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
sequencelengths 1
1.84k
| sha
null | created_at
stringlengths 25
25
|
|---|---|---|---|---|---|---|---|---|
null | null | {} | Seokhyun1/tinyllava-v2x-single | null | [
"region:us"
] | null | 2024-05-01T00:59:22+00:00 |
|
text-to-image | diffusers |
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# SDXL LoRA DreamBooth - embracellm/sushi15_LoRA
<Gallery />
## Model description
These are embracellm/sushi15_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Trigger words
You should use a photo of Salmon Avocado Roll to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](embracellm/sushi15_LoRA/tree/main) them in the Files & versions tab.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] | {"license": "openrail++", "library_name": "diffusers", "tags": ["text-to-image", "text-to-image", "diffusers-training", "diffusers", "dora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "instance_prompt": "a photo of Salmon Avocado Roll", "widget": []} | embracellm/sushi15_LoRA | null | [
"diffusers",
"tensorboard",
"text-to-image",
"diffusers-training",
"dora",
"template:sd-lora",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] | null | 2024-05-01T00:59:29+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. -->
# tinyllama-1.1b-sum-sft-qlora
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the martimfasantos/openai-tldr-filtered dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1466
## 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: 0.0004
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.1383 | 1.0 | 1351 | 2.1541 |
| 2.1135 | 2.0 | 2702 | 2.1466 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "apache-2.0", "library_name": "peft", "tags": ["alignment-handbook", "trl", "sft", "generated_from_trainer"], "datasets": ["martimfasantos/openai-tldr-filtered"], "base_model": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T", "model-index": [{"name": "tinyllama-1.1b-sum-sft-qlora", "results": []}]} | martimfasantos/tinyllama-1.1b-sum-sft-qlora | null | [
"peft",
"tensorboard",
"safetensors",
"llama",
"alignment-handbook",
"trl",
"sft",
"generated_from_trainer",
"dataset:martimfasantos/openai-tldr-filtered",
"base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
"license:apache-2.0",
"4-bit",
"region:us"
] | null | 2024-05-01T01:01:07+00:00 |
text-generation | transformers | 
# flammen22X-mistral-7B
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [nbeerbower/flammen22C-mistral-7B](https://huggingface.co/nbeerbower/flammen22C-mistral-7B) as a base.
### Models Merged
The following models were included in the merge:
* [KatyTheCutie/LemonadeRP-4.5.3](https://huggingface.co/KatyTheCutie/LemonadeRP-4.5.3)
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
* [ChaoticNeutrals/Nyanade_Stunna-Maid-7B-v0.2](https://huggingface.co/ChaoticNeutrals/Nyanade_Stunna-Maid-7B-v0.2)
* [flammenai/flammen18X-mistral-7B](https://huggingface.co/flammenai/flammen18X-mistral-7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: flammenai/flammen18X-mistral-7B
- model: ChaoticNeutrals/Nyanade_Stunna-Maid-7B-v0.2
- model: KatyTheCutie/LemonadeRP-4.5.3
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B
merge_method: model_stock
base_model: nbeerbower/flammen22C-mistral-7B
dtype: bfloat16
```
| {"license": "apache-2.0", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["nbeerbower/flammen22C-mistral-7B", "KatyTheCutie/LemonadeRP-4.5.3", "SanjiWatsuki/Kunoichi-DPO-v2-7B", "ChaoticNeutrals/Nyanade_Stunna-Maid-7B-v0.2", "flammenai/flammen18X-mistral-7B"]} | flammenai/flammen22X-mistral-7B | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2403.19522",
"base_model:nbeerbower/flammen22C-mistral-7B",
"base_model:KatyTheCutie/LemonadeRP-4.5.3",
"base_model:SanjiWatsuki/Kunoichi-DPO-v2-7B",
"base_model:ChaoticNeutrals/Nyanade_Stunna-Maid-7B-v0.2",
"base_model:flammenai/flammen18X-mistral-7B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T01:01:40+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]
| {"license": "mit", "library_name": "transformers", "tags": []} | shramay-palta/test-demo-t5_base-qa | null | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T01:05:57+00:00 |
text-generation | transformers | {} | ImagineIt/dont-use-broken | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T01:11:36+00:00 |
|
null | null | {} | WALIDALI/walidAnimescape | null | [
"region:us"
] | null | 2024-05-01T01:12:42+00:00 |
|
text-generation | transformers |
# Uploaded model
- **Developed by:** katharsis
- **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"} | katharsis/llama3-8b-oig-unsloth-merged-necromunda | 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 | 2024-05-01T01:13:09+00:00 |
null | null | # TinyDolphin-2.8-1.1b
## Requisitos
Para usar este modelo, necesitas tener instalado llama.cpp en tu equipo. Puedes obtener llama.cpp desde el siguiente repositorio:
- [Repositorio de llama.cpp](https://github.com/ggerganov/llama.cpp)
Para instalar llama.cpp, sigue estos pasos:
```bash
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
make
```
## Uso del modelo
La plantilla del modelo es la siguiente:
```plaintext
"<|im_start|>system\nYou are Dolphin, a helpful AI assistant.<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
```
Puedes utilizar el modelo en llama.cpp con el siguiente comando:
```bash
./main -m ggml-model-Q8_0.gguf -p ""<|im_start|>system\nYou are Dolphin, a helpful AI assistant.<|im_end|>\n<|im_start|>user\nHi!<|im_end|>\n<|im_start|>assistant"" --log-disable
```
LM Studio config-presets
Filename:tinydolphin.preset.json
```json
{
"name": "TinyDolphin 2.8",
"inference_params": {
"input_prefix": "<|im_start|>user\n",
"input_suffix": "<|im_end|>\n<|im_start|>assistant\n",
"antiprompt": [
"<|im_start|>user\n",
"<|im_end|>\n<|im_start|>assistant"
],
"pre_prompt": "<|im_start|>system\nYou are Dolphin, a helpful AI assistant.<|im_end|>",
"pre_prompt_prefix": "",
"pre_prompt_suffix": ""
},
"load_params": {
"rope_freq_scale": 0,
"rope_freq_base": 0
}
}
```
## Referencias
- [Repositorio original](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b)
- [Repositorio de llama.cpp](https://github.com/ggerganov/llama.cpp) | {"language": ["en"], "tags": ["gguf", "llama.cpp", "tinydolphin", "tiny"]} | HirCoir/TinyDolphin-2.8-1.1b-GGUF | null | [
"gguf",
"llama.cpp",
"tinydolphin",
"tiny",
"en",
"region:us"
] | null | 2024-05-01T01:17:02+00:00 |
text-generation | transformers |
INTERM STEP VERSION:
Step 1 in trying to make Tiefighter 32,768 context.
This version is not usable in current form.
Step 2 however (a linear remerge of Tiefighter with this merge) is however working.
GGUFs are also working... at 32768 context.
