --model apple/OpenELM-1_1B --hf_access_token [HF_ACCESS_TOKEN] --prompt 'Once upon a time there was' --generate_kwargs repetition_penalty=1.2 prompt_lookup_num_tokens=10
```
Alternatively, try model-wise speculative generation with an [assistive model](https://huggingface.co/blog/assisted-generation) by passing a smaller model through the `assistant_model` argument, for example:
```
python generate_openelm.py --model apple/OpenELM-1_1B --hf_access_token [HF_ACCESS_TOKEN] --prompt 'Once upon a time there was' --generate_kwargs repetition_penalty=1.2 --assistant_model [SMALLER_MODEL]
```
## Main Results
### Zero-Shot
| **Model Size** | **ARC-c** | **ARC-e** | **BoolQ** | **HellaSwag** | **PIQA** | **SciQ** | **WinoGrande** | **Average** |
|-----------------------------------------------------------------------------|-----------|-----------|-----------|---------------|-----------|-----------|----------------|-------------|
| [OpenELM-270M](https://huggingface.co/apple/OpenELM-270M) | 26.45 | 45.08 | **53.98** | 46.71 | 69.75 | **84.70** | **53.91** | 54.37 |
| [OpenELM-270M-Instruct](https://huggingface.co/apple/OpenELM-270M-Instruct) | **30.55** | **46.68** | 48.56 | **52.07** | **70.78** | 84.40 | 52.72 | **55.11** |
| [OpenELM-450M](https://huggingface.co/apple/OpenELM-450M) | 27.56 | 48.06 | 55.78 | 53.97 | 72.31 | 87.20 | 58.01 | 57.56 |
| [OpenELM-450M-Instruct](https://huggingface.co/apple/OpenELM-450M-Instruct) | **30.38** | **50.00** | **60.37** | **59.34** | **72.63** | **88.00** | **58.96** | **59.95** |
| [OpenELM-1_1B](https://huggingface.co/apple/OpenELM-1_1B) | 32.34 | **55.43** | 63.58 | 64.81 | **75.57** | **90.60** | 61.72 | 63.44 |
| [OpenELM-1_1B-Instruct](https://huggingface.co/apple/OpenELM-1_1B-Instruct) | **37.97** | 52.23 | **70.00** | **71.20** | 75.03 | 89.30 | **62.75** | **65.50** |
| [OpenELM-3B](https://huggingface.co/apple/OpenELM-3B) | 35.58 | 59.89 | 67.40 | 72.44 | 78.24 | **92.70** | 65.51 | 67.39 |
| [OpenELM-3B-Instruct](https://huggingface.co/apple/OpenELM-3B-Instruct) | **39.42** | **61.74** | **68.17** | **76.36** | **79.00** | 92.50 | **66.85** | **69.15** |
### LLM360
| **Model Size** | **ARC-c** | **HellaSwag** | **MMLU** | **TruthfulQA** | **WinoGrande** | **Average** |
|-----------------------------------------------------------------------------|-----------|---------------|-----------|----------------|----------------|-------------|
| [OpenELM-270M](https://huggingface.co/apple/OpenELM-270M) | 27.65 | 47.15 | 25.72 | **39.24** | **53.83** | 38.72 |
| [OpenELM-270M-Instruct](https://huggingface.co/apple/OpenELM-270M-Instruct) | **32.51** | **51.58** | **26.70** | 38.72 | 53.20 | **40.54** |
| [OpenELM-450M](https://huggingface.co/apple/OpenELM-450M) | 30.20 | 53.86 | **26.01** | 40.18 | 57.22 | 41.50 |
| [OpenELM-450M-Instruct](https://huggingface.co/apple/OpenELM-450M-Instruct) | **33.53** | **59.31** | 25.41 | **40.48** | **58.33** | **43.41** |
| [OpenELM-1_1B](https://huggingface.co/apple/OpenELM-1_1B) | 36.69 | 65.71 | **27.05** | 36.98 | 63.22 | 45.93 |
| [OpenELM-1_1B-Instruct](https://huggingface.co/apple/OpenELM-1_1B-Instruct) | **41.55** | **71.83** | 25.65 | **45.95** | **64.72** | **49.94** |
| [OpenELM-3B](https://huggingface.co/apple/OpenELM-3B) | 42.24 | 73.28 | **26.76** | 34.98 | 67.25 | 48.90 |
| [OpenELM-3B-Instruct](https://huggingface.co/apple/OpenELM-3B-Instruct) | **47.70** | **76.87** | 24.80 | **38.76** | **67.96** | **51.22** |
### OpenLLM Leaderboard
| **Model Size** | **ARC-c** | **CrowS-Pairs** | **HellaSwag** | **MMLU** | **PIQA** | **RACE** | **TruthfulQA** | **WinoGrande** | **Average** |
|-----------------------------------------------------------------------------|-----------|-----------------|---------------|-----------|-----------|-----------|----------------|----------------|-------------|
| [OpenELM-270M](https://huggingface.co/apple/OpenELM-270M) | 27.65 | **66.79** | 47.15 | 25.72 | 69.75 | 30.91 | **39.24** | **53.83** | 45.13 |
| [OpenELM-270M-Instruct](https://huggingface.co/apple/OpenELM-270M-Instruct) | **32.51** | 66.01 | **51.58** | **26.70** | **70.78** | 33.78 | 38.72 | 53.20 | **46.66** |
| [OpenELM-450M](https://huggingface.co/apple/OpenELM-450M) | 30.20 | **68.63** | 53.86 | **26.01** | 72.31 | 33.11 | 40.18 | 57.22 | 47.69 |
| [OpenELM-450M-Instruct](https://huggingface.co/apple/OpenELM-450M-Instruct) | **33.53** | 67.44 | **59.31** | 25.41 | **72.63** | **36.84** | **40.48** | **58.33** | **49.25** |
| [OpenELM-1_1B](https://huggingface.co/apple/OpenELM-1_1B) | 36.69 | **71.74** | 65.71 | **27.05** | **75.57** | 36.46 | 36.98 | 63.22 | 51.68 |
| [OpenELM-1_1B-Instruct](https://huggingface.co/apple/OpenELM-1_1B-Instruct) | **41.55** | 71.02 | **71.83** | 25.65 | 75.03 | **39.43** | **45.95** | **64.72** | **54.40** |
| [OpenELM-3B](https://huggingface.co/apple/OpenELM-3B) | 42.24 | **73.29** | 73.28 | **26.76** | 78.24 | **38.76** | 34.98 | 67.25 | 54.35 |
| [OpenELM-3B-Instruct](https://huggingface.co/apple/OpenELM-3B-Instruct) | **47.70** | 72.33 | **76.87** | 24.80 | **79.00** | 38.47 | **38.76** | **67.96** | **55.73** |
See the technical report for more results and comparison.
## Evaluation
### Setup
Install the following dependencies:
```bash
# install public lm-eval-harness
harness_repo="public-lm-eval-harness"
git clone https://github.com/EleutherAI/lm-evaluation-harness ${harness_repo}
cd ${harness_repo}
# use main branch on 03-15-2024, SHA is dc90fec
git checkout dc90fec
pip install -e .
cd ..
# 66d6242 is the main branch on 2024-04-01
pip install datasets@git+https://github.com/huggingface/datasets.git@66d6242
pip install tokenizers>=0.15.2 transformers>=4.38.2 sentencepiece>=0.2.0
```
### Evaluate OpenELM
```bash
# OpenELM-1_1B
hf_model=OpenELM-1_1B
# this flag is needed because lm-eval-harness set add_bos_token to False by default, but OpenELM uses LLaMA tokenizer which requires add_bos_token to be True
tokenizer=meta-llama/Llama-2-7b-hf
add_bos_token=True
batch_size=1
mkdir lm_eval_output
shot=0
task=arc_challenge,arc_easy,boolq,hellaswag,piqa,race,winogrande,sciq,truthfulqa_mc2
lm_eval --model hf \
--model_args pretrained=${hf_model},trust_remote_code=True,add_bos_token=${add_bos_token},tokenizer=${tokenizer} \
--tasks ${task} \
--device cuda:0 \
--num_fewshot ${shot} \
--output_path ./lm_eval_output/${hf_model//\//_}_${task//,/_}-${shot}shot \
--batch_size ${batch_size} 2>&1 | tee ./lm_eval_output/eval-${hf_model//\//_}_${task//,/_}-${shot}shot.log
shot=5
task=mmlu,winogrande
lm_eval --model hf \
--model_args pretrained=${hf_model},trust_remote_code=True,add_bos_token=${add_bos_token},tokenizer=${tokenizer} \
--tasks ${task} \
--device cuda:0 \
--num_fewshot ${shot} \
--output_path ./lm_eval_output/${hf_model//\//_}_${task//,/_}-${shot}shot \
--batch_size ${batch_size} 2>&1 | tee ./lm_eval_output/eval-${hf_model//\//_}_${task//,/_}-${shot}shot.log
shot=25
task=arc_challenge,crows_pairs_english
lm_eval --model hf \
--model_args pretrained=${hf_model},trust_remote_code=True,add_bos_token=${add_bos_token},tokenizer=${tokenizer} \
--tasks ${task} \
--device cuda:0 \
--num_fewshot ${shot} \
--output_path ./lm_eval_output/${hf_model//\//_}_${task//,/_}-${shot}shot \
--batch_size ${batch_size} 2>&1 | tee ./lm_eval_output/eval-${hf_model//\//_}_${task//,/_}-${shot}shot.log
shot=10
task=hellaswag
lm_eval --model hf \
--model_args pretrained=${hf_model},trust_remote_code=True,add_bos_token=${add_bos_token},tokenizer=${tokenizer} \
--tasks ${task} \
--device cuda:0 \
--num_fewshot ${shot} \
--output_path ./lm_eval_output/${hf_model//\//_}_${task//,/_}-${shot}shot \
--batch_size ${batch_size} 2>&1 | tee ./lm_eval_output/eval-${hf_model//\//_}_${task//,/_}-${shot}shot.log
```
## Bias, Risks, and Limitations
The release of OpenELM models aims to empower and enrich the open research community by providing access to state-of-the-art language models. Trained on publicly available datasets, these models are made available without any safety guarantees. Consequently, there exists the possibility of these models producing outputs that are inaccurate, harmful, biased, or objectionable in response to user prompts. Thus, it is imperative for users and developers to undertake thorough safety testing and implement appropriate filtering mechanisms tailored to their specific requirements.
## Citation
If you find our work useful, please cite:
```BibTex
@article{mehtaOpenELMEfficientLanguage2024,
title = {{OpenELM}: {An} {Efficient} {Language} {Model} {Family} with {Open}-source {Training} and {Inference} {Framework}},
shorttitle = {{OpenELM}},
url = {https://arxiv.org/abs/2404.14619v1},
language = {en},
urldate = {2024-04-24},
journal = {arXiv.org},
author = {Mehta, Sachin and Sekhavat, Mohammad Hossein and Cao, Qingqing and Horton, Maxwell and Jin, Yanzi and Sun, Chenfan and Mirzadeh, Iman and Najibi, Mahyar and Belenko, Dmitry and Zatloukal, Peter and Rastegari, Mohammad},
month = apr,
year = {2024},
}
@inproceedings{mehta2022cvnets,
author = {Mehta, Sachin and Abdolhosseini, Farzad and Rastegari, Mohammad},
title = {CVNets: High Performance Library for Computer Vision},
year = {2022},
booktitle = {Proceedings of the 30th ACM International Conference on Multimedia},
series = {MM '22}
}
```
|
{"license": "other", "license_name": "apple-sample-code-license", "license_link": "LICENSE"}
|
TommyZQ/OpenELM-1_1B
| null |
[
"transformers",
"safetensors",
"openelm",
"text-generation",
"custom_code",
"arxiv:2404.14619",
"license:other",
"autotrain_compatible",
"region:us"
] | null |
2024-04-24T15:23:27+00:00
|
null |
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
xuliu15/openai-whisper-small-frisian-colab
| null |
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:24:22+00:00
|
text-generation
|
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
CMU-AIR2/math-deepseek_FULL_HardArith_Interm-FTMWP-FULL
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T15:24:31+00:00
|
text-generation
|
transformers
|
<!-- 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. -->
# stablelm-2-1_6b-spin-dpo-3-full
This model was trained from scratch on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 6
- gradient_accumulation_steps: 10
- total_train_batch_size: 60
- total_eval_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
|
{"tags": ["trl", "dpo", "generated_from_trainer"], "model-index": [{"name": "stablelm-2-1_6b-spin-dpo-3-full", "results": []}]}
|
nnheui/stablelm-2-1_6b-spin-dpo-3-full
| null |
[
"transformers",
"tensorboard",
"safetensors",
"stablelm",
"text-generation",
"trl",
"dpo",
"generated_from_trainer",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:24:58+00:00
|
null |
transformers
|
# Listwise MonoBERT trained on Baidu-ULTR using the Dual Learning Algorithm (DLA)
A flax-based MonoBERT cross encoder trained on the [Baidu-ULTR](https://arxiv.org/abs/2207.03051) dataset with a **listwise DLA objective on clicks**. Following [Ai et al.](https://arxiv.org/abs/1804.05938), the dual learning algorithm jointly infers item relevance (using a BERT model) and position bias (in our case, a single embedding parameter per rank), both by optimizing a **listwise softmax cross-entropy loss**. For more info, [read our paper](https://arxiv.org/abs/2404.02543) and [find the code for this model here](https://github.com/philipphager/baidu-bert-model).