Step 2 is here: [DavidAU/D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp](DavidAU/D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp)
# D_AU-Tiefighter-Giraffe-13B-32k-slerp
D_AU-Tiefighter-Giraffe-13B-32k-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [KoboldAI/LLaMA2-13B-Tiefighter](https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter)
* [abacusai/Giraffe-13b-32k-v3](https://huggingface.co/abacusai/Giraffe-13b-32k-v3)
## 🧩 Configuration
```yaml
slices:
- sources:
- model: KoboldAI/LLaMA2-13B-Tiefighter
layer_range: [0, 40]
- model: abacusai/Giraffe-13b-32k-v3
layer_range: [0, 40]
merge_method: slerp
base_model: abacusai/Giraffe-13b-32k-v3
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` | {"tags": ["merge", "mergekit", "lazymergekit", "KoboldAI/LLaMA2-13B-Tiefighter", "abacusai/Giraffe-13b-32k-v3"], "base_model": ["KoboldAI/LLaMA2-13B-Tiefighter", "abacusai/Giraffe-13b-32k-v3"]} | DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"KoboldAI/LLaMA2-13B-Tiefighter",
"abacusai/Giraffe-13b-32k-v3",
"base_model:KoboldAI/LLaMA2-13B-Tiefighter",
"base_model:abacusai/Giraffe-13b-32k-v3",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T01:18:03+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** katharsis
- **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"} | katharsis/llama3-8b-oig-unsloth-necromunda | 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 | 2024-05-01T01:18:04+00:00 |
null | transformers | {} | magnifi/llama-cls-ner-mt-chat-v21-2_epoch_24-ct2b | null | [
"transformers",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T01:18:16+00:00 |
|
null | null | {} | TristanSylvain/Vincent-Ropion | null | [
"region:us"
] | null | 2024-05-01T01:18:31+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": []} | claudios/plbart-c-cpp-defect-detection | null | [
"transformers",
"safetensors",
"plbart",
"feature-extraction",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T01:18:36+00:00 |
null | transformers | {} | dangvohiep/wikit5-v2 | null | [
"transformers",
"safetensors",
"t5",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T01:18:48+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. -->
# opt-125m-finetuned-mnli-mm
This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7598
- Accuracy: 0.4952
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 1 | 0.7366 | 0.4926 |
| No log | 2.0 | 2 | 0.7388 | 0.5004 |
| No log | 3.0 | 3 | 0.7405 | 0.5053 |
| No log | 4.0 | 4 | 0.7420 | 0.5072 |
| No log | 5.0 | 5 | 0.7433 | 0.5104 |
| No log | 6.0 | 6 | 0.7445 | 0.5104 |
| No log | 7.0 | 7 | 0.7456 | 0.5108 |
| No log | 8.0 | 8 | 0.7464 | 0.5125 |
| No log | 9.0 | 9 | 0.7469 | 0.5135 |
| No log | 10.0 | 10 | 0.7470 | 0.5131 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "other", "library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "facebook/opt-125m", "model-index": [{"name": "opt-125m-finetuned-mnli-mm", "results": []}]} | elliottfitzgerald/opt-125m-finetuned-mnli-mm | null | [
"peft",
"tensorboard",
"safetensors",
"opt",
"generated_from_trainer",
"base_model:facebook/opt-125m",
"license:other",
"region:us"
] | null | 2024-05-01T01:22:02+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": []} | claudios/codebert-base | null | [
"transformers",
"safetensors",
"roberta",
"feature-extraction",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T01:22:14+00:00 |
null | null | {"license": "openrail"} | sadeghboghi/videotest | null | [
"license:openrail",
"region:us"
] | null | 2024-05-01T01:23:47+00:00 |
|
null | null | <!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<a href="https://www.pruna.ai/" target="_blank" rel="noopener noreferrer">
<img src="https://i.imgur.com/eDAlcgk.png" alt="PrunaAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</a>
</div>
<!-- header end -->
[](https://twitter.com/PrunaAI)
[](https://github.com/PrunaAI)
[](https://www.linkedin.com/company/93832878/admin/feed/posts/?feedType=following)
[](https://discord.com/invite/vb6SmA3hxu)
## This repo contains GGUF versions of the bigcode/starcoder2-15b-instruct-v0.1 model.
# Simply make AI models cheaper, smaller, faster, and greener!
- Give a thumbs up if you like this model!
- Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
- Request access to easily compress your *own* AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
- Read the documentations to know more [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/)
- Join Pruna AI community on Discord [here](https://discord.com/invite/vb6SmA3hxu) to share feedback/suggestions or get help.
**Frequently Asked Questions**
- ***How does the compression work?*** The model is compressed with GGUF.
- ***How does the model quality change?*** The quality of the model output might vary compared to the base model.
- ***What is the model format?*** We use GGUF format.
- ***What calibration data has been used?*** If needed by the compression method, we used WikiText as the calibration data.
- ***How to compress my own models?*** You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
# Downloading and running the models
You can download the individual files from the Files & versions section. Here is a list of the different versions we provide. For more info checkout [this chart](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) and [this guide](https://www.reddit.com/r/LocalLLaMA/comments/1ba55rj/overview_of_gguf_quantization_methods/):
| Quant type | Description |
|------------|--------------------------------------------------------------------------------------------|
| Q5_K_M | High quality, recommended. |
| Q5_K_S | High quality, recommended. |
| Q4_K_M | Good quality, uses about 4.83 bits per weight, recommended. |
| Q4_K_S | Slightly lower quality with more space savings, recommended. |
| IQ4_NL | Decent quality, slightly smaller than Q4_K_S with similar performance, recommended. |
| IQ4_XS | Decent quality, smaller than Q4_K_S with similar performance, recommended. |
| Q3_K_L | Lower quality but usable, good for low RAM availability. |
| Q3_K_M | Even lower quality. |
| IQ3_M | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| IQ3_S | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
| Q3_K_S | Low quality, not recommended. |
| IQ3_XS | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| Q2_K | Very low quality but surprisingly usable. |
## How to download GGUF files ?
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
- **Option A** - Downloading in `text-generation-webui`:
- **Step 1**: Under Download Model, you can enter the model repo: PrunaAI/starcoder2-15b-instruct-v0.1-GGUF-smashed and below it, a specific filename to download, such as: phi-2.IQ3_M.gguf.
- **Step 2**: Then click Download.
- **Option B** - Downloading on the command line (including multiple files at once):
- **Step 1**: We recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
- **Step 2**: Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download PrunaAI/starcoder2-15b-instruct-v0.1-GGUF-smashed starcoder2-15b-instruct-v0.1.IQ3_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
Alternatively, you can also download multiple files at once with a pattern:
```shell
huggingface-cli download PrunaAI/starcoder2-15b-instruct-v0.1-GGUF-smashed --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download PrunaAI/starcoder2-15b-instruct-v0.1-GGUF-smashed starcoder2-15b-instruct-v0.1.IQ3_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## How to run model in GGUF format?
- **Option A** - Introductory example with `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m starcoder2-15b-instruct-v0.1.IQ3_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<s>[INST] {prompt\} [/INST]"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
- **Option B** - Running in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20-%20Model%20Tab.md#llamacpp).
- **Option C** - Running from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python
from llama_cpp import Llama
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = Llama(
model_path="./starcoder2-15b-instruct-v0.1.IQ3_M.gguf", # Download the model file first
n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"<s>[INST] {prompt} [/INST]", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./starcoder2-15b-instruct-v0.1.IQ3_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
```
- **Option D** - Running with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
## Configurations
The configuration info are in `smash_config.json`.
## Credits & License
The license of the smashed model follows the license of the original model. Please check the license of the original model before using this model which provided the base model. The license of the `pruna-engine` is [here](https://pypi.org/project/pruna-engine/) on Pypi.
## Want to compress other models?
- Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
- Request access to easily compress your own AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
| {"tags": ["pruna-ai"], "metrics": ["memory_disk", "memory_inference", "inference_latency", "inference_throughput", "inference_CO2_emissions", "inference_energy_consumption"], "thumbnail": "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"} | PrunaAI/starcoder2-15b-instruct-v0.1-GGUF-smashed | null | [
"gguf",
"pruna-ai",
"region:us"
] | null | 2024-05-01T01:23:56+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": []} | claudios/codebert-base-mlm | null | [
"transformers",
"safetensors",
"roberta",
"feature-extraction",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T01:25:44+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]
- **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]
### Framework versions
- PEFT 0.10.0 | {"library_name": "peft", "base_model": "unsloth/llama-3-70b-Instruct-bnb-4bit"} | ImagineIt/dont-use-broken-lora | null | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:unsloth/llama-3-70b-Instruct-bnb-4bit",
"region:us"
] | null | 2024-05-01T01:25:56+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": []} | salangarica/BioMistral-LLM | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T01:26:16+00:00 |
null | null | {"license": "openrail++"} | EthanRhys/Charmy-Bee-Current | null | [
"license:openrail++",
"region:us"
] | null | 2024-05-01T01:26:48+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. -->
# opt-350m-finetuned-mnli
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2789
- Accuracy: 0.5235
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 1 | 1.4105 | 0.4852 |
| No log | 2.0 | 2 | 1.1544 | 0.5132 |
| No log | 3.0 | 3 | 1.2071 | 0.5163 |
| No log | 4.0 | 4 | 1.0910 | 0.5094 |
| No log | 5.0 | 5 | 1.1394 | 0.5154 |
| No log | 6.0 | 6 | 1.1741 | 0.5185 |
| No log | 7.0 | 7 | 1.2318 | 0.5199 |
| No log | 8.0 | 8 | 1.2789 | 0.5235 |
| No log | 9.0 | 9 | 1.3077 | 0.5211 |
| No log | 10.0 | 10 | 1.3205 | 0.5202 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "other", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "facebook/opt-350m", "model-index": [{"name": "opt-350m-finetuned-mnli", "results": []}]} | elliottfitzgerald/opt-350m-finetuned-mnli | null | [
"transformers",
"tensorboard",
"safetensors",
"opt",
"text-classification",
"generated_from_trainer",
"base_model:facebook/opt-350m",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T01:27:53+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": []} | claudios/longcoder-base | null | [
"transformers",
"safetensors",
"longformer",
"feature-extraction",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T01:29:17+00:00 |
null | null | # TinyLlama-1.1B-Chat-v1.0
## Requisitos
Para usar este modelo, necesitas tener instalado llama.cpp en tu equipo. Puedes obtener llama.cpp desde el siguiente repositorio:
- [Repositorio de llama.cpp](https://github.com/ggerganov/llama.cpp)
Para instalar llama.cpp, sigue estos pasos:
```bash
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
make
```
## Uso del modelo
La plantilla del modelo es la siguiente:
```plaintext
<|system|>\nAnswer user questions</s>\n<|user|>\n{prompt}</s>\n<|assistant|>
```
Puedes utilizar el modelo en llama.cpp con el siguiente comando:
```bash
./main -m ggml-model-Q8_0.gguf -p "<|system|>\nAnswer user questions</s>\n<|user|>\nHi</s>\n<|assistant|>" --log-disable
```
LM Studio config-presets
Filename:tinyllamachat.preset.json
```json
{
"name": "TinyLlama Chat",
"inference_params": {
"input_prefix": "<|user|>\n",
"input_suffix": "</s>\n<|assistant|>\n",
"antiprompt": [
"<|user|>\n",
"</s>\n<|assistant|>\n"
],
"pre_prompt": "<|system|>\nAnswer user questions</s>",
"pre_prompt_prefix": "",
"pre_prompt_suffix": ""
},
"load_params": {
"rope_freq_scale": 0,
"rope_freq_base": 0
}
}
```
## Referencias
- [Repositorio original](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
- [Repositorio de llama.cpp](https://github.com/ggerganov/llama.cpp) | {"language": ["en"], "tags": ["gguf", "llama.cpp", "tiny", "tinyllama"]} | HirCoir/TinyLlama-1.1B-Chat-v1.0-GGUF | null | [
"gguf",
"llama.cpp",
"tiny",
"tinyllama",
"en",
"region:us"
] | null | 2024-05-01T01:33:02+00:00 |
null | 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:** Mahi
- **Model type:** chatbot
- **Language(s) (NLP):** pyton
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** https://huggingface.co/MaheshwariDantuluri/MIS340
- **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] | {} | MaheshwariDantuluri/MIS340 | null | [
"arxiv:1910.09700",
"region:us"
] | null | 2024-05-01T01:33:34+00:00 |
null | null | {} | amboulchouk/test_dom | null | [
"region:us"
] | null | 2024-05-01T01:36:54+00:00 |
|
null | null | {} | anushkat/DistilGPT2-Beatles-Spotify-model-Final | null | [
"safetensors",
"region:us"
] | null | 2024-05-01T01:37:52+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": []} | zesquirrelnator/moondream-finetune | null | [
"transformers",
"safetensors",
"moondream1",
"text-generation",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"region:us"
] | null | 2024-05-01T01:41:22+00:00 |
null | null |
This model has been pushed to the Hub using ****:
- Repo: [More Information Needed]
- Docs: [More Information Needed] | {"tags": ["pytorch_model_hub_mixin", "model_hub_mixin"]} | sebastiansarasti/stack_over_flow | null | [
"safetensors",
"pytorch_model_hub_mixin",
"model_hub_mixin",
"region:us"
] | null | 2024-05-01T01:41:42+00:00 |
null | null | {} | io0/animation.gif | null | [
"region:us"
] | null | 2024-05-01T01:44:19+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]
| {"license": "mit", "library_name": "transformers", "tags": []} | shramay-palta/test-demo-t5-small-qa | null | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"arxiv:1910.09700",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T01:46:05+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": []} | jski/OrpoLlama-3-8B | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T01:48:08+00:00 |
null | null | {"license": "openrail"} | kyubbae/Kyuhyun | null | [
"license:openrail",
"region:us"
] | null | 2024-05-01T01:51:39+00:00 |
|
null | null | {} | Ksgk-fy/Zaligner-v1-test1 | null | [
"tensorboard",
"safetensors",
"region:us"
] | null | 2024-05-01T01:51:55+00:00 |
|
null | null | {} | Geddez/Comp3161_Final_Assignment | null | [
"region:us"
] | null | 2024-05-01T01:51:55+00:00 |
|
null | null | {} | anushkat/DistilGPT2-Beatles-Spotify-Final | null | [
"safetensors",
"region:us"
] | null | 2024-05-01T01:56:40+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-small_MOE_chinese_max2000_b8
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2929
- Wer: 8.3078
## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- training_steps: 2000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.5563 | 1.0204 | 100 | 0.6041 | 12.0499 |
| 0.1815 | 2.0408 | 200 | 0.2631 | 13.5326 |
| 0.076 | 3.0612 | 300 | 0.2622 | 14.3563 |
| 0.0418 | 4.0816 | 400 | 0.2556 | 13.5797 |
| 0.0206 | 5.1020 | 500 | 0.2600 | 8.8962 |
| 0.0178 | 6.1224 | 600 | 0.2651 | 8.9668 |
| 0.0071 | 7.1429 | 700 | 0.2685 | 8.3784 |
| 0.0038 | 8.1633 | 800 | 0.2712 | 8.4961 |
| 0.0051 | 9.1837 | 900 | 0.2769 | 8.0725 |
| 0.0031 | 10.2041 | 1000 | 0.2770 | 8.0960 |
| 0.0018 | 11.2245 | 1100 | 0.2829 | 8.2608 |
| 0.0015 | 12.2449 | 1200 | 0.2779 | 8.3078 |
| 0.0009 | 13.2653 | 1300 | 0.2794 | 8.1666 |
| 0.0017 | 14.2857 | 1400 | 0.2863 | 8.4961 |
| 0.0003 | 15.3061 | 1500 | 0.2907 | 8.3314 |
| 0.0007 | 16.3265 | 1600 | 0.2895 | 8.1666 |
| 0.0003 | 17.3469 | 1700 | 0.2912 | 8.6373 |
| 0.0003 | 18.3673 | 1800 | 0.2915 | 8.2608 |
| 0.0004 | 19.3878 | 1900 | 0.2927 | 8.2843 |
| 0.0004 | 20.4082 | 2000 | 0.2929 | 8.3078 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["wer"], "base_model": "openai/whisper-small", "model-index": [{"name": "whisper-small_MOE_chinese_max2000_b8", "results": []}]} | racheltong/whisper-small_MOE_chinese_max2000_b8 | null | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"base_model:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T01:57:07+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** PythonCreate
- **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"} | PythonCreate/my_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 | 2024-05-01T01:57:21+00:00 |
text-generation | transformers |
# Dolphin 2.9 Mixtral 8x22b 🐬
Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations
Discord: https://discord.gg/8fbBeC7ZGx
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
My appreciation for the sponsors of Dolphin 2.9:
- [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 8xH100 node
This model is based on Dolphin-2.9-Mixtral-8x22b, and is Apache-2.0 licensed.