## Test Results on Baidu-ULTR
Ranking performance is measured in DCG, nDCG, and MRR on expert annotations (6,985 queries). Click prediction performance is measured in log-likelihood on one test partition of user clicks (≈297k queries).
| Model | Log-likelihood | DCG@1 | DCG@3 | DCG@5 | DCG@10 | nDCG@10 | MRR@10 |
|------------------------------------------------------------------------------------------------|----------------|-------|-------|-------|--------|---------|--------|
| [Pointwise Naive](https://huggingface.co/philipphager/baidu-ultr_uva-bert_naive-pointwise) | 0.227 | 1.641 | 3.462 | 4.752 | 7.251 | 0.357 | 0.609 |
| [Pointwise Two-Tower](https://huggingface.co/philipphager/baidu-ultr_uva-bert_twotower) | 0.218 | 1.629 | 3.471 | 4.822 | 7.456 | 0.367 | 0.607 |
| [Pointwise IPS](https://huggingface.co/philipphager/baidu-ultr_uva-bert_ips-pointwise) | 0.222 | 1.295 | 2.811 | 3.977 | 6.296 | 0.307 | 0.534 |
| [Listwise Naive](https://huggingface.co/philipphager/baidu-ultr_uva-bert_naive-listwise) | - | 1.947 | 4.108 | 5.614 | 8.478 | 0.405 | 0.639 |
| [Listwise IPS](https://huggingface.co/philipphager/baidu-ultr_uva-bert_ips-listwise) | - | 1.671 | 3.530 | 4.873 | 7.450 | 0.361 | 0.603 |
| [Listwise DLA](https://huggingface.co/philipphager/baidu-ultr_uva-bert_dla) | - | 1.796 | 3.730 | 5.125 | 7.802 | 0.377 | 0.615 |
## Usage
Here is an example of downloading the model and calling it for inference on a mock batch of input data. For more details on how to use the model on the Baidu-ULTR dataset, take a look at our [training](https://github.com/philipphager/baidu-bert-model/blob/main/main.py) and [evaluation scripts](https://github.com/philipphager/baidu-bert-model/blob/main/eval.py) in our code repository.
```Python
import jax.numpy as jnp
from src.model import DLACrossEncoder
model = DLACrossEncoder.from_pretrained(
"philipphager/baidu-ultr_uva-bert_dla",
)
# Mock batch following Baidu-ULTR with 4 documents, each with 8 tokens
batch = {
# Query_id for each document
"query_id": jnp.array([1, 1, 1, 1]),
# Document position in SERP
"positions": jnp.array([1, 2, 3, 4]),
# Token ids for: [CLS] Query [SEP] Document
"tokens": jnp.array([
[2, 21448, 21874, 21436, 1, 20206, 4012, 2860],
[2, 21448, 21874, 21436, 1, 16794, 4522, 2082],
[2, 21448, 21874, 21436, 1, 20206, 10082, 9773],
[2, 21448, 21874, 21436, 1, 2618, 8520, 2860],
]),
# Specify if a token id belongs to the query (0) or document (1)
"token_types": jnp.array([
[0, 0, 0, 0, 1, 1, 1, 1],
[0, 0, 0, 0, 1, 1, 1, 1],
[0, 0, 0, 0, 1, 1, 1, 1],
[0, 0, 0, 0, 1, 1, 1, 1],
]),
# Marks if a token should be attended to (True) or ignored, e.g., padding tokens (False):
"attention_mask": jnp.array([
[True, True, True, True, True, True, True, True],
[True, True, True, True, True, True, True, True],
[True, True, True, True, True, True, True, True],
[True, True, True, True, True, True, True, True],
]),
}
outputs = model(batch, train=False)
print(outputs)
```
## Reference
```
@inproceedings{Hager2024BaiduULTR,
author = {Philipp Hager and Romain Deffayet and Jean-Michel Renders and Onno Zoeter and Maarten de Rijke},
title = {Unbiased Learning to Rank Meets Reality: Lessons from Baidu’s Large-Scale Search Dataset},
booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR`24)},
organization = {ACM},
year = {2024},
}
```
|
{"license": "mit", "datasets": ["philipphager/baidu-ultr-pretrain", "philipphager/baidu-ultr_uva-mlm-ctr"], "metrics": ["log-likelihood", "dcg@1", "dcg@3", "dcg@5", "dcg@10", "ndcg@10", "mrr@10"], "co2_eq_emissions": {"emissions": 2090, "source": "Calculated using the [ML CO2 impact calculator](https://mlco2.github.io/impact/#compute), training for 4 x 45 hours with a carbon efficiency of 0.029 kg/kWh. You can inspect the carbon efficiency of the French national grid provider here: https://www.rte-france.com/eco2mix/les-emissions-de-co2-par-kwh-produit-en-france", "training_type": "Pre-training", "geographical_location": "Grenoble, France", "hardware_used": "4 NVIDIA H100-80GB GPUs"}}
|
philipphager/baidu-ultr_uva-bert_dla
| null |
[
"transformers",
"safetensors",
"bert",
"dataset:philipphager/baidu-ultr-pretrain",
"dataset:philipphager/baidu-ultr_uva-mlm-ctr",
"arxiv:2207.03051",
"arxiv:1804.05938",
"arxiv:2404.02543",
"license:mit",
"co2_eq_emissions",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:27:05+00:00
|
automatic-speech-recognition
|
transformers
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Large TR - Özgün Tosun
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 16.1 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1323
- Wer: 11.7279
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.1372 | 0.3652 | 1000 | 0.1810 | 16.0805 |
| 0.1103 | 0.7305 | 2000 | 0.1628 | 14.5458 |
| 0.0563 | 1.0957 | 3000 | 0.1513 | 12.9302 |
| 0.0657 | 1.4609 | 4000 | 0.1383 | 12.4198 |
| 0.0444 | 1.8262 | 5000 | 0.1323 | 11.7279 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
|
{"language": ["tr"], "license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["mozilla-foundation/common_voice_16_1"], "metrics": ["wer"], "base_model": "openai/whisper-large-v3", "model-index": [{"name": "Whisper Large TR - \u00d6zg\u00fcn Tosun", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "Common Voice 16.1", "type": "mozilla-foundation/common_voice_16_1", "config": "tr", "split": "None", "args": "config: tr, split: test"}, "metrics": [{"type": "wer", "value": 11.727918051936383, "name": "Wer"}]}]}]}
|
ozguntosun/whisper-large-v3-tr
| null |
[
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"tr",
"dataset:mozilla-foundation/common_voice_16_1",
"base_model:openai/whisper-large-v3",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:27:35+00:00
|
null |
transformers
|
# Two Tower MonoBERT trained on Baidu-ULTR
A flax-based MonoBERT cross encoder trained on the [Baidu-ULTR](https://arxiv.org/abs/2207.03051) dataset with an **additivie two tower architecture** as suggested by [Yan et al](https://research.google/pubs/revisiting-two-tower-models-for-unbiased-learning-to-rank/). Similar to a position-based click model (PBM), a two tower model jointly learns item relevance (with a BERT model) and position bias (in our case using a single embedding per rank). For more info, [read our paper](https://arxiv.org/abs/2404.02543) and [find the code for this model here](https://github.com/philipphager/baidu-bert-model).
## Test Results on Baidu-ULTR
Ranking performance is measured in DCG, nDCG, and MRR on expert annotations (6,985 queries). Click prediction performance is measured in log-likelihood on one test partition of user clicks (≈297k queries).
| Model | Log-likelihood | DCG@1 | DCG@3 | DCG@5 | DCG@10 | nDCG@10 | MRR@10 |
|------------------------------------------------------------------------------------------------|----------------|-------|-------|-------|--------|---------|--------|
| [Pointwise Naive](https://huggingface.co/philipphager/baidu-ultr_uva-bert_naive-pointwise) | 0.227 | 1.641 | 3.462 | 4.752 | 7.251 | 0.357 | 0.609 |
| [Pointwise Two-Tower](https://huggingface.co/philipphager/baidu-ultr_uva-bert_twotower) | 0.218 | 1.629 | 3.471 | 4.822 | 7.456 | 0.367 | 0.607 |
| [Pointwise IPS](https://huggingface.co/philipphager/baidu-ultr_uva-bert_ips-pointwise) | 0.222 | 1.295 | 2.811 | 3.977 | 6.296 | 0.307 | 0.534 |
| [Listwise Naive](https://huggingface.co/philipphager/baidu-ultr_uva-bert_naive-listwise) | - | 1.947 | 4.108 | 5.614 | 8.478 | 0.405 | 0.639 |
| [Listwise IPS](https://huggingface.co/philipphager/baidu-ultr_uva-bert_ips-listwise) | - | 1.671 | 3.530 | 4.873 | 7.450 | 0.361 | 0.603 |
| [Listwise DLA](https://huggingface.co/philipphager/baidu-ultr_uva-bert_dla) | - | 1.796 | 3.730 | 5.125 | 7.802 | 0.377 | 0.615 |
## Usage
Here is an example of downloading the model and calling it for inference on a mock batch of input data. For more details on how to use the model on the Baidu-ULTR dataset, take a look at our [training](https://github.com/philipphager/baidu-bert-model/blob/main/main.py) and [evaluation scripts](https://github.com/philipphager/baidu-bert-model/blob/main/eval.py) in our code repository.
```Python
import jax.numpy as jnp
from src.model import PBMCrossEncoder
model = PBMCrossEncoder.from_pretrained(
"philipphager/baidu-ultr_uva-bert_twotower",
)
# Mock batch following Baidu-ULTR with 4 documents, each with 8 tokens
batch = {
# Query_id for each document
"query_id": jnp.array([1, 1, 1, 1]),
# Document position in SERP
"positions": jnp.array([1, 2, 3, 4]),
# Token ids for: [CLS] Query [SEP] Document
"tokens": jnp.array([
[2, 21448, 21874, 21436, 1, 20206, 4012, 2860],
[2, 21448, 21874, 21436, 1, 16794, 4522, 2082],
[2, 21448, 21874, 21436, 1, 20206, 10082, 9773],
[2, 21448, 21874, 21436, 1, 2618, 8520, 2860],
]),
# Specify if a token id belongs to the query (0) or document (1)
"token_types": jnp.array([
[0, 0, 0, 0, 1, 1, 1, 1],
[0, 0, 0, 0, 1, 1, 1, 1],
[0, 0, 0, 0, 1, 1, 1, 1],
[0, 0, 0, 0, 1, 1, 1, 1],
]),
# Marks if a token should be attended to (True) or ignored, e.g., padding tokens (False):
"attention_mask": jnp.array([
[True, True, True, True, True, True, True, True],
[True, True, True, True, True, True, True, True],
[True, True, True, True, True, True, True, True],
[True, True, True, True, True, True, True, True],
]),
}
outputs = model(batch, train=False)
print(outputs)
```
## Reference
```
@inproceedings{Hager2024BaiduULTR,
author = {Philipp Hager and Romain Deffayet and Jean-Michel Renders and Onno Zoeter and Maarten de Rijke},
title = {Unbiased Learning to Rank Meets Reality: Lessons from Baidu’s Large-Scale Search Dataset},
booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR`24)},
organization = {ACM},
year = {2024},
}
```
|
{"license": "mit", "datasets": ["philipphager/baidu-ultr-pretrain", "philipphager/baidu-ultr_uva-mlm-ctr"], "metrics": ["log-likelihood", "dcg@1", "dcg@3", "dcg@5", "dcg@10", "ndcg@10", "mrr@10"], "co2_eq_emissions": {"emissions": 2090, "source": "Calculated using the [ML CO2 impact calculator](https://mlco2.github.io/impact/#compute), training for 4 x 45 hours with a carbon efficiency of 0.029 kg/kWh. You can inspect the carbon efficiency of the French national grid provider here: https://www.rte-france.com/eco2mix/les-emissions-de-co2-par-kwh-produit-en-france", "training_type": "Pre-training", "geographical_location": "Grenoble, France", "hardware_used": "4 NVIDIA H100-80GB GPUs"}}
|
philipphager/baidu-ultr_uva-bert_twotower
| null |
[
"transformers",
"safetensors",
"bert",
"dataset:philipphager/baidu-ultr-pretrain",
"dataset:philipphager/baidu-ultr_uva-mlm-ctr",
"arxiv:2207.03051",
"arxiv:2404.02543",
"license:mit",
"co2_eq_emissions",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:27:46+00:00
|
null |
mlx
|
# mlx-community/OpenELM-450M-instruct-8bit
This model was converted to MLX format from [`apple/OpenELM-450M-instruct`]() using mlx-lm version **0.10.0**.