The base model has 64k context, and the full-weight fine-tuning was with 4k sequence length.
It took 1 week on 8xH100 provided by Crusoe Cloud
This model was trained FFT on 50% parameters (targeted with [Laser Scanner](https://github.com/cognitivecomputations/laserRMT/blob/main/laser_scanner.py) by Fernando Fernandes, David Golchinfar, Lucas Atkins, and Eric Hartford) , using ChatML prompt template format.
example:
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.
Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
Dolphin is licensed Apache 2.0. I grant permission for any use, including commercial, that falls within accordance with Apache-2.0 license. Dolphin was trained on data generated from GPT4, among other models.
## Evals
## Training
[<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)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.0`
```yaml
base_model: mistral-community/Mixtral-8x22B-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true
load_in_8bit: false
load_in_4bit: false
strict: false
unfrozen_parameters:
- ^lm_head.weight$
- ^model.embed_tokens.weight$
- model.layers.0.self_attn.q_proj
- model.layers.1.self_attn.q_proj
- model.layers.2.self_attn.q_proj
- model.layers.22.self_attn.q_proj
- model.layers.27.self_attn.q_proj
- model.layers.28.self_attn.q_proj
- model.layers.13.self_attn.q_proj
- model.layers.21.self_attn.q_proj
- model.layers.24.self_attn.q_proj
- model.layers.14.self_attn.q_proj
- model.layers.15.self_attn.q_proj
- model.layers.11.self_attn.q_proj
- model.layers.20.self_attn.q_proj
- model.layers.23.self_attn.q_proj
- model.layers.30.self_attn.k_proj
- model.layers.31.self_attn.k_proj
- model.layers.25.self_attn.k_proj
- model.layers.23.self_attn.k_proj
- model.layers.27.self_attn.k_proj
- model.layers.26.self_attn.k_proj
- model.layers.29.self_attn.k_proj
- model.layers.28.self_attn.k_proj
- model.layers.24.self_attn.k_proj
- model.layers.16.self_attn.k_proj
- model.layers.19.self_attn.k_proj
- model.layers.22.self_attn.k_proj
- model.layers.20.self_attn.k_proj
- model.layers.6.self_attn.k_proj
- model.layers.22.self_attn.v_proj
- model.layers.29.self_attn.v_proj
- model.layers.31.self_attn.v_proj
- model.layers.5.self_attn.v_proj
- model.layers.8.self_attn.v_proj
- model.layers.4.self_attn.v_proj
- model.layers.25.self_attn.v_proj
- model.layers.30.self_attn.v_proj
- model.layers.17.self_attn.v_proj
- model.layers.23.self_attn.v_proj
- model.layers.28.self_attn.v_proj
- model.layers.9.self_attn.v_proj
- model.layers.26.self_attn.v_proj
- model.layers.27.self_attn.v_proj
- model.layers.20.self_attn.o_proj
- model.layers.19.self_attn.o_proj
- model.layers.16.self_attn.o_proj
- model.layers.13.self_attn.o_proj
- model.layers.18.self_attn.o_proj
- model.layers.17.self_attn.o_proj
- model.layers.12.self_attn.o_proj
- model.layers.15.self_attn.o_proj
- model.layers.14.self_attn.o_proj
- model.layers.22.self_attn.o_proj
- model.layers.23.self_attn.o_proj
- model.layers.21.self_attn.o_proj
- model.layers.10.self_attn.o_proj
- model.layers.0.self_attn.o_proj
- model.layers.0.block_sparse_moe.experts.0.w1
- model.layers.1.block_sparse_moe.experts.0.w1
- model.layers.2.block_sparse_moe.experts.0.w1
- model.layers.3.block_sparse_moe.experts.0.w1
- model.layers.4.block_sparse_moe.experts.0.w1
- model.layers.5.block_sparse_moe.experts.0.w1
- model.layers.6.block_sparse_moe.experts.0.w1
- model.layers.7.block_sparse_moe.experts.0.w1
- model.layers.8.block_sparse_moe.experts.0.w1
- model.layers.9.block_sparse_moe.experts.0.w1
- model.layers.10.block_sparse_moe.experts.0.w1
- model.layers.11.block_sparse_moe.experts.0.w1
- model.layers.12.block_sparse_moe.experts.0.w1
- model.layers.13.block_sparse_moe.experts.0.w1
- model.layers.0.block_sparse_moe.experts.0.w2
- model.layers.1.block_sparse_moe.experts.0.w2
- model.layers.2.block_sparse_moe.experts.0.w2
- model.layers.3.block_sparse_moe.experts.0.w2
- model.layers.4.block_sparse_moe.experts.0.w2
- model.layers.5.block_sparse_moe.experts.0.w2
- model.layers.6.block_sparse_moe.experts.0.w2
- model.layers.7.block_sparse_moe.experts.0.w2
- model.layers.8.block_sparse_moe.experts.0.w2
- model.layers.9.block_sparse_moe.experts.0.w2
- model.layers.10.block_sparse_moe.experts.0.w2
- model.layers.11.block_sparse_moe.experts.0.w2
- model.layers.12.block_sparse_moe.experts.0.w2
- model.layers.13.block_sparse_moe.experts.0.w2
- model.layers.0.block_sparse_moe.experts.0.w3
- model.layers.1.block_sparse_moe.experts.0.w3
- model.layers.2.block_sparse_moe.experts.0.w3
- model.layers.3.block_sparse_moe.experts.0.w3
- model.layers.4.block_sparse_moe.experts.0.w3
- model.layers.5.block_sparse_moe.experts.0.w3
- model.layers.6.block_sparse_moe.experts.0.w3
- model.layers.7.block_sparse_moe.experts.0.w3
- model.layers.8.block_sparse_moe.experts.0.w3
- model.layers.9.block_sparse_moe.experts.0.w3
- model.layers.10.block_sparse_moe.experts.0.w3
- model.layers.11.block_sparse_moe.experts.0.w3
- model.layers.12.block_sparse_moe.experts.0.w3
- model.layers.13.block_sparse_moe.experts.0.w3
- model.layers.0.block_sparse_moe.experts.1.w1
- model.layers.1.block_sparse_moe.experts.1.w1
- model.layers.2.block_sparse_moe.experts.1.w1
- model.layers.3.block_sparse_moe.experts.1.w1
- model.layers.4.block_sparse_moe.experts.1.w1
- model.layers.5.block_sparse_moe.experts.1.w1
- model.layers.6.block_sparse_moe.experts.1.w1
- model.layers.7.block_sparse_moe.experts.1.w1
- model.layers.8.block_sparse_moe.experts.1.w1
- model.layers.9.block_sparse_moe.experts.1.w1
- model.layers.10.block_sparse_moe.experts.1.w1
- model.layers.11.block_sparse_moe.experts.1.w1
- model.layers.12.block_sparse_moe.experts.1.w1
- model.layers.13.block_sparse_moe.experts.1.w1
- model.layers.40.block_sparse_moe.experts.1.w2
- model.layers.0.block_sparse_moe.experts.1.w2
- model.layers.1.block_sparse_moe.experts.1.w2
- model.layers.2.block_sparse_moe.experts.1.w2
- model.layers.3.block_sparse_moe.experts.1.w2
- model.layers.4.block_sparse_moe.experts.1.w2
- model.layers.5.block_sparse_moe.experts.1.w2
- model.layers.6.block_sparse_moe.experts.1.w2
- model.layers.7.block_sparse_moe.experts.1.w2
- model.layers.8.block_sparse_moe.experts.1.w2
- model.layers.9.block_sparse_moe.experts.1.w2
- model.layers.10.block_sparse_moe.experts.1.w2
- model.layers.11.block_sparse_moe.experts.1.w2
- model.layers.12.block_sparse_moe.experts.1.w2
- model.layers.5.block_sparse_moe.experts.1.w3
- model.layers.0.block_sparse_moe.experts.1.w3
- model.layers.1.block_sparse_moe.experts.1.w3
- model.layers.2.block_sparse_moe.experts.1.w3
- model.layers.3.block_sparse_moe.experts.1.w3
- model.layers.4.block_sparse_moe.experts.1.w3
- model.layers.6.block_sparse_moe.experts.1.w3
- model.layers.7.block_sparse_moe.experts.1.w3
- model.layers.8.block_sparse_moe.experts.1.w3
- model.layers.9.block_sparse_moe.experts.1.w3
- model.layers.10.block_sparse_moe.experts.1.w3
- model.layers.11.block_sparse_moe.experts.1.w3
- model.layers.12.block_sparse_moe.experts.1.w3
- model.layers.13.block_sparse_moe.experts.1.w3
- model.layers.1.block_sparse_moe.experts.2.w1
- model.layers.0.block_sparse_moe.experts.2.w1
- model.layers.2.block_sparse_moe.experts.2.w1
- model.layers.3.block_sparse_moe.experts.2.w1
- model.layers.4.block_sparse_moe.experts.2.w1
- model.layers.5.block_sparse_moe.experts.2.w1
- model.layers.6.block_sparse_moe.experts.2.w1
- model.layers.7.block_sparse_moe.experts.2.w1
- model.layers.8.block_sparse_moe.experts.2.w1
- model.layers.9.block_sparse_moe.experts.2.w1
- model.layers.10.block_sparse_moe.experts.2.w1
- model.layers.11.block_sparse_moe.experts.2.w1
- model.layers.12.block_sparse_moe.experts.2.w1
- model.layers.13.block_sparse_moe.experts.2.w1
- model.layers.1.block_sparse_moe.experts.2.w2
- model.layers.0.block_sparse_moe.experts.2.w2
- model.layers.2.block_sparse_moe.experts.2.w2
- model.layers.3.block_sparse_moe.experts.2.w2
- model.layers.4.block_sparse_moe.experts.2.w2
- model.layers.5.block_sparse_moe.experts.2.w2
- model.layers.6.block_sparse_moe.experts.2.w2
- model.layers.7.block_sparse_moe.experts.2.w2
- model.layers.8.block_sparse_moe.experts.2.w2
- model.layers.9.block_sparse_moe.experts.2.w2
- model.layers.10.block_sparse_moe.experts.2.w2
- model.layers.11.block_sparse_moe.experts.2.w2
- model.layers.12.block_sparse_moe.experts.2.w2
- model.layers.13.block_sparse_moe.experts.2.w2
- model.layers.1.block_sparse_moe.experts.2.w3
- model.layers.0.block_sparse_moe.experts.2.w3
- model.layers.2.block_sparse_moe.experts.2.w3
- model.layers.3.block_sparse_moe.experts.2.w3
- model.layers.4.block_sparse_moe.experts.2.w3
- model.layers.5.block_sparse_moe.experts.2.w3
- model.layers.6.block_sparse_moe.experts.2.w3
- model.layers.7.block_sparse_moe.experts.2.w3
- model.layers.8.block_sparse_moe.experts.2.w3
- model.layers.9.block_sparse_moe.experts.2.w3
- model.layers.10.block_sparse_moe.experts.2.w3
- model.layers.11.block_sparse_moe.experts.2.w3
- model.layers.12.block_sparse_moe.experts.2.w3
- model.layers.13.block_sparse_moe.experts.2.w3
- model.layers.2.block_sparse_moe.experts.3.w1
- model.layers.1.block_sparse_moe.experts.3.w1
- model.layers.0.block_sparse_moe.experts.3.w1
- model.layers.3.block_sparse_moe.experts.3.w1
- model.layers.4.block_sparse_moe.experts.3.w1
- model.layers.5.block_sparse_moe.experts.3.w1
- model.layers.6.block_sparse_moe.experts.3.w1
- model.layers.7.block_sparse_moe.experts.3.w1
- model.layers.8.block_sparse_moe.experts.3.w1
- model.layers.9.block_sparse_moe.experts.3.w1
- model.layers.10.block_sparse_moe.experts.3.w1
- model.layers.11.block_sparse_moe.experts.3.w1
- model.layers.12.block_sparse_moe.experts.3.w1
- model.layers.13.block_sparse_moe.experts.3.w1
- model.layers.2.block_sparse_moe.experts.3.w2
- model.layers.1.block_sparse_moe.experts.3.w2
- model.layers.0.block_sparse_moe.experts.3.w2
- model.layers.3.block_sparse_moe.experts.3.w2
- model.layers.4.block_sparse_moe.experts.3.w2
- model.layers.5.block_sparse_moe.experts.3.w2
- model.layers.6.block_sparse_moe.experts.3.w2
- model.layers.7.block_sparse_moe.experts.3.w2
- model.layers.8.block_sparse_moe.experts.3.w2
- model.layers.9.block_sparse_moe.experts.3.w2
- model.layers.10.block_sparse_moe.experts.3.w2
- model.layers.11.block_sparse_moe.experts.3.w2
- model.layers.12.block_sparse_moe.experts.3.w2
- model.layers.13.block_sparse_moe.experts.3.w2
- model.layers.2.block_sparse_moe.experts.3.w3
- model.layers.1.block_sparse_moe.experts.3.w3
- model.layers.0.block_sparse_moe.experts.3.w3
- model.layers.3.block_sparse_moe.experts.3.w3
- model.layers.4.block_sparse_moe.experts.3.w3
- model.layers.5.block_sparse_moe.experts.3.w3
- model.layers.6.block_sparse_moe.experts.3.w3
- model.layers.7.block_sparse_moe.experts.3.w3
- model.layers.8.block_sparse_moe.experts.3.w3
- model.layers.9.block_sparse_moe.experts.3.w3
- model.layers.10.block_sparse_moe.experts.3.w3
- model.layers.11.block_sparse_moe.experts.3.w3
- model.layers.12.block_sparse_moe.experts.3.w3
- model.layers.13.block_sparse_moe.experts.3.w3
- model.layers.3.block_sparse_moe.experts.4.w1
- model.layers.2.block_sparse_moe.experts.4.w1
- model.layers.1.block_sparse_moe.experts.4.w1
- model.layers.0.block_sparse_moe.experts.4.w1
- model.layers.4.block_sparse_moe.experts.4.w1
- model.layers.5.block_sparse_moe.experts.4.w1
- model.layers.6.block_sparse_moe.experts.4.w1
- model.layers.7.block_sparse_moe.experts.4.w1
- model.layers.8.block_sparse_moe.experts.4.w1
- model.layers.9.block_sparse_moe.experts.4.w1
- model.layers.10.block_sparse_moe.experts.4.w1
- model.layers.11.block_sparse_moe.experts.4.w1
- model.layers.12.block_sparse_moe.experts.4.w1
- model.layers.13.block_sparse_moe.experts.4.w1
- model.layers.2.block_sparse_moe.experts.4.w2