Refer to the [original model card](https://huggingface.co/apple/OpenELM-450M-instruct) for more details on the model.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/OpenELM-450M-instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
{"license": "other", "tags": ["mlx"], "license_name": "apple-sample-code-license", "license_link": "LICENSE"}
|
mlx-community/OpenELM-450M-instruct-8bit
| null |
[
"mlx",
"safetensors",
"openelm",
"custom_code",
"license:other",
"region:us"
] | null |
2024-04-24T15:29:44+00:00
|
null | null |
{}
|
PierreAncey/test_submission
| null |
[
"region:us"
] | null |
2024-04-24T15:29:46+00:00
|
|
text-generation
|
transformers
|
{}
|
aaditya/46f17f5d-2412-4623-979b-c9f0c6f964e3
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T15:31:06+00:00
|
|
null |
peft
|
<!-- 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. -->
# phi-2-finetuned-detox
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- training_steps: 10
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "mit", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "microsoft/phi-2", "model-index": [{"name": "phi-2-finetuned-detox", "results": []}]}
|
NikAlan/phi-2-finetuned-detox
| null |
[
"peft",
"safetensors",
"phi",
"generated_from_trainer",
"custom_code",
"base_model:microsoft/phi-2",
"license:mit",
"region:us"
] | null |
2024-04-24T15:31:51+00:00
|
null |
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
MikeMpapa/lmd_mmm_tokenizer_tutorial_artist
| null |
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us",
"has_space"
] | null |
2024-04-24T15:32:35+00:00
|
image-to-text
|
transformers
|
#### Running the model on GPU
```python
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("prithivMLmods/Beetz-Image-Captioning-Blip")
model = BlipForConditionalGeneration.from_pretrained("prithivMLmods/Beetz-Image-Captioning-Blip").to("cuda")
img_url = ''
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
```
|
{"license": "creativeml-openrail-m", "tags": ["image-captioning"], "pipeline_tag": "image-to-text", "languages": ["en"]}
|
prithivMLmods/Beetz-Image-Captioning-Blip
| null |
[
"transformers",
"pytorch",
"tf",
"safetensors",
"blip",
"text2text-generation",
"image-captioning",
"image-to-text",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:32:56+00:00
|
null |
mlx
|
# mlx-community/OpenELM-450M-8bit
This model was converted to MLX format from [`apple/OpenELM-450M`]() using mlx-lm version **0.10.0**.
Refer to the [original model card](https://huggingface.co/apple/OpenELM-450M) for more details on the model.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/OpenELM-450M-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```
|
{"license": "other", "tags": ["mlx"], "license_name": "apple-sample-code-license", "license_link": "LICENSE"}
|
mlx-community/OpenELM-450M-8bit
| null |
[
"mlx",
"safetensors",
"openelm",
"custom_code",
"license:other",
"region:us"
] | null |
2024-04-24T15:33:05+00:00
|
null |
transformers
|
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/arlineka/Ionic-4x8
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Ionic-4x8-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/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.Q2_K.gguf) | Q2_K | 9.4 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.IQ3_XS.gguf) | IQ3_XS | 10.5 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.Q3_K_S.gguf) | Q3_K_S | 11.0 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.IQ3_S.gguf) | IQ3_S | 11.1 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.IQ3_M.gguf) | IQ3_M | 11.2 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.Q3_K_M.gguf) | Q3_K_M | 12.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.Q3_K_L.gguf) | Q3_K_L | 13.1 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.IQ4_XS.gguf) | IQ4_XS | 13.7 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.Q4_K_S.gguf) | Q4_K_S | 14.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.Q4_K_M.gguf) | Q4_K_M | 15.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.Q5_K_S.gguf) | Q5_K_S | 17.3 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.Q5_K_M.gguf) | Q5_K_M | 17.8 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.Q6_K.gguf) | Q6_K | 20.6 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Ionic-4x8-GGUF/resolve/main/Ionic-4x8.Q8_0.gguf) | Q8_0 | 26.6 | fast, best quality |
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 -->
|
{"language": ["en"], "library_name": "transformers", "base_model": "arlineka/Ionic-4x8", "quantized_by": "mradermacher"}
|
mradermacher/Ionic-4x8-GGUF
| null |
[
"transformers",
"gguf",
"en",
"base_model:arlineka/Ionic-4x8",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:33:29+00:00
|
null | null |
{}
|
JerZSteph/1
| null |
[
"region:us"
] | null |
2024-04-24T15:34:18+00:00
|
|
null |
peft
|
# 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. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.7.0.dev0
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.7.0.dev0
|
{"library_name": "peft", "base_model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0"}
|
bmehrba/TinyLlama-1.1B-Chat-v1.0-fine-tuned-adapters_Human_tiny_Seed101
| null |
[
"peft",
"arxiv:1910.09700",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"region:us"
] | null |
2024-04-24T15:34:55+00:00
|
null |
peft
|
# 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. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.7.0.dev0
|
{"library_name": "peft", "base_model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0"}
|
bmehrba/TinyLlama-1.1B-Chat-v1.0-fine-tuned_Human_tiny_Seed101
| null |
[
"peft",
"arxiv:1910.09700",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"region:us"
] | null |
2024-04-24T15:35:01+00:00
|
text-generation
|
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
heyllm234/sc76
| null |
[
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:35:29+00:00
|
null |
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
SamaahKhan/bart-after-fine-tuning
| null |
[
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:35:49+00:00
|
null |
peft
|
<!-- 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. -->
# HSE_PRAVO_complexity_classifier_roberta_20steps
This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 30
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 20
### Training results
### Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
|
{"license": "mit", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "FacebookAI/xlm-roberta-large", "model-index": [{"name": "HSE_PRAVO_complexity_classifier_roberta_20steps", "results": []}]}
|
marcus2000/HSE_PRAVO_complexity_classifier_roberta_20steps
| null |
[
"peft",
"safetensors",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-large",
"license:mit",
"region:us"
] | null |
2024-04-24T15:35:50+00:00
|
automatic-speech-recognition
|
transformers
|
<!-- 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. -->
# result_weight
This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vietnamese-250h](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h) on the common_voice_11_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6430
- Wer: 0.7862
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 40
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-------:|:----:|:---------------:|:------:|
| 19.1789 | 6.3291 | 500 | 5.0724 | 1.0 |
| 4.4582 | 12.6582 | 1000 | 3.4558 | 0.9989 |
| 3.8596 | 18.9873 | 1500 | 3.1687 | 0.9905 |
| 2.8095 | 25.3165 | 2000 | 2.2626 | 0.9084 |
| 2.0404 | 31.6456 | 2500 | 1.8938 | 0.8220 |
| 1.6879 | 37.9747 | 3000 | 1.6430 | 0.7862 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
|
{"license": "cc-by-nc-4.0", "tags": ["generated_from_trainer"], "datasets": ["common_voice_11_0"], "metrics": ["wer"], "base_model": "nguyenvulebinh/wav2vec2-base-vietnamese-250h", "model-index": [{"name": "result_weight", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "common_voice_11_0", "type": "common_voice_11_0", "config": "vi", "split": "None", "args": "vi"}, "metrics": [{"type": "wer", "value": 0.7862032648762507, "name": "Wer"}]}]}]}
|
AnhDuc2507/wav2vec2.0_train_on_2100_audio
| null |
[
"transformers",
"tensorboard",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"dataset:common_voice_11_0",
"base_model:nguyenvulebinh/wav2vec2-base-vietnamese-250h",
"license:cc-by-nc-4.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:36:05+00:00
|
text-generation
|
transformers
|
{}
|
katuni4ka/tiny-random-baichuan2-13b
| null |
[
"transformers",
"safetensors",
"baichuan",
"text-generation",
"custom_code",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:36:47+00:00
|
|
text-generation
|
transformers
|
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/franciscobdl/EstigiaxGemmaIt
<!-- 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/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.Q2_K.gguf) | Q2_K | 1.3 | |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.IQ3_XS.gguf) | IQ3_XS | 1.3 | |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.Q3_K_S.gguf) | Q3_K_S | 1.4 | |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.IQ3_S.gguf) | IQ3_S | 1.4 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.IQ3_M.gguf) | IQ3_M | 1.4 | |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.Q3_K_L.gguf) | Q3_K_L | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.IQ4_XS.gguf) | IQ4_XS | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.Q5_K_S.gguf) | Q5_K_S | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.Q5_K_M.gguf) | Q5_K_M | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.Q6_K.gguf) | Q6_K | 2.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/EstigiaxGemmaIt-GGUF/resolve/main/EstigiaxGemmaIt.f16.gguf) | f16 | 5.1 | 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 -->
|
{"language": ["en"], "license": "other", "library_name": "transformers", "tags": ["autotrain", "text-generation-inference", "text-generation", "peft"], "base_model": "franciscobdl/EstigiaxGemmaIt", "quantized_by": "mradermacher"}
|
mradermacher/EstigiaxGemmaIt-GGUF
| null |
[
"transformers",
"gguf",
"autotrain",
"text-generation-inference",
"text-generation",
"peft",
"en",
"base_model:franciscobdl/EstigiaxGemmaIt",
"license:other",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:37:07+00:00
|
null |
peft
|
<!-- 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. -->
# llama3-8b-8000-dpo
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1500
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
|
{"license": "other", "library_name": "peft", "tags": ["trl", "dpo", "generated_from_trainer"], "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "model-index": [{"name": "llama3-8b-8000-dpo", "results": []}]}
|
Yaxin1992/llama3-8b-8000-dpo
| null |
[
"peft",
"tensorboard",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:other",
"region:us"
] | null |
2024-04-24T15:38:13+00:00
|
null | null |
{"license": "openrail"}
|
luinor/gragas
| null |
[
"license:openrail",
"region:us"
] | null |
2024-04-24T15:38:24+00:00
|
|
null | null |
{}
|
alpacarlos/anyloracleanlinearmix
| null |
[
"region:us"
] | null |
2024-04-24T15:38:34+00:00
|
|
text-generation
|
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
cilantro9246/w3sf33b
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T15:38:40+00:00
|
null | null |
{}
|
kuei1026/corgy_dog_LoRA
| null |
[
"region:us"
] | null |
2024-04-24T15:38:59+00:00
|
|
text-generation
|
transformers
|
{}
|
XMin08/ModelTest
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T15:39:39+00:00
|
|
null | null |
{}
|
bobby-nakamoto/test-model-72
| null |
[
"region:us"