- model.layers.3.block_sparse_moe.experts.4.w2
- model.layers.1.block_sparse_moe.experts.4.w2
- model.layers.20.block_sparse_moe.experts.4.w2
- model.layers.0.block_sparse_moe.experts.4.w2
- model.layers.4.block_sparse_moe.experts.4.w2
- model.layers.5.block_sparse_moe.experts.4.w2
- model.layers.6.block_sparse_moe.experts.4.w2
- model.layers.7.block_sparse_moe.experts.4.w2
- model.layers.8.block_sparse_moe.experts.4.w2
- model.layers.9.block_sparse_moe.experts.4.w2
- model.layers.10.block_sparse_moe.experts.4.w2
- model.layers.11.block_sparse_moe.experts.4.w2
- model.layers.12.block_sparse_moe.experts.4.w2
- model.layers.3.block_sparse_moe.experts.4.w3
- model.layers.2.block_sparse_moe.experts.4.w3
- model.layers.1.block_sparse_moe.experts.4.w3
- model.layers.0.block_sparse_moe.experts.4.w3
- model.layers.4.block_sparse_moe.experts.4.w3
- model.layers.5.block_sparse_moe.experts.4.w3
- model.layers.6.block_sparse_moe.experts.4.w3
- model.layers.7.block_sparse_moe.experts.4.w3
- model.layers.8.block_sparse_moe.experts.4.w3
- model.layers.9.block_sparse_moe.experts.4.w3
- model.layers.10.block_sparse_moe.experts.4.w3
- model.layers.11.block_sparse_moe.experts.4.w3
- model.layers.12.block_sparse_moe.experts.4.w3
- model.layers.13.block_sparse_moe.experts.4.w3
- model.layers.4.block_sparse_moe.experts.5.w1
- model.layers.3.block_sparse_moe.experts.5.w1
- model.layers.2.block_sparse_moe.experts.5.w1
- model.layers.1.block_sparse_moe.experts.5.w1
- model.layers.0.block_sparse_moe.experts.5.w1
- model.layers.5.block_sparse_moe.experts.5.w1
- model.layers.6.block_sparse_moe.experts.5.w1
- model.layers.7.block_sparse_moe.experts.5.w1
- model.layers.8.block_sparse_moe.experts.5.w1
- model.layers.9.block_sparse_moe.experts.5.w1
- model.layers.10.block_sparse_moe.experts.5.w1
- model.layers.11.block_sparse_moe.experts.5.w1
- model.layers.12.block_sparse_moe.experts.5.w1
- model.layers.13.block_sparse_moe.experts.5.w1
- model.layers.4.block_sparse_moe.experts.5.w2
- model.layers.2.block_sparse_moe.experts.5.w2
- model.layers.3.block_sparse_moe.experts.5.w2
- model.layers.1.block_sparse_moe.experts.5.w2
- model.layers.0.block_sparse_moe.experts.5.w2
- model.layers.5.block_sparse_moe.experts.5.w2
- model.layers.6.block_sparse_moe.experts.5.w2
- model.layers.7.block_sparse_moe.experts.5.w2
- model.layers.8.block_sparse_moe.experts.5.w2
- model.layers.9.block_sparse_moe.experts.5.w2
- model.layers.10.block_sparse_moe.experts.5.w2
- model.layers.11.block_sparse_moe.experts.5.w2
- model.layers.12.block_sparse_moe.experts.5.w2
- model.layers.13.block_sparse_moe.experts.5.w2
- model.layers.4.block_sparse_moe.experts.5.w3
- model.layers.3.block_sparse_moe.experts.5.w3
- model.layers.2.block_sparse_moe.experts.5.w3
- model.layers.1.block_sparse_moe.experts.5.w3
- model.layers.0.block_sparse_moe.experts.5.w3
- model.layers.5.block_sparse_moe.experts.5.w3
- model.layers.6.block_sparse_moe.experts.5.w3
- model.layers.7.block_sparse_moe.experts.5.w3
- model.layers.8.block_sparse_moe.experts.5.w3
- model.layers.9.block_sparse_moe.experts.5.w3
- model.layers.10.block_sparse_moe.experts.5.w3
- model.layers.11.block_sparse_moe.experts.5.w3
- model.layers.12.block_sparse_moe.experts.5.w3
- model.layers.13.block_sparse_moe.experts.5.w3
- model.layers.5.block_sparse_moe.experts.6.w1
- model.layers.4.block_sparse_moe.experts.6.w1
- model.layers.3.block_sparse_moe.experts.6.w1
- model.layers.2.block_sparse_moe.experts.6.w1
- model.layers.1.block_sparse_moe.experts.6.w1
- model.layers.0.block_sparse_moe.experts.6.w1
- model.layers.6.block_sparse_moe.experts.6.w1
- model.layers.7.block_sparse_moe.experts.6.w1
- model.layers.8.block_sparse_moe.experts.6.w1
- model.layers.9.block_sparse_moe.experts.6.w1
- model.layers.10.block_sparse_moe.experts.6.w1
- model.layers.11.block_sparse_moe.experts.6.w1
- model.layers.12.block_sparse_moe.experts.6.w1
- model.layers.13.block_sparse_moe.experts.6.w1
- model.layers.5.block_sparse_moe.experts.6.w2
- model.layers.4.block_sparse_moe.experts.6.w2
- model.layers.2.block_sparse_moe.experts.6.w2
- model.layers.3.block_sparse_moe.experts.6.w2
- model.layers.1.block_sparse_moe.experts.6.w2
- model.layers.0.block_sparse_moe.experts.6.w2
- model.layers.6.block_sparse_moe.experts.6.w2
- model.layers.7.block_sparse_moe.experts.6.w2
- model.layers.8.block_sparse_moe.experts.6.w2
- model.layers.9.block_sparse_moe.experts.6.w2
- model.layers.10.block_sparse_moe.experts.6.w2
- model.layers.11.block_sparse_moe.experts.6.w2
- model.layers.12.block_sparse_moe.experts.6.w2
- model.layers.13.block_sparse_moe.experts.6.w2
- model.layers.5.block_sparse_moe.experts.6.w3
- model.layers.4.block_sparse_moe.experts.6.w3
- model.layers.3.block_sparse_moe.experts.6.w3
- model.layers.2.block_sparse_moe.experts.6.w3
- model.layers.1.block_sparse_moe.experts.6.w3
- model.layers.0.block_sparse_moe.experts.6.w3
- model.layers.6.block_sparse_moe.experts.6.w3
- model.layers.7.block_sparse_moe.experts.6.w3
- model.layers.8.block_sparse_moe.experts.6.w3
- model.layers.9.block_sparse_moe.experts.6.w3
- model.layers.10.block_sparse_moe.experts.6.w3
- model.layers.11.block_sparse_moe.experts.6.w3
- model.layers.12.block_sparse_moe.experts.6.w3
- model.layers.13.block_sparse_moe.experts.6.w3
- model.layers.5.block_sparse_moe.experts.7.w1
- model.layers.6.block_sparse_moe.experts.7.w1
- model.layers.3.block_sparse_moe.experts.7.w1
- model.layers.4.block_sparse_moe.experts.7.w1
- model.layers.2.block_sparse_moe.experts.7.w1
- model.layers.0.block_sparse_moe.experts.7.w1
- model.layers.7.block_sparse_moe.experts.7.w1
- model.layers.8.block_sparse_moe.experts.7.w1
- model.layers.9.block_sparse_moe.experts.7.w1
- model.layers.10.block_sparse_moe.experts.7.w1
- model.layers.11.block_sparse_moe.experts.7.w1
- model.layers.12.block_sparse_moe.experts.7.w1
- model.layers.13.block_sparse_moe.experts.7.w1