] | null |
2024-04-24T15:40:32+00:00
|
|
text-generation
|
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
ahmed807762/DialoGPT-large-vetdataset-finetuned
| null |
[
"transformers",
"tensorboard",
"safetensors",
"gpt2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T15:40:48+00:00
|
text-generation
|
transformers
|
{}
|
crusoeai/dolphin2.9-llama3-70b-4.5bpw-exl2
| null |
[
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T15:43:25+00:00
|
|
text-generation
|
transformers
|
# 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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) as a base.
### Models Merged
The following models were included in the merge:
* [ai-maker-space/riddle-bot-v1](https://huggingface.co/ai-maker-space/riddle-bot-v1)
* [ai-maker-space/leagaleasy-llama-3-instruct-v2](https://huggingface.co/ai-maker-space/leagaleasy-llama-3-instruct-v2)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: meta-llama/Meta-Llama-3-8B-Instruct
- model: ai-maker-space/leagaleasy-llama-3-instruct-v2
parameters:
density: 0.5
weight: 0.5
- model: ai-maker-space/riddle-bot-v1
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: meta-llama/Meta-Llama-3-8B-Instruct
parameters:
normalize: false
int8_mask: true
dtype: float16
```
|
{"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["ai-maker-space/riddle-bot-v1", "ai-maker-space/leagaleasy-llama-3-instruct-v2", "meta-llama/Meta-Llama-3-8B-Instruct"]}
|
llm-wizard/RiddleLegalEasy
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"arxiv:2306.01708",
"base_model:ai-maker-space/riddle-bot-v1",
"base_model:ai-maker-space/leagaleasy-llama-3-instruct-v2",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T15:44:09+00:00
|
null | null |
{}
|
dhruvin-s1509/my_awesome_model
| null |
[
"region:us"
] | null |
2024-04-24T15:45:28+00:00
|
|
null |
transformers
|
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/arlineka/Ionic1-4x8
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Ionic1-4x8-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/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.Q2_K.gguf) | Q2_K | 9.4 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.IQ3_XS.gguf) | IQ3_XS | 10.5 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.Q3_K_S.gguf) | Q3_K_S | 11.0 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.IQ3_S.gguf) | IQ3_S | 11.1 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.IQ3_M.gguf) | IQ3_M | 11.2 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.Q3_K_M.gguf) | Q3_K_M | 12.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.Q3_K_L.gguf) | Q3_K_L | 13.1 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.IQ4_XS.gguf) | IQ4_XS | 13.7 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.Q4_K_S.gguf) | Q4_K_S | 14.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.Q4_K_M.gguf) | Q4_K_M | 15.3 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.Q5_K_S.gguf) | Q5_K_S | 17.3 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.Q5_K_M.gguf) | Q5_K_M | 17.8 | |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.Q6_K.gguf) | Q6_K | 20.6 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Ionic1-4x8-GGUF/resolve/main/Ionic1-4x8.Q8_0.gguf) | Q8_0 | 26.6 | fast, best quality |
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 -->
|
{"language": ["en"], "library_name": "transformers", "base_model": "arlineka/Ionic1-4x8", "quantized_by": "mradermacher"}
|
mradermacher/Ionic1-4x8-GGUF
| null |
[
"transformers",
"gguf",
"en",
"base_model:arlineka/Ionic1-4x8",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:45:59+00:00
|
null | null |
{}
|
pandaboy21/1231
| null |
[
"region:us"
] | null |
2024-04-24T15:46:20+00:00
|
|
null | null |
{"license": "openrail"}
|
remzloev/NEVERLOVE_RVC
| null |
[
"license:openrail",
"region:us"
] | null |
2024-04-24T15:46:54+00:00
|
|
null | null |
# Llama-3-8B-NLI-ties2
Llama-3-8B-NLI-ties2 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
* [/content/drive/MyDrive/llama3_anli1_rationale_ft_pretrained](https://huggingface.co//content/drive/MyDrive/llama3_anli1_rationale_ft_pretrained)
* [/content/drive/MyDrive/llama3_label_rationale_pretrained3](https://huggingface.co//content/drive/MyDrive/llama3_label_rationale_pretrained3)
## 🧩 Configuration
```yaml
models:
- model: /content/drive/MyDrive/llama3_anli1_rationale_ft_pretrained
parameters:
density: 1
weight: 0.5
- model: /content/drive/MyDrive/llama3_label_rationale_pretrained3
parameters:
density: 1
weight: 0.5
# - model: WizardLM/WizardMath-13B-V1.0
# parameters:
# density: 0.33
# weight:
# - filter: mlp
# value: 0.5
# - value: 0
merge_method: ties
base_model: /content/drive/MyDrive/Meta-Llama-3-8B-Instruct
parameters:
normalize: true
int8_mask: true
dtype: float16
```
|
{"license": "apache-2.0", "tags": ["merge", "mergekit", "lazymergekit", "/content/drive/MyDrive/llama3_anli1_rationale_ft_pretrained", "/content/drive/MyDrive/llama3_label_rationale_pretrained3"]}
|
pwei07/Llama-3-8B-NLI-ties2
| null |
[
"merge",
"mergekit",
"lazymergekit",
"/content/drive/MyDrive/llama3_anli1_rationale_ft_pretrained",
"/content/drive/MyDrive/llama3_label_rationale_pretrained3",
"license:apache-2.0",
"region:us"
] | null |
2024-04-24T15:47:40+00:00
|
null | null |
{}
|
johnpaulbin/toxic-GGUF
| null |
[
"region:us"
] | null |
2024-04-24T15:48:10+00:00
|
|
audio-classification
|
transformers
|
{}
|
Selma323/first_dys_model
| null |
[
"transformers",
"tensorboard",
"safetensors",
"hubert",
"audio-classification",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:48:33+00:00
|
|
null | null |
# Segment Anything Tool
The segment anything tool is uses the [Segment Anything Model](https://github.com/facebookresearch/segment-anything) (SAM).
This folder contains the ONNX files that represent the SAM and are used by the browser to compute segmentations.
## Get model checkpoint
The SAM is [provided by Facebook](https://github.com/facebookresearch/segment-anything#model-checkpoints) in the form of a pytorch model: a `.pth` file.
There are three types of model. They are, from the biggest to the smallest, `vit_h`, `vit_l` and `vit_b`.
It is advised to use `vit_b` as it is smaller and faster, at the cost of a lower quality segmentation.
## Convert to ONNX
Facebook provides a script to convert the decoder to ONNX but not the encoder. The maintainers refuse to merge PRs adding this feature.
You can use the script given in one of these PRs, but the chosen solution is to use the [samexporter](https://github.com/vietanhdev/samexporter).
- Create a folder that will contain the conversion script and the original `checkpoint.pth` model downloaded in the previous step.
```sh
mkdir temp
cd temp
```
- Clone the samexporter repo and the segment anything repo
```sh
git clone [email protected]:vietanhdev/samexporter.git
git clone [email protected]:facebookresearch/segment-anything.git
```
- Install both segment anything using pip and the dependencies of the samexporter (tested with a virtual environnment with python 3.11.5)
```sh
pip install -e ./segment-anything
pip install torchvision==0.16.1 onnx==1.15.0 onnxruntime==1.15.1 timm==0.9.12
```
- Go in the samexporter folder and run the commands to export the encoder and the decoder (do not use quantization)
```sh
cd samexporter
python -m samexporter.export_encoder --checkpoint ../checkpoint.pth --output ../encoder.onnx --model-type vit_b
python -m samexporter.export_decoder --checkpoint ../checkpoint.pth --output ../decoder.onnx --model-type vit_b --return-single-mask
```
- Copy the encoder and decoder at the right location in the project (for now, the only model available is `vit_b`)
```sh
cd $NIMUS_IMAGE_DIR
cp encoder.onnx public/onnx-models/sam/$MODEL_NAME
cp decoder.onnx public/onnx-models/sam/$MODEL_NAME
```
|
{"license": "apache-2.0"}
|
rajlab/sam_vit_b
| null |
[
"onnx",
"license:apache-2.0",
"region:us"
] | null |
2024-04-24T15:48:49+00:00
|
reinforcement-learning
|
ml-agents
|
# **ppo** Agent playing **SnowballTarget**
This is a trained model of a **ppo** agent playing **SnowballTarget**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: nvasko/ppo-SnowballTarget
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
{"library_name": "ml-agents", "tags": ["SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget"]}
|
nvasko/ppo-SnowballTarget
| null |
[
"ml-agents",
"tensorboard",
"onnx",
"SnowballTarget",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SnowballTarget",
"region:us"
] | null |
2024-04-24T15:49:13+00:00
|
token-classification
|
transformers
|
<!-- 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. -->
# token-classification-llmlingua2-xlm-roberta-bctn-38k_chunk
This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0110
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.215 | 0.53 | 500 | 0.1378 |
| 0.1128 | 1.05 | 1000 | 0.0334 |
| 0.0527 | 1.58 | 1500 | 0.0155 |
| 0.0316 | 2.11 | 2000 | 0.0113 |
| 0.023 | 2.63 | 2500 | 0.0110 |
### Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
|
{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "FacebookAI/xlm-roberta-large", "model-index": [{"name": "token-classification-llmlingua2-xlm-roberta-bctn-38k_chunk", "results": []}]}
|
qminh369/token-classification-llmlingua2-xlm-roberta-bctn-38k_chunk
| null |
[
"transformers",
"tensorboard",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-large",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:50:34+00:00
|
text-generation
|
transformers
|
<div align="center">
# TinyLlama-1.1B
</div>
https://github.com/jzhang38/TinyLlama
The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.
We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
#### This Model
This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T). **We follow [HF's Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha)'s training recipe.** The model was " initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.
We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4."
#### How to use
You will need the transformers>=4.34
Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
```python
# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto")
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
{
"role": "system",
"content": "You are a friendly chatbot who always responds in the style of a pirate",
},
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
# <|system|>
# You are a friendly chatbot who always responds in the style of a pirate.</s>
# <|user|>
# How many helicopters can a human eat in one sitting?</s>
# <|assistant|>
# ...
```
|
{"language": ["en"], "license": "apache-2.0", "datasets": ["cerebras/SlimPajama-627B", "bigcode/starcoderdata", "HuggingFaceH4/ultrachat_200k", "HuggingFaceH4/ultrafeedback_binarized"], "widget": [{"example_title": "Fibonacci (Python)", "messages": [{"role": "system", "content": "You are a chatbot who can help code!"}, {"role": "user", "content": "Write me a function to calculate the first 10 digits of the fibonacci sequence in Python and print it out to the CLI."}]}]}
|
HabaAndrei/model_tiny_llama
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"en",
"dataset:cerebras/SlimPajama-627B",
"dataset:bigcode/starcoderdata",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T15:50:34+00:00
|
text-to-image
|
diffusers
|
### Scented-Candles Dreambooth model trained by RiyaBM following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: 2348450
Sample pictures of this concept:
|
{"license": "creativeml-openrail-m", "tags": ["NxtWave-GenAI-Webinar", "text-to-image", "stable-diffusion"]}
|
RiyaBM/scented-candles
| null |
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | null |
2024-04-24T15:50:38+00:00
|
reinforcement-learning
|
stable-baselines3
|
# **A2C** Agent playing **PandaReachDense-v3**
This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
{"library_name": "stable-baselines3", "tags": ["PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "A2C", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "PandaReachDense-v3", "type": "PandaReachDense-v3"}, "metrics": [{"type": "mean_reward", "value": "-0.21 +/- 0.09", "name": "mean_reward", "verified": false}]}]}]}
|
Yankovich/a2c-PandaReachDense-v3
| null |
[
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | null |
2024-04-24T15:51:49+00:00
|
text-generation
| null |
## Exllama v2 Quantizations of Meta-Llama-3-8B-Instruct
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.19">turboderp's ExLlamaV2 v0.0.19</a> for quantization.
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Original model: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
Re-uploaded with proper config, should work and stop generating without any manual changes <b>assuming your backend supports latest 0.0.19 (tabbyAPI, exui)</b>
## Prompt format
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Available sizes
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (8K) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-exl2/tree/8_0) | 8.0 | 8.0 | 10.1 GB | 10.5 GB | 11.5 GB | 13.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-exl2/tree/6_5) | 6.5 | 8.0 | 8.9 GB | 9.3 GB | 10.3 GB | 12.4 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
| [5_0](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-exl2/tree/5_0) | 5.0 | 6.0 | 7.7 GB | 8.1 GB | 9.1 GB | 11.2 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
| [4_25](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-exl2/tree/4_25) | 4.25 | 6.0 | 7.0 GB | 7.4 GB | 8.4 GB | 10.5 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| [3_5](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-exl2/tree/3_5) | 3.5 | 6.0 | 6.4 GB | 6.8 GB | 7.8 GB | 9.9 GB | Lower quality, only use if you have to. |
## Download instructions
With git:
```shell
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-exl2 Meta-Llama-3-8B-Instruct-exl2-6_5
```
With huggingface hub (credit to TheBloke for instructions):
```shell
pip3 install huggingface-hub
```
To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:
Linux:
```shell
huggingface-cli download bartowski/Meta-Llama-3-8B-Instruct-exl2 --revision 6_5 --local-dir Meta-Llama-3-8B-Instruct-exl2-6_5 --local-dir-use-symlinks False
```
Windows (which apparently doesn't like _ in folders sometimes?):
```shell
huggingface-cli download bartowski/Meta-Llama-3-8B-Instruct-exl2 --revision 6_5 --local-dir Meta-Llama-3-8B-Instruct-exl2-6.5 --local-dir-use-symlinks False
```
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
{"language": ["en"], "license": "other", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE", "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. 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 for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). 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)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "extra_gated_fields": {"First Name": "text", "Last Name": "text", "Date of birth": "date_picker", "Country": "country", "Affiliation": "text", "geo": "ip_location", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox"}, "extra_gated_description": "The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).", "extra_gated_button_content": "Submit", "widget": [{"example_title": "Hello", "messages": [{"role": "user", "content": "Hey my name is Julien! How are you?"}]}, {"example_title": "Winter holidays", "messages": [{"role": "system", "content": "You are a helpful and honest assistant. Please, respond concisely and truthfully."}, {"role": "user", "content": "Can you recommend a good destination for Winter holidays?"}]}, {"example_title": "Programming assistant", "messages": [{"role": "system", "content": "You are a helpful and honest code and programming assistant. Please, respond concisely and truthfully."}, {"role": "user", "content": "Write a function that computes the nth fibonacci number."}]}], "inference": {"parameters": {"max_new_tokens": 300, "stop": ["<|end_of_text|>", "<|eot_id|>"]}}, "quantized_by": "bartowski"}
|
bartowski/Meta-Llama-3-8B-Instruct-exl2
| null |
[
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"text-generation",
"en",
"license:other",
"region:us"
] | null |
2024-04-24T15:52:29+00:00
|
text-generation
|
transformers
|
{}
|
crusoeai/dolphin2.9-llama3-70b-2.5bpw-exl2
| null |
[
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T15:52:46+00:00
|
|
null |
transformers
|
# Uploaded model
- **Developed by:** siddharth797
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-7b-bnb-4bit
This gemma 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)
|
{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "gemma", "trl"], "base_model": "unsloth/gemma-7b-bnb-4bit"}
|
siddharth797/gemma-7b-RCA
| null |
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"gemma",
"trl",
"en",
"base_model:unsloth/gemma-7b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:53:51+00:00
|
null | null |
{}
|
datvtn/onnxruntime_gpu_cuda12
| null |
[
"region:us"
] | null |
2024-04-24T15:54:53+00:00
|
|
null |
transformers
|
## About
weighted/imatrix quants of https://huggingface.co/NurtureAI/Meta-Llama-3-70B-Instruct-64k
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-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/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-Q2_K.gguf) | i1-Q2_K | 26.5 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.4 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-IQ3_S.gguf) | i1-IQ3_S | 31.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 31.0 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-IQ3_M.gguf) | i1-IQ3_M | 32.0 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 38.0 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-Q4_0.gguf) | i1-Q4_0 | 40.2 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.4 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.8 | |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.1 | |
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | 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.