- model.layers.14.block_sparse_moe.experts.7.w1
- model.layers.6.block_sparse_moe.experts.7.w2
- model.layers.5.block_sparse_moe.experts.7.w2
- model.layers.4.block_sparse_moe.experts.7.w2
- model.layers.2.block_sparse_moe.experts.7.w2
- model.layers.3.block_sparse_moe.experts.7.w2
- model.layers.1.block_sparse_moe.experts.7.w2
- model.layers.0.block_sparse_moe.experts.7.w2
- model.layers.7.block_sparse_moe.experts.7.w2
- model.layers.8.block_sparse_moe.experts.7.w2
- model.layers.9.block_sparse_moe.experts.7.w2
- model.layers.10.block_sparse_moe.experts.7.w2
- model.layers.11.block_sparse_moe.experts.7.w2
- model.layers.12.block_sparse_moe.experts.7.w2
- model.layers.13.block_sparse_moe.experts.7.w2
- model.layers.6.block_sparse_moe.experts.7.w3
- model.layers.5.block_sparse_moe.experts.7.w3
- model.layers.4.block_sparse_moe.experts.7.w3
- model.layers.3.block_sparse_moe.experts.7.w3
- model.layers.2.block_sparse_moe.experts.7.w3
- model.layers.0.block_sparse_moe.experts.7.w3
- model.layers.7.block_sparse_moe.experts.7.w3
- model.layers.8.block_sparse_moe.experts.7.w3
- model.layers.9.block_sparse_moe.experts.7.w3
- model.layers.10.block_sparse_moe.experts.7.w3
- model.layers.11.block_sparse_moe.experts.7.w3
- model.layers.12.block_sparse_moe.experts.7.w3
- model.layers.13.block_sparse_moe.experts.7.w3
- model.layers.14.block_sparse_moe.experts.7.w3
- model.layers.0.block_sparse_moe.gate
- model.layers.1.block_sparse_moe.gate
- model.layers.2.block_sparse_moe.gate
- model.layers.3.block_sparse_moe.gate
- model.layers.4.block_sparse_moe.gate
- model.layers.5.block_sparse_moe.gate
- model.layers.6.block_sparse_moe.gate
- model.layers.7.block_sparse_moe.gate
- model.layers.8.block_sparse_moe.gate
- model.layers.9.block_sparse_moe.gate
- model.layers.10.block_sparse_moe.gate
- model.layers.11.block_sparse_moe.gate
- model.layers.12.block_sparse_moe.gate
- model.layers.13.block_sparse_moe.gate
model_config:
output_router_logits: true
datasets:
- path: /workspace/datasets/dolphin-2.9/dolphin201-sharegpt2.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/Ultrachat200kunfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/dolphin-coder-translate-sharegpt2.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/dolphin-coder-codegen-sharegpt2.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/not_samantha_norefusals.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/Orca-Math-resort-unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/agent_instruct_react_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/toolbench_instruct_j1s1_3k_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/toolbench_negative_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/toolbench_react_10p_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/toolbench_tflan_cot_30p_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/openhermes200k_unfiltered.jsonl
type: sharegpt
conversation: chatml
- path: /workspace/datasets/dolphin-2.9/SystemConversations.jsonl
type: sharegpt
conversation: chatml
chat_template: chatml
dataset_prepared_path: thingy
val_set_size: 0.0002
output_dir: ./out
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
gradient_accumulation_steps: 8
micro_batch_size: 4
num_epochs: 3
logging_steps: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2.7e-5
wandb_project: dolphin-2.9-mixtral-8x22b
wandb_watch:
wandb_run_id:
wandb_log_model:
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
# resume_from_checkpoint: /home/ehartford/axolotl/out/checkpoint-316
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
saves_per_epoch: 8
save_total_limit: 2
save_steps:
evals_per_epoch: 4
eval_sample_packing: false
debug:
deepspeed: deepspeed_configs/zero3_bf16_cpuoffload_params.json
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
eos_token: "<|im_end|>"
tokens:
- "<|im_start|>"
```
</details><br>
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.7022 | 0.0 | 1 | 0.6989 |
| 0.5344 | 0.25 | 238 | 0.5138 |
| 0.5204 | 0.5 | 476 | 0.5018 |
| 0.5059 | 0.75 | 714 | 0.4951 |
| 0.5112 | 1.0 | 952 | 0.4911 |
| 0.4561 | 1.24 | 1190 | 0.4978 |
| 0.478 | 1.49 | 1428 | 0.4935 |
| 0.4714 | 1.74 | 1666 | 0.4899 |
| 0.4626 | 1.99 | 1904 | 0.4861 |
| 0.3675 | 2.22 | 2142 | 0.5240 |
| 0.3595 | 2.47 | 2380 | 0.5229 |
| 0.3438 | 2.72 | 2618 | 0.5217 |
### Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0 | {"language": ["en"], "license": "apache-2.0", "tags": ["generated_from_trainer", "axolotl"], "datasets": ["cognitivecomputations/Dolphin-2.9", "teknium/OpenHermes-2.5", "m-a-p/CodeFeedback-Filtered-Instruction", "cognitivecomputations/dolphin-coder", "cognitivecomputations/samantha-data", "HuggingFaceH4/ultrachat_200k", "microsoft/orca-math-word-problems-200k", "abacusai/SystemChat-1.1", "Locutusque/function-calling-chatml", "internlm/Agent-FLAN"], "base_model": "mistral-community/Mixtral-8x22B-v0.1", "model-index": [{"name": "out", "results": []}]} | blockblockblock/dolphin-2.9-mixtral-8x22b-bpw2.25-exl2 | null | [
"transformers",
"safetensors",
"mixtral",
"text-generation",
"generated_from_trainer",
"axolotl",
"conversational",
"en",
"dataset:cognitivecomputations/Dolphin-2.9",
"dataset:teknium/OpenHermes-2.5",
"dataset:m-a-p/CodeFeedback-Filtered-Instruction",
"dataset:cognitivecomputations/dolphin-coder",
"dataset:cognitivecomputations/samantha-data",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:microsoft/orca-math-word-problems-200k",
"dataset:abacusai/SystemChat-1.1",
"dataset:Locutusque/function-calling-chatml",
"dataset:internlm/Agent-FLAN",
"base_model:mistral-community/Mixtral-8x22B-v0.1",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T01:58:45+00:00 |
null | null | {} | anushkat/DistilGPT2-Beatles-Spotify-Finalized | null | [
"region:us"
] | null | 2024-05-01T02:00:48+00:00 |
|