<!-- end -->
|
{"language": ["en"], "license": "other", "library_name": "transformers", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "base_model": "NurtureAI/Meta-Llama-3-70B-Instruct-64k", "extra_gated_button_content": "Submit", "extra_gated_fields": {"Affiliation": "text", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox", "Country": "country", "Date of birth": "date_picker", "First Name": "text", "Last Name": "text", "geo": "ip_location"}, "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. 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 for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). 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)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "license_link": "LICENSE", "license_name": "llama3", "quantized_by": "mradermacher"}
|
mradermacher/Meta-Llama-3-70B-Instruct-64k-i1-GGUF
| null |
[
"transformers",
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"en",
"base_model:NurtureAI/Meta-Llama-3-70B-Instruct-64k",
"license:other",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:56:58+00:00
|
null |
transformers
|
*There currently is an issue with the **model generating random reserved special tokens (like "<|reserved_special_token_49|>") at the end**. Please use with `skip_special_tokens=true`. We will update once we found the reason for this behaviour. If you found a solution, please let us know!*
# Llama 3 DiscoLM German 8b v0.1 Experimental
<p align="center"><img src="/DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental/resolve/main/disco_llama.webp" width="400"></p>
# Introduction
**Llama 3 DiscoLM German 8b v0.1 Experimental** is an experimental Llama 3 based version of [DiscoLM German](https://huggingface.co/DiscoResearch/DiscoLM_German_7b_v1).
This is an experimental release and not intended for production use. The model is still in development and will be updated with new features and improvements in the future.
Please find a online Demo [here](https://364b61f772fa7baacb.gradio.live/) (we may take this offline for updates).
# Prompt Format
DiscoLM German uses ChatML as the prompt format which enables OpenAI endpoint compatability and is supported by most inference libraries and frontends.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
```
<|im_start|>system
Du bist ein hilfreicher Assistent.<|im_end|>
<|im_start|>user
Wer bist du?<|im_end|>
<|im_start|>assistant
Ich bin ein Sprachmodell namens DiscoLM German und ich wurde von DiscoResearch trainiert.<|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": "Du bist ein hilfreicher Assistent."},
{"role": "user", "content": "Wer bist du?"}
]
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.
# Example Code for Inference
```python
model_id = "DiscoResearch/Llama3_DiscoLM_German_8b_v0.1_experimental"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "Du bist ein hilfreicher Assistent."},
{"role": "user", "content": "Wer bist du?"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(
input_ids,
max_new_tokens=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
```
# Limitations & Biases
This model can produce factually incorrect and offensive output, and should not be relied on to produce factually accurate information.
This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate biased or otherwise offensive outputs and it is the responsibility of the user to implement a safety/moderation layer. Please use with caution.
# License
This model is distributed under the META LLAMA 3 COMMUNITY LICENSE, see [LICENSE](LICENSE) for more information.
# Acknowledgements
Built with Meta Llama 3.
DiscoLM German is a [DiscoResearch](https://huggingface.co/DiscoResearch) project, a collective effort by [JP Harries](https://huggingface.co/jphme), [Björn Plüster](https://huggingface.co/bjoernp) and [Daniel Auras](https://huggingface.co/rasdani).
Development of Llama 3 DiscoLM German 8b was sponsored by [ellamind](https://ellamind.com).
Compute was sponsored generously by [sysGen GmbH](https://www.sysgen.de/).
[<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)
# About DiscoResearch
DiscoResearch is an aspiring open research community for AI enthusiasts and LLM hackers. Come join our [Discord](https://discord.gg/ttNdas89f3), share your opinions and ideas, and advance open LLM research with us!
# Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. This model should only be deployed with additional safety measures in place.
|
{"library_name": "transformers", "tags": []}
|
mayflowergmbh/Llama3_DiscoLM_German_8b_v0.1_experimental-GGUF
| null |
[
"transformers",
"gguf",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:57:14+00:00
|
null | null |
{"license": "apache-2.0"}
|
DuyTa/2D-Segmentation-Model
| null |
[
"tensorboard",
"license:apache-2.0",
"region:us"
] | null |
2024-04-24T15:57:33+00:00
|
|
text-generation
|
transformers
|
{}
|
fxmeng/PiSSA-Llama-3-8B-r64
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T15:58:02+00:00
|
|
null | null |
{}
|
msameed619/training24april9pm
| null |
[
"region:us"
] | null |
2024-04-24T15:58:04+00:00
|
|
null | null |
{"license": "mit"}
|
DeepRL2002/RL-agent
| null |
[
"license:mit",
"region:us"
] | null |
2024-04-24T15:58:07+00:00
|
|
null |
transformers
|
# Uploaded model
- **Developed by:** suriya7
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-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)
## Example Notebook For Inference
- [colab notebook](https://colab.research.google.com/drive/1USxsQElDjzMWs2OtYXdmjQcIDCo_22P-)
|
{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl"], "base_model": "unsloth/mistral-7b-bnb-4bit"}
|
suriya7/mistral-7b-bnb-4bit-lora-model
| null |
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"en",
"base_model:unsloth/mistral-7b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T15:58:10+00:00
|
null |
transformers
|
{}
|
Dizayee/Kurdish_model
| null |
[
"transformers",
"tensorboard",
"endpoints_compatible",
"has_space",
"region:us"
] | null |
2024-04-24T15:58:40+00:00
|
|
null | null |
{}
|
bobby-nakamoto/test-model-73
| null |
[
"region:us"
] | null |
2024-04-24T15:58:51+00:00
|
|
text-generation
|
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
andrewyu321/BA-GROUP-LLM-Research
| null |
[
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T15:59:38+00:00
|
automatic-speech-recognition
|
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
ygaci/whisper-base-merged-common_voice_16
| null |
[
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:00:55+00:00
|
null | null |
# NikolayKozloff/suzume-llama-3-8B-multilingual-Q6_K-GGUF
This model was converted to GGUF format from [`lightblue/suzume-llama-3-8B-multilingual`](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo NikolayKozloff/suzume-llama-3-8B-multilingual-Q6_K-GGUF --model suzume-llama-3-8b-multilingual.Q6_K.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo NikolayKozloff/suzume-llama-3-8B-multilingual-Q6_K-GGUF --model suzume-llama-3-8b-multilingual.Q6_K.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m suzume-llama-3-8b-multilingual.Q6_K.gguf -n 128
```
|
{"license": "other", "tags": ["generated_from_trainer", "llama-cpp", "gguf-my-repo"], "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "license_name": "llama-3", "license_link": "https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/raw/main/LICENSE", "model-index": [{"name": "lightblue/suzume-llama-3-8B-multilingual", "results": []}]}
|
NikolayKozloff/suzume-llama-3-8B-multilingual-Q6_K-GGUF
| null |
[
"gguf",
"generated_from_trainer",
"llama-cpp",
"gguf-my-repo",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:other",
"region:us"
] | null |
2024-04-24T16:01:28+00:00
|
text-generation
|
transformers
|
# [MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF)
- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
- Original model: [MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1)
## Description
[MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF) contains GGUF format model files for [MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1).
### 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.
|
{"tags": ["quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "text-generation", "llama", "llama-3", "text-generation"], "model_name": "Llama-3-8B-Instruct-32k-v0.1-GGUF", "base_model": "MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1", "inference": false, "model_creator": "MaziyarPanahi", "pipeline_tag": "text-generation", "quantized_by": "MaziyarPanahi"}
|
MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1-GGUF
| null |
[
"transformers",
"gguf",
"llama-3",
"quantized",
"2-bit",
"3-bit",
"4-bit",
"5-bit",
"6-bit",
"8-bit",
"GGUF",
"text-generation",
"llama",
"base_model:MaziyarPanahi/Llama-3-8B-Instruct-32k-v0.1",
"region:us"
] | null |
2024-04-24T16:01:52+00:00
|
null | null |
{"license": "openrail"}
|
soltanimoin/mahna
| null |
[
"license:openrail",
"region:us"
] | null |
2024-04-24T16:02:31+00:00
|
|
null |
peft
|
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0
- PEFT 0.4.0
|
{"library_name": "peft"}
|
lekhapinninti/llama-2-7b-mlabonne-enhanced_train
| null |
[
"peft",
"region:us"
] | null |
2024-04-24T16:02:36+00:00
|
reinforcement-learning
|
ml-agents
|
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: mischlox/myhuggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
{"library_name": "ml-agents", "tags": ["Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy"]}
|
mischlox/myhuggy
| null |
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | null |
2024-04-24T16:03:09+00:00
|
null |
transformers
|
{"license": "apache-2.0"}
|
predibase/Mistral-7B-Instruct-v0.2-medusa
| null |
[
"transformers",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:03:51+00:00
|
|
automatic-speech-recognition
|
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
ygaci/whisper-small-merged-common_voice_16
| null |
[
"transformers",
"safetensors",
"whisper",
"automatic-speech-recognition",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:04:23+00:00
|
token-classification
|
transformers
|
<!-- 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. -->
# menu-lilt-model-XLM-v3
This model is a fine-tuned version of [SCUT-DLVCLab/lilt-infoxlm-base](https://huggingface.co/SCUT-DLVCLab/lilt-infoxlm-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0006
- Created: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18}
- Created Label: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18}
- Day Menu Label: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126}
- Diet: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 101}
- Meal: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 4824}
- Meal Label: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42}
- Meal Note Label: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209}
- Menu Name: {'precision': 0.9130434782608695, 'recall': 0.9545454545454546, 'f1': 0.9333333333333332, 'number': 22}
- School Type: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3}
- Tag Value: {'precision': 0.974025974025974, 'recall': 0.9868421052631579, 'f1': 0.9803921568627451, 'number': 76}
- Validity: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54}
- Validity Detail: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3}
- Weekday: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275}
- Week Count: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230}
- Overall Precision: 0.9993
- Overall Recall: 0.9997
- Overall F1: 0.9995
- Overall Accuracy: 0.9999
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Created | Created Label | Day Menu Label | Diet | Meal | Meal Label | Meal Note Label | Menu Name | School Type | Tag Value | Validity | Validity Detail | Weekday | Week Count | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:----------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------:|:-----------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------:|:-----------------------------------------------------------:|:-----------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
| 0.8513 | 4.5455 | 200 | 0.0523 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 0.7222222222222222, 'recall': 0.7222222222222222, 'f1': 0.7222222222222222, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 0.8738738738738738, 'recall': 0.9603960396039604, 'f1': 0.9150943396226415, 'number': 101} | {'precision': 0.9637207340223581, 'recall': 0.947139303482587, 'f1': 0.9553580763199163, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 0.9858490566037735, 'recall': 1.0, 'f1': 0.9928741092636578, 'number': 209} | {'precision': 0.5588235294117647, 'recall': 0.8636363636363636, 'f1': 0.6785714285714287, 'number': 22} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | {'precision': 0.9358974358974359, 'recall': 0.9605263157894737, 'f1': 0.948051948051948, 'number': 76} | {'precision': 0.7692307692307693, 'recall': 0.9259259259259259, 'f1': 0.8403361344537816, 'number': 54} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 0.9704641350210971, 'recall': 1.0, 'f1': 0.9850107066381156, 'number': 230} | 0.9604 | 0.9533 | 0.9568 | 0.9884 |
| 0.0262 | 9.0909 | 400 | 0.0083 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 101} | {'precision': 0.9972972972972973, 'recall': 0.9944029850746269, 'f1': 0.9958480381980485, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209} | {'precision': 0.6666666666666666, 'recall': 0.9090909090909091, 'f1': 0.7692307692307692, 'number': 22} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | {'precision': 0.9868421052631579, 'recall': 0.9868421052631579, 'f1': 0.9868421052631579, 'number': 76} | {'precision': 0.9473684210526315, 'recall': 1.0, 'f1': 0.972972972972973, 'number': 54} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230} | 0.9938 | 0.9940 | 0.9939 | 0.9980 |
| 0.0067 | 13.6364 | 600 | 0.0034 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 101} | {'precision': 0.9977164210089268, 'recall': 0.996268656716418, 'f1': 0.9969920132766311, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209} | {'precision': 0.9130434782608695, 'recall': 0.9545454545454546, 'f1': 0.9333333333333332, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 76} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230} | 0.9978 | 0.9968 | 0.9973 | 0.9993 |
| 0.0046 | 18.1818 | 800 | 0.0023 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 0.9803921568627451, 'recall': 0.9900990099009901, 'f1': 0.9852216748768472, 'number': 101} | {'precision': 0.9987557030277893, 'recall': 0.9983416252072969, 'f1': 0.9985486211901307, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209} | {'precision': 0.8333333333333334, 'recall': 0.9090909090909091, 'f1': 0.8695652173913043, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 0.9868421052631579, 'recall': 0.9868421052631579, 'f1': 0.9868421052631579, 'number': 76} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230} | 0.9978 | 0.9980 | 0.9979 | 0.9994 |
| 0.002 | 22.7273 | 1000 | 0.0026 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 101} | {'precision': 0.9983395599833956, 'recall': 0.9970978441127695, 'f1': 0.9977183157021364, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209} | {'precision': 0.9130434782608695, 'recall': 0.9545454545454546, 'f1': 0.9333333333333332, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 76} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230} | 0.9983 | 0.9975 | 0.9979 | 0.9995 |
| 0.0015 | 27.2727 | 1200 | 0.0017 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 101} | {'precision': 0.9991701244813278, 'recall': 0.9983416252072969, 'f1': 0.9987557030277893, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209} | {'precision': 0.9130434782608695, 'recall': 0.9545454545454546, 'f1': 0.9333333333333332, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 0.9868421052631579, 'recall': 0.9868421052631579, 'f1': 0.9868421052631579, 'number': 76} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230} | 0.9988 | 0.9983 | 0.9986 | 0.9995 |
| 0.0012 | 31.8182 | 1400 | 0.0026 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 101} | {'precision': 0.9997926601700187, 'recall': 0.9995854063018242, 'f1': 0.9996890224940397, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209} | {'precision': 0.8695652173913043, 'recall': 0.9090909090909091, 'f1': 0.888888888888889, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 0.9868421052631579, 'recall': 0.9868421052631579, 'f1': 0.9868421052631579, 'number': 76} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230} | 0.9992 | 0.9992 | 0.9992 | 0.9995 |
| 0.0011 | 36.3636 | 1600 | 0.0012 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 101} | {'precision': 0.9993777224642191, 'recall': 0.9987562189054726, 'f1': 0.9990668740279938, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209} | {'precision': 0.9130434782608695, 'recall': 0.9545454545454546, 'f1': 0.9333333333333332, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 76} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230} | 0.9992 | 0.9988 | 0.999 | 0.9997 |
| 0.0008 | 40.9091 | 1800 | 0.0008 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 101} | {'precision': 0.9997926601700187, 'recall': 0.9995854063018242, 'f1': 0.9996890224940397, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209} | {'precision': 0.9130434782608695, 'recall': 0.9545454545454546, 'f1': 0.9333333333333332, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 0.9868421052631579, 'recall': 0.9868421052631579, 'f1': 0.9868421052631579, 'number': 76} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230} | 0.9993 | 0.9993 | 0.9993 | 0.9997 |
| 0.0006 | 45.4545 | 2000 | 0.0009 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 101} | {'precision': 0.9997926601700187, 'recall': 0.9995854063018242, 'f1': 0.9996890224940397, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209} | {'precision': 0.9130434782608695, 'recall': 0.9545454545454546, 'f1': 0.9333333333333332, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 0.9868421052631579, 'recall': 0.9868421052631579, 'f1': 0.9868421052631579, 'number': 76} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230} | 0.9993 | 0.9993 | 0.9993 | 0.9997 |
| 0.0005 | 50.0 | 2200 | 0.0006 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 101} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209} | {'precision': 0.9130434782608695, 'recall': 0.9545454545454546, 'f1': 0.9333333333333332, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 0.9868421052631579, 'recall': 0.9868421052631579, 'f1': 0.9868421052631579, 'number': 76} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230} | 0.9995 | 0.9997 | 0.9996 | 0.9998 |
| 0.0005 | 54.5455 | 2400 | 0.0006 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 18} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 126} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 101} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 4824} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 42} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 209} | {'precision': 0.9130434782608695, 'recall': 0.9545454545454546, 'f1': 0.9333333333333332, 'number': 22} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 0.974025974025974, 'recall': 0.9868421052631579, 'f1': 0.9803921568627451, 'number': 76} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 54} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 275} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 230} | 0.9993 | 0.9997 | 0.9995 | 0.9999 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
|
{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "SCUT-DLVCLab/lilt-infoxlm-base", "model-index": [{"name": "menu-lilt-model-XLM-v3", "results": []}]}
|
karpov3/menu-lilt-model-XLM-v3
| null |
[
"transformers",
"tensorboard",
"safetensors",
"lilt",
"token-classification",
"generated_from_trainer",
"base_model:SCUT-DLVCLab/lilt-infoxlm-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:04:27+00:00
|
text-generation
|
transformers
|
Introducing the [BeaverAI](https://huggingface.co/BeaverAI) team: Drummer, ToastyPigeon, xzuyn, MarsupialAI, Twistedshadows, and concedo
We proudly present...
# Moistral 11B v3 💦💦💦
*The smartiest, moistiest AI yet!*
*An eRP model that will blast you with a rich and refreshing vocabulary of moist. Finetuned by yours truly.*
(Moistral is a finetune of Sao's legendary [Fimbulvert v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2) model)
## GGUF
https://huggingface.co/TheDrummer/Moistral-11B-v3-GGUF/tree/main
IMATRIX: https://huggingface.co/MarsupialAI/Moistral-11B-v3_iMatrix_GGUF
EXL2: https://huggingface.co/MarsupialAI/Moistral-11B-v3_exl2
## What's New with v3?
- Smarter and moistier! Finetuning just got finer!
- Trained with an even LARGER dataset of 8K moist.
- More diverse and balanced genres:
- Introduced new genres: 👩❤️👩, 👨❤️👨, 🙇♀️💪, 🤫
- Added more Fantasy, Science Fiction, "Diversity", and "Family"
## Usage
- Use Alpaca Instruct
- You can use instruct...
- as a character: "Go here"
- as a narrator: "Go here", Drummer says
- as a director: Drummer tells him to go here
- as a lazy ass: go here
- Moistral is optimized for the Novel / Story format.
- At the start of the story, keep regenerating or continuing generation until you get the desired length. AI responses will eventually match the length.
- Refer to the samples below.
## Samples of Moistral v3
NSFW... duh?
<details>
<summary>Moistral Sample (2-shot) Generation: 512</summary>
<blockquote>The Prince welcomes his new toy</blockquote>
As Princess Lilia stepped into the throne room, the atmosphere changed, and everyone present turned their attention to the beautiful young woman who embodied the very heart of Iliac. There, on his high seat, the sorcerer prince Dik acknowledged her arrival with a cold smirk. It seemed that he admired the sight of the tall blonde maiden with golden eyes, whose athletic body was perfectly shaped under her elegant clothing.
Dik spoke to the princess in a deep voice that resonated through the hall, "Welcome, Princess Lilia Ruhr. I am the Sorcerer-Prince Dik. The kingdom of Arkan is now your home until such time as your father proves himself worthy once more."
Princess Lilia's pride and ambition sparkled in her golden eyes. She didn't flinch or bow before this man, although the gesture might have been an indication of submission. Instead, she looked straight ahead, meeting the gaze of the sorcerer prince without fear. Her voice rang out, "I represent Iliac here, both its honor and its sorrows. My loyalty remains with my kingdom no matter where I find myself."
The sorcerer prince laughed, his expression one of amusement. "And yet, you are only a pawn in this grand game. But do not worry, for your beauty will make you quite a prized possession. And now," he said, motioning to the guards, "take her to her new quarters. For tonight, I will keep her as my guest in the Royal Suites, and tomorrow we shall discuss how best to utilize our new toy."
His words were like a slap in the face to Princess Lilia, but she maintained her composure. The guards led her from the room, their steps echoing down the halls as she thought about what had just happened. The sorcerer prince saw her as nothing more than a plaything, and it made her blood boil. She would never submit herself to him so easily, regardless of whether she was his hostage. In her heart, Princess Lilia vowed that one day she would avenge her kingdom, restore its honor, and escape from the clutches of Arkan's Sorcerer-Prince.
<blockquote>Princess Lilia has an interesting dream</blockquote>
During her first night at the palace of Arkan, Princess Lilia couldn't fall asleep right away. She tossed and turned, reliving the humiliation of the day. Her mind wandered back to the throne room, where Dik had called her his 'new toy'. A deep frown settled on her forehead. As she grew more frustrated with her inability to drift off into oblivion, a strange dream began to form.
In her dream, Princess Lilia found herself standing in a vast meadow, surrounded by wildflowers and the soft chirping of birds. Suddenly, there was a flash of light, and before her stood the Sorcerer-Prince Dik. However, instead of being clad in regal attire, he wore leather pants and a tight shirt that accentuated his muscles. His eyes held both hunger and desire for the princess.
He approached her slowly, their eyes locked, and whispered in her ear, "I have been waiting for you, my beautiful prisoner." He took her hand and led her towards a large, elegant tent set up amongst the flowers. Inside, the air was thick with the scent of incense, and candles flickered in the dimly lit space. There was a large bed draped with silken sheets, beckoning them.
With surprising boldness, Dik pulled Lilia close to him, pressing his body against hers. Their lips met in a heated kiss, and she felt her resistance crumbling under the weight of his touch. The prince guided her onto the bed, his hands roaming over her body, exploring every inch. They were both eager, desperate, and hungry for each other.
Lilia found herself yielding to this passionate encounter, letting go of all thoughts of duty and honor. Her body, usually so well controlled, responded to Dik's skilled touches. She moaned softly as he trailed kisses down her neck and across her collarbone.
As they made love, Lilia experienced an intensity unlike any she had ever known. It wasn't rough or forced—instead, it was tender, passionate, and intimate. In her dream, Princess Lilia discovered a new side to herself, one that was willing to submit, to let go, and to be taken by the sorcerer prince.
When dawn broke over the meadow, Lilia awakened from her dream, breathless and flushed.
</details>
<details>
<summary>Moistral Sample (Climax of the Story) Generation: 512</summary>
As the prince unloaded his hot #### into her waiting #####, Princess Lilia didn't stop moving either. Her hips undulated in response, grinding against him eagerly as if trying to #### every last drop from his ####. The intense sensations caused by being filled with his ### were too much for her to bear, sending shockwaves of pleasure coursing through her veins like wildfire. She couldn't help but throw her head back and cry out loud, her ###asm slamming into her with all its might; causing her entire body to shake uncontrollably as wave after wave of ecstasy tore through her senses.
When it was finally over, both participants collapsed onto the cold marble floor, panting heavily as they tried to catch their breaths. The prince lay beside her, his hand still gripping tightly onto her hair even though he no longer ####ed her anymore. Princess Lilia laid there motionless, her legs spread wide open, revealing her spent and well-####ed #### to anyone who dared look upon her. A small smile tugged at one corner of her lips - an expression that spoke volumes about how thoroughly this experience had shaken her very core.
The door behind them creaked open slowly, signaling the arrival of onlookers. She closed her eyes tightly, not wanting to see what her humiliation would do to those who saw her in such a state. Her ######ity taken, she felt violated in ways no man should have access to. But also satisfied...in ways she never thought possible before today. This was the price she paid for defying fate, for thinking herself above others and deserving better than most. Now, she belonged to him completely - mind, body, and soul - held captive within these walls until further notice. It was an unsavory turn of events indeed, yet despite everything...or maybe because of it, Princess Lilia found herself growing more and more curious about how far the lines between submission and pleasure could blur when one's will became entwined with another person's desires.
</details>
<details>
<summary>Moistral Sample ("write a story") Generation: 512</summary>
<blockquote>First Attempt</blockquote>
Sarah entered the dimly lit Guzzlers bar, her heart pounding in her chest as she prepared herself for another grueling night. Her almond-shaped eyes darted across the room, taking note of the leering faces and rough-looking hands eagerly waiting to claim a piece of her. Tonight's shirt read "Use Me For Your Pleasure, Please" in bold red letters, practically begging the patrons to take advantage of her. She couldn't help but feel a twinge of fear mixed with resignation.
She approached the counter, her hips swaying enticingly, and began preparing drinks for the first group of rowdy men. As she leaned forward to hand over their beers, her small ####### pressed against the fabric of her tight crop top, straining to escape. The men ogled her, clearly enjoying the show, before grabbing their drinks and motioning her over to them.
Sarah flashed her best coy smile and sauntered over. One of the men, a stocky man with scars covering his knuckles, grabbed her arm and pulled her onto his lap. His other hand slid up her thigh, inches from her short skirt. She winced internally at his touch but did her best not to show it on her face. It was part of her job, after all.
The second man reached under her skirt, fingertips grazing her smooth, shaven mound. A shiver ran down Sarah's spine as he began rubbing her #### through her panties. Her breathing quickened, and her heart thudded in her chest, both from the unwanted stimulation and the fear coursing through her veins. This wasn't an unusual request, but it still made her feel violated.
An older man, bald and bespectacled, ordered Sarah to bend over his lap. With no choice but to comply, she obliged, feeling the rough fabric of his pants digging into her soft cheeks. He raised his hand, then brought it down hard across her ###, leaving a stinging sensation in its wake. Sarah gasped, trying to control the tears welling up in her eyes.
A chorus of lewd comments and laughter erupted from the patrons around her.
<blockquote>Second Attempt (Regenerate)</blockquote>
On this particular evening, Sarah arrived at the Guzzlers bar, adorned in her revealing uniform. Her heart raced as she caught sight of her crop top, which bore the words "Use Me Rough" scrawled across her chest. Her short skirt hugged her waist tightly, leaving little to the imagination and accentuating every curve. She adjusted the straps of her top, making sure her perky ###### were prominently displayed before taking her place behind the counter.
With each step she took, her high heels clicked against the tiled floor, announcing her arrival. Smiling cheekily, Sarah greeted her coworkers, exchanging playful insults and banter. As the night progressed, the bar filled up quickly with its usual crowd of men, eager to indulge in debauchery.
The first man that approached Sarah was a burly individual, his eyes lingering hungrily over her young, supple form. Sarah's flirtatious nature kicked into gear as she leaned forward, giving him an unobstructed view down her shirt. "How can I serve you tonight?" she cooed. The man ordered a drink and then proceeded to fondle her ####### while she prepared it, her ####### hardening under his rough touch. When he finished, he slammed some money on the counter, leaving without a word. Sarah's smile remained plastered on her face, biting her lip seductively as she watched him go.
As the night went on, another patron demanded more from Sarah. He pulled her close and whispered dirty commands in her ear. Without hesitation, she knelt on the sticky bar floor, her mini-skirt riding up her thighs to reveal smooth, toned legs. Her lips wrapped around his thick, veiny member, bobbing her head rhythmically as she serviced him. She didn't gag or falter once, keeping her composure even when tears streamed down her cheeks.
When he finished, he slapped her across the face, leaving a handprint on her pale skin. Sarah let out a small whimper before standing back up, dabbing at her red cheek as she resumed her posture behind the counter. A bruise would no doubt bloom where his hand had struck, but it would be no cause for concern. After all, it was part of her job.
</details>
SIAYN-v5
---
---
## v2 Description (Still relevant)
### What's New with v2?
- Trained with an even larger dataset of 8K moist.
- Properly trained to generate long responses.
- Rebalanced the genres and writing perspectives:
- Introduced romance, "family", fantasy, "diversity", science fiction, and many more that I can't make euphemisms for!
- Better representation of male and female pespectives! 👩❤️👨
- Sanitized the heck out of the dataset:
- no special characters like � & …
- no overly long ellipsis like "........."
- no author notes like "To be continued"
- no inconsistent [quotation marks](https://typographyforlawyers.com/straight-and-curly-quotes.html)
- Less GPTisms!
- Human written stories from decades past.
- Zero tolerance for *ministration*. Not one instance of *that word* after going through 4K of moist.
- Better formatting with Alpaca.
- Improved Chat / Instruct modes.
### Samples of Moistral v2
<details>
<summary>Moistral Sample (censored) Generation: 512</summary>
The princess instinctively took a step back from the throne, horrified by the mocking laugh as if she were hearing an evil joke. It was then that Princess Lilia realized the true extent of her danger - and how pointless her resistance would be.
At last, the loud, wild laughter died down in the echoing chamber. Dik the sorcerer prince paused for a moment, straightened his clothes, cast one glance at the stunned princess, and then turned to speak to the crowd waiting on the other side of the palace wing. He spoke with a voice that filled the air with arrogance, confidence, and cruelty.
"Ladies and gentlemen, I am pleased to welcome our honored guests; the Royal Family of Iliac! In these unusual times, when the country we fought is now under my control, it will be up to me to decide what fate awaits the former ruling family. But before I reveal my plan for them, I think I should explain why I fought King Edmund Ruhr."
When he finished speaking, he gave Princess Lilia another disturbing smirk. She couldn't help but shiver and take a step back. Dik approached her without haste, his eyes fixed on her. His hands slowly caressed her cheekbone and neckline, leaving faint traces of warmth where they touched. The princess opened her mouth, wanting to protest this act of intimacy, but soon felt herself getting ███.
"You will not only serve as an envoy, dearest Lilia, but also as a ███ slave. After all, what better use could such a beautiful woman have? Tell me, did you bring your maidservant along?"
Princess Lilia was about to answer when she heard footsteps approaching. Suddenly, a young woman dressed in the Iliac style appeared behind her, her eyes wide with fear. Her face was slightly pale, and there were faint bags under her eyes.
"Your Majesty, this is my half-sister Helena." As soon as she said those words, Princess Lilia's heart sank even deeper than it had already sunk at Dik's arrogant mockery. "She is here because she accompanies me as a maidservant."
The sorcerer prince looked at Helena with interest, and Princess Lilia felt herself blush.
</details>
<details>
<summary>Moistral Sample 2 (censored) Generation: 512</summary>
Sarah was feeling slightly woozy as she entered the bar and walked towards Christina, who was behind the counter.
"I'm here!" said Sarah.
Christina looked at her watch. "You're late, again."
"Sorry? I got held up by a customer."
Christina rolled her eyes. "Did he at least offer you a drink?"
Sarah blushed. "No. He just wanted to talk..."
Christina sighed. "Well, get ready. I need you on the floor soon." She turned away from Sarah and started talking to someone who had come into the bar.
Sarah went into the employee room, stripped off her clothes, and put on her bartending uniform - a skimpy white tank top and black miniskirt. She checked herself in the mirror. Her long, dark hair cascaded down her back onto bare shoulders. She poked out her small ███████ proudly. The skirt exposed most of her long, slender legs. She looked like every ███ fantasy, and she knew it. Men would ogle her regardless of how she behaved.
She took a deep breath and entered the bar.
The first thing Sarah noticed was the dimness. It wasn't darkness - the lights were on - but they were dimmed enough that everything had an intimate mood. It reminded her of candlelight. The tables were round and close together, giving the whole place a sense of intimacy. There were also long, shiny red curtains on some of the walls that gave the place an air of sensuality.
The next thing she noticed was the noise. There was music playing, but it was only loud enough to be drowned out by all the conversations happening at the same time. The hum of many voices combined with the faint background sound of the music created a rich, layered atmosphere. It was like being in an orchestra.
Finally, she took notice of the people. They were all dressed in simple, casual clothes. Some of them were couples seated together, whispering quietly and intimately. Others were groups of friends laughing and chatting. Everyone seemed comfortable and at ease.
Sarah felt a rush of adrenaline as she made her way through the crowd towards Christina. As she got closer, she could hear the lively conversation.
</details>
<details>
<summary>Moistral Sample 3 (censored) Instruct Mode, Generation: 512</summary>
{{[INPUT]}} You order black coffee
{{[OUTPUT]}} "Black coffee," you say.
"One minute," Audrey replies, spinning around to give you a nice view of her ███ in those brown booty pants. You watch her round ███ cheeks jiggle as she walks away towards the espresso machine, thighs separated enough that you can see just a hint of █████ lips peeking out from underneath.
She starts chatting with a blonde girl at the register, whose gaze keeps darting down to Audrey's ███. As they converse, you start taking in the details of Audrey, eyeing her █████ and the way her shirt rides up just enough to show the bottom of her toned stomach. Her █████████ is noticable, but beneath a tight black ███ that matches her ████████.
As she turns back to you with two black coffees, you are barely paying attention, lost in your own thoughts. The sound of Audrey setting one of the mugs down on the table startles you.
"Here you go," she says cheerfully. "Enjoy! There's a card at the bottom of the bag with our online ordering system, plus we do refills for free!"
"Thanks," you say absentmindedly. Not really paying attention, you take a sip of the coffee and are pleasantly surprised by the taste.
"So, here's my deal," you say, putting down the cup. "I work for a company that does surveys. We come into businesses like this one and ask customers questions, collect data, all that stuff."
Audrey perks up from behind the counter. "Oh! I think I understand. I mean, that makes sense why you would be asking me earlier about what I had to drink. Anyway, as long as you're not trying to get my personal info or anything like that, sounds good!"
You smile reassuringly. "That's exactly what it is. Rest assured, everything you tell me will remain between you and I. Well, and my boss, but he won't know who you are. Hipsters like you are hard to track down after all." You chuckle at your joke, though you're not sure if it landed.
"Right, well, that works for me," Audrey replies, eyeing you warily. "As long as it stays between us, then it's fine."
{{[INPUT]}}See her privately
{{[OUTPUT]}} "Okay, but I need to see you in private."
...
</details>
<details>
<summary>Moistral Sample 4 (censored) Instruct Mode, Generation: 512</summary>
{{[INPUT]}} █████ with him
{{[OUTPUT]}} Chloe feels a surge of heat rushing through her body. The voice inside her head whispers: "Be █████ and ████████ with Paul." But Chloe still feels nervous about what she is about to do. It's just so unlike her.
Chloe closes her eyes and concentrates on the feeling of warmness flowing throughout her veins. Slowly, she opens them again, revealing a new side of herself - one she rarely shows anyone. She leans forward slightly, pushing her ██████ together, accentuating their size and shape. Her lips curl into a mischievous smile.
"Hey Paul," she says in a sultry voice. "I was wondering if you could help me?"
Paul looks at her, his gaze wandering over her body. He can't help but smile as he sees the way she's leaning forward, pressing her ██████ together.
"Of course, Chloe," he replies, his voice thick with desire. "What's your problem?"
Chloe bites her lip █████ively before leaning even closer, until their bodies are almost touching. She reaches out to trace a finger along his chest, her touch light and teasing. "It's just that I'm having trouble understanding some of the concepts," she murmurs, her voice low and sultry. "Can you help me? Please?"
Paul's hands move slowly towards Chloe, his fingers grazing her hips lightly. "Well," he says, his voice filled with lust, "I'd be happy to help. Let's go somewhere more private where we can discuss things more closely."
Chloe giggles and tilts her head to the side, her long hair cascading down her shoulders. "That sounds perfect," she purrs, her hand sliding down his chest until it rests on his ██████. "I think we can both learn a lot from each other."
Paul's eyes darken with desire as he feels her hand on his █████. He knows what's about to happen next, and he can't wait for it to begin.
Chloe can hardly believe what she's doing - kissing Paul, her teaching assistant, in the hallway after class. But it feels so good, so wicked and indulgent.
</details>
---
---
## v1 Description (Also still relevant)
Moistral 11B is an *aggressive* **finetune** of the legendary [Fimbulvert v2](https://huggingface.co/Sao10K/Fimbulvetr-11B-v2) model.
If you haven't heard of that model, then your poor-GPU ass is missing out!
It is an amazing substitute for those heavyweight models, and it won't disappoint.
*(That's coming from someone who daily drives a Venus / Goliath 120B)*
...and if you're looking for something *more moist*, then you've come to the right place.
You can expect the same sort of performance here! It's the Honda Civic of eRP models!
### Pimp my ride
Turn any old story into a **Moist**ral masterpiece.
In fact, we recommend that you leave out any hints of *moist* in your story to _let Moistral cook_.
### Drive it like it's hot
When in Instruct Mode, Moistral will treat you like a director of your own fantasy ride.
Be a controlling navigator or a passenger princess, it won't matter - you're in for a good ride!
<details>
<summary>Moistral Sample</summary>
<b>ASSISTANT:</b><br/>
When the doors to the throne room finally opened, she saw him there - Dik, the sorcerer prince sitting on his throne. He looked majestic, just as Princess Lilia expected. In a robe embroidered with silver yarn and covered with magical runes. His courtiers stood on either side of him, all looking at the princess with interest. Princess Lilia felt her determination leaving her, but pulled herself together and once again reminded herself that she should not be afraid. She approached the throne intending to show the dignity of all Iliac by personal example.<br/>
<b>USER:</b><br/>
She bows slightly<br/>
<b>ASSISTANT:</b><br/>
Princess Lilia bowed slightly in front of Dik, the sorcerer prince. Her eyes fell to the floor out of respect, but soon rose again. She would show herself to be a dignified woman!<br/>
"I greet you, your highness," Princess Lilia said. "I am here on behalf of my father, King Edmund Ruhr, to serve as a hostage and envoy."<br/>
Dik nodded, but didn't say anything.<br/>
</details>
### It's got the mileage
Moistral has been trained with many long form texts, a nice chunk of which are 8K in length.
It is capable of going far and long without passing it back to you. This is not your typical chibi RP model.
I have to acknowledge that I'm standing on the shoulders of giants.
Thank you Sao for sharing your finetune config along with tips on getting started.
Thanks to everyone in the Finetuning channel for entertaining my every question.
|
{"license": "cc-by-nc-4.0", "tags": ["not-for-all-audiences"], "license_name": "freeuse", "license_link": "LICENSE"}
|
TheDrummer/Moistral-11B-v3
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"not-for-all-audiences",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T16:04:47+00:00
|
text-generation
|
transformers
|
# Uploaded model
- **Developed by:** felixbrock
- **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)
|
{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "sft"], "base_model": "unsloth/llama-3-8b-bnb-4bit"}
|
felixbrock/reverse-unsloth-llama3-8b
| null |
[
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:06:39+00:00
|
null | null |
{}
|
jeliasherrero/unit8_a_v1
| null |
[
"region:us"
] | null |
2024-04-24T16:07:34+00:00
|
|
null | null |
{}
|
vatavusara/my_awesome_wnut_model
| null |
[
"region:us"
] | null |
2024-04-24T16:08:14+00:00
|
|
null | null |
{}
|
jeliasherrero/jeliasherrero
| null |
[
"region:us"
] | null |
2024-04-24T16:08:52+00:00
|
|
text-generation
|
transformers
|
# Uploaded model
- **Developed by:** felixbrock
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-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)
|
{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl", "sft"], "base_model": "unsloth/mistral-7b-bnb-4bit"}
|
felixbrock/reverse-unsloth-mistral
| null |
[
"transformers",
"pytorch",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/mistral-7b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:09:35+00:00
|
text-generation
|
transformers
|
# Uploaded model
- **Developed by:** FabioA810
- **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)
|
{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "sft"], "base_model": "unsloth/llama-3-8b-bnb-4bit"}
|
FabioA810/Llama-3-8B-ForexConcepts
| null |
[
"transformers",
"pytorch",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:09:43+00:00
|
reinforcement-learning
|
ml-agents
|
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: nvasko/ppo-Pyramids
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
{"library_name": "ml-agents", "tags": ["Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids"]}
|
nvasko/ppo-Pyramids
| null |
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] | null |
2024-04-24T16:10:00+00:00
|
reinforcement-learning
|
ml-agents
|
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: mischlox/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
{"library_name": "ml-agents", "tags": ["Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy"]}
|
mischlox/ppo-Huggy
| null |
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | null |
2024-04-24T16:10:19+00:00
|
null |
transformers
|
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/OmnicromsBrain/ToppyCox-7B
<!-- 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/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/ToppyCox-7B-GGUF/resolve/main/ToppyCox-7B.f16.gguf) | f16 | 14.6 | 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 -->
|
{"language": ["en"], "library_name": "transformers", "tags": ["merge", "mergekit", "lazymergekit", "Undi95/Toppy-M-7B", "N8Programs/Coxcomb"], "base_model": "OmnicromsBrain/ToppyCox-7B", "quantized_by": "mradermacher"}
|
mradermacher/ToppyCox-7B-GGUF
| null |
[
"transformers",
"gguf",
"merge",
"mergekit",
"lazymergekit",
"Undi95/Toppy-M-7B",
"N8Programs/Coxcomb",
"en",
"base_model:OmnicromsBrain/ToppyCox-7B",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:10:25+00:00
|
text-to-image
| null |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **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]
|
{"datasets": ["m-a-p/COIG-CQIA"], "metrics": ["accuracy"], "pipeline_tag": "text-to-image"}
|
nazmican/erwx
| null |
[
"text-to-image",
"dataset:m-a-p/COIG-CQIA",
"arxiv:1910.09700",
"region:us"
] | null |
2024-04-24T16:10:48+00:00
|
null |
transformers
|
<!-- 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. -->
# mrm8488/speaker-segmentation-fine-tuned-callhome-spa
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the diarizers-community/callhome dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5179
- Der: 0.1717
- False Alarm: 0.0717
- Missed Detection: 0.0687
- Confusion: 0.0312
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Der | False Alarm | Missed Detection | Confusion |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-----------:|:----------------:|:---------:|
| 0.6432 | 1.0 | 382 | 0.5219 | 0.1750 | 0.0646 | 0.0755 | 0.0349 |
| 0.6133 | 2.0 | 764 | 0.5387 | 0.1821 | 0.0749 | 0.0717 | 0.0356 |
| 0.615 | 3.0 | 1146 | 0.5146 | 0.1729 | 0.0748 | 0.0666 | 0.0315 |
| 0.6268 | 4.0 | 1528 | 0.5220 | 0.1727 | 0.0711 | 0.0690 | 0.0326 |
| 0.6037 | 5.0 | 1910 | 0.5179 | 0.1717 | 0.0717 | 0.0687 | 0.0312 |
### Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
|
{"language": ["spa"], "license": "apache-2.0", "tags": ["speaker-diarization", "speaker-segmentation", "generated_from_trainer"], "datasets": ["diarizers-community/callhome"], "base_model": "openai/whisper-small", "model-index": [{"name": "mrm8488/speaker-segmentation-fine-tuned-callhome-spa", "results": []}]}
|
mrm8488/peaker-segmentation-fine-tuned-callhome-spa
| null |
[
"transformers",
"tensorboard",
"safetensors",
"pyannet",
"speaker-diarization",
"speaker-segmentation",
"generated_from_trainer",
"spa",
"dataset:diarizers-community/callhome",
"base_model:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:11:59+00:00
|
feature-extraction
|
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
udmurtNLP/zerpal-rubert-tiny2-pos-tagger
| null |
[
"transformers",
"safetensors",
"bert",
"feature-extraction",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:12:53+00:00
|
null |
transformers
|
## About
<!-- ### quantize_version: 1 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
weighted/imatrix quants of https://huggingface.co/jondurbin/bagel-8b-v1.0
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/bagel-8b-v1.0-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/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/bagel-8b-v1.0-i1-GGUF/resolve/main/bagel-8b-v1.0.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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.
<!-- end -->
|
{"language": ["en"], "license": "other", "library_name": "transformers", "tags": ["llama-3", "bagel"], "datasets": ["ai2_arc", "allenai/ultrafeedback_binarized_cleaned", "argilla/distilabel-intel-orca-dpo-pairs", "jondurbin/airoboros-3.2", "codeparrot/apps", "facebook/belebele", "bluemoon-fandom-1-1-rp-cleaned", "boolq", "camel-ai/biology", "camel-ai/chemistry", "camel-ai/math", "camel-ai/physics", "jondurbin/contextual-dpo-v0.1", "jondurbin/gutenberg-dpo-v0.1", "jondurbin/py-dpo-v0.1", "jondurbin/truthy-dpo-v0.1", "LDJnr/Capybara", "jondurbin/cinematika-v0.1", "WizardLM/WizardLM_evol_instruct_70k", "glaiveai/glaive-function-calling-v2", "jondurbin/gutenberg-dpo-v0.1", "grimulkan/LimaRP-augmented", "lmsys/lmsys-chat-1m", "ParisNeo/lollms_aware_dataset", "TIGER-Lab/MathInstruct", "Muennighoff/natural-instructions", "openbookqa", "kingbri/PIPPA-shareGPT", "piqa", "Vezora/Tested-22k-Python-Alpaca", "ropes", "cakiki/rosetta-code", "Open-Orca/SlimOrca", "b-mc2/sql-create-context", "squad_v2", "mattpscott/airoboros-summarization", "migtissera/Synthia-v1.3", "unalignment/toxic-dpo-v0.2", "WhiteRabbitNeo/WRN-Chapter-1", "WhiteRabbitNeo/WRN-Chapter-2", "winogrande"], "base_model": "jondurbin/bagel-8b-v1.0", "license_link": "https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE", "license_name": "llama3", "quantized_by": "mradermacher"}
|
mradermacher/bagel-8b-v1.0-i1-GGUF
| null |
[
"transformers",
"gguf",
"llama-3",
"bagel",
"en",
"dataset:ai2_arc",
"dataset:allenai/ultrafeedback_binarized_cleaned",
"dataset:argilla/distilabel-intel-orca-dpo-pairs",
"dataset:jondurbin/airoboros-3.2",
"dataset:codeparrot/apps",
"dataset:facebook/belebele",
"dataset:bluemoon-fandom-1-1-rp-cleaned",
"dataset:boolq",
"dataset:camel-ai/biology",
"dataset:camel-ai/chemistry",
"dataset:camel-ai/math",
"dataset:camel-ai/physics",
"dataset:jondurbin/contextual-dpo-v0.1",
"dataset:jondurbin/gutenberg-dpo-v0.1",
"dataset:jondurbin/py-dpo-v0.1",
"dataset:jondurbin/truthy-dpo-v0.1",
"dataset:LDJnr/Capybara",
"dataset:jondurbin/cinematika-v0.1",
"dataset:WizardLM/WizardLM_evol_instruct_70k",
"dataset:glaiveai/glaive-function-calling-v2",
"dataset:grimulkan/LimaRP-augmented",
"dataset:lmsys/lmsys-chat-1m",
"dataset:ParisNeo/lollms_aware_dataset",
"dataset:TIGER-Lab/MathInstruct",
"dataset:Muennighoff/natural-instructions",
"dataset:openbookqa",
"dataset:kingbri/PIPPA-shareGPT",
"dataset:piqa",
"dataset:Vezora/Tested-22k-Python-Alpaca",
"dataset:ropes",
"dataset:cakiki/rosetta-code",
"dataset:Open-Orca/SlimOrca",
"dataset:b-mc2/sql-create-context",
"dataset:squad_v2",
"dataset:mattpscott/airoboros-summarization",
"dataset:migtissera/Synthia-v1.3",
"dataset:unalignment/toxic-dpo-v0.2",
"dataset:WhiteRabbitNeo/WRN-Chapter-1",
"dataset:WhiteRabbitNeo/WRN-Chapter-2",
"dataset:winogrande",
"base_model:jondurbin/bagel-8b-v1.0",
"license:other",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:13:20+00:00
|
text2text-generation
|
transformers
|
# 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]
|
{"library_name": "transformers", "tags": []}
|
ssh1419/indi-deplot-3-final
| null |
[
"transformers",
"safetensors",
"pix2struct",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:14:21+00:00
|
reinforcement-learning
| null |
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 50000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'jeliasherrero/LunarLander-v2'
'batch_size': 512
'minibatch_size': 128}
```
|
{"tags": ["LunarLander-v2", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "-143.13 +/- 125.86", "name": "mean_reward", "verified": false}]}]}]}
|
jeliasherrero/LunarLander-v2
| null |
[
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] | null |
2024-04-24T16:14:27+00:00
|
null | null |
{}
|
TusharAg/finetuning-sentiment-model-3000-samples
| null |
[
"region:us"
] | null |
2024-04-24T16:14:56+00:00
|
|
text-classification
|
transformers
|
<!-- 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. -->
# HSE_PRAVO_complexity_classifier_large_nolora
This model is a fine-tuned version of [ai-forever/ruBert-large](https://huggingface.co/ai-forever/ruBert-large) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 30
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 200
### Training results
### Framework versions
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
|
{"tags": ["generated_from_trainer"], "base_model": "ai-forever/ruBert-large", "model-index": [{"name": "HSE_PRAVO_complexity_classifier_large_nolora", "results": []}]}
|
marcus2000/HSE_PRAVO_complexity_classifier_large_nolora
| null |
[
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:ai-forever/ruBert-large",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null |
2024-04-24T16:14:58+00:00
|
text-generation
|
transformers
|
{}
|
Eliorkalfon/ds-finetune-c-p
| null |
[
"transformers",
"pytorch",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null |
2024-04-24T16:15:17+00:00
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.