null | null | {} | anushkat/DistilGPT2-Beatles-Spotify-FinalV | null | [
"region:us"
] | null | 2024-05-01T02:00:58+00:00 |
|
null | null | {} | ivykopal/german_prompt_100k | null | [
"region:us"
] | null | 2024-05-01T02:01:33+00:00 |
|
null | null | {"license": "unknown"} | hautc/z12 | null | [
"license:unknown",
"region:us"
] | null | 2024-05-01T02:02:08+00:00 |
|
null | null | {} | Zouziak/Gagnat | null | [
"region:us"
] | null | 2024-05-01T02:02:44+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. -->
# DistilGPT2-Beatles-Spotify-FinalVersion
This model is a fine-tuned version of [wvangils/DistilGPT2-Beatles-Lyrics-finetuned](https://huggingface.co/wvangils/DistilGPT2-Beatles-Lyrics-finetuned) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8839
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.1125 | 0.0 | 25 | 1.9245 |
| 2.1035 | 0.0 | 50 | 1.9315 |
| 2.1064 | 0.0 | 75 | 1.9184 |
| 2.0874 | 0.0 | 100 | 1.9101 |
| 2.0948 | 0.0 | 125 | 1.9143 |
| 2.1088 | 0.0 | 150 | 1.8953 |
| 2.0612 | 0.01 | 175 | 1.9130 |
| 2.0828 | 0.01 | 200 | 1.9046 |
| 2.0676 | 0.01 | 225 | 1.8950 |
| 2.072 | 0.01 | 250 | 1.9092 |
| 2.0748 | 0.01 | 275 | 1.8814 |
| 2.0769 | 0.01 | 300 | 1.8948 |
| 2.068 | 0.01 | 325 | 1.8921 |
| 2.0513 | 0.01 | 350 | 1.8904 |
| 2.0686 | 0.01 | 375 | 1.8794 |
| 2.0702 | 0.01 | 400 | 1.8800 |
| 2.059 | 0.01 | 425 | 1.8780 |
| 2.0562 | 0.01 | 450 | 1.8841 |
| 2.0705 | 0.01 | 475 | 1.8824 |
| 2.0675 | 0.02 | 500 | 1.8839 |
### Framework versions
- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 1.13.1
- Datasets 2.17.0
- Tokenizers 0.15.2 | {"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "wvangils/DistilGPT2-Beatles-Lyrics-finetuned", "model-index": [{"name": "DistilGPT2-Beatles-Spotify-FinalVersion", "results": []}]} | anushkat/DistilGPT2-Beatles-Spotify-FinalVersion | null | [
"peft",
"safetensors",
"generated_from_trainer",
"base_model:wvangils/DistilGPT2-Beatles-Lyrics-finetuned",
"license:apache-2.0",
"region:us"
] | null | 2024-05-01T02:02:55+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. -->
# opt-350m-finetuned-mnli-mm
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 3.0148
- Accuracy: 0.5163
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 1 | 3.0148 | 0.5163 |
| No log | 2.0 | 2 | 1.7303 | 0.5153 |
| No log | 3.0 | 3 | 0.9062 | 0.4932 |
| No log | 4.0 | 4 | 1.1445 | 0.4908 |
| No log | 5.0 | 5 | 1.3091 | 0.4863 |
| No log | 6.0 | 6 | 1.2249 | 0.4901 |
| No log | 7.0 | 7 | 1.0692 | 0.4935 |
| No log | 8.0 | 8 | 0.9502 | 0.5031 |
| No log | 9.0 | 9 | 0.9018 | 0.5054 |
| No log | 10.0 | 10 | 0.8909 | 0.5089 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "other", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "facebook/opt-350m", "model-index": [{"name": "opt-350m-finetuned-mnli-mm", "results": []}]} | elliottfitzgerald/opt-350m-finetuned-mnli-mm | null | [
"transformers",
"tensorboard",
"safetensors",
"opt",
"text-classification",
"generated_from_trainer",
"base_model:facebook/opt-350m",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T02:03:09+00:00 |
null | null | {} | ttc0000/mistral_Progressive_Homesite_text_lora_r64_a128_info_extract | null | [
"safetensors",
"region:us"
] | null | 2024-05-01T02:07:03+00:00 |
|
text-generation | transformers | <img src="./veteus_logo.svg" width="100%" height="20%" alt="">
# Our Models
- [Vecteus](https://huggingface.co/Local-Novel-LLM-project/Vecteus-v1)
- [Ninja-v1](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1)
- [Ninja-v1-NSFW](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1-NSFW)
- [Ninja-v1-128k](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1-128k)
- [Ninja-v1-NSFW-128k](https://huggingface.co/Local-Novel-LLM-project/Ninja-v1-NSFW-128k)
## Model Card for VecTeus-v1.0
The Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1
VecTeus has the following changes compared to Mistral-7B-v0.1.
- 128k context window (8k context in v0.1)
- Achieving both high quality Japanese and English generation
- Can be generated NSFW
- Memory ability that does not forget even after long-context generation
This model was created with the help of GPUs from the first LocalAI hackathon.
We would like to take this opportunity to thank
## List of Creation Methods
- Chatvector for multiple models
- Simple linear merging of result models
- Domain and Sentence Enhancement with LORA
- Context expansion
## Instruction format
Freed from templates. Congratulations
## Example prompts to improve (Japanese)
- BAD: あなたは○○として振る舞います
- GOOD: あなたは○○です
- BAD: あなたは○○ができます
- GOOD: あなたは○○をします
## Performing inference
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "Local-Novel-LLM-project/Vecteus-v1"
new_tokens = 1024
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, torch_dtype=torch.float16, attn_implementation="flash_attention_2", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_id)
system_prompt = "あなたはプロの小説家です。\n小説を書いてください\n-------- "
prompt = input("Enter a prompt: ")
system_prompt += prompt + "\n-------- "
model_inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
generated_ids = model.generate(**model_inputs, max_new_tokens=new_tokens, do_sample=True)
print(tokenizer.batch_decode(generated_ids)[0])
````
## Merge recipe
- VT0.1 = Ninjav1 + Original Lora
- VT0.2 = Ninjav1 128k + Original Lora
- VT0.2on0.1 = VT0.1 + VT0.2
- VT1 = all VT Series + Lora + Ninja 128k and Normal
## Other points to keep in mind
- The training data may be biased. Be careful with the generated sentences.
- Memory usage may be large for long inferences.
- If possible, we recommend inferring with llamacpp rather than Transformers. | {"language": ["en", "ja"], "license": "apache-2.0", "library_name": "transformers", "tags": ["finetuned"], "pipeline_tag": "text-generation"} | Local-Novel-LLM-project/Vecteus-v1 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"finetuned",
"en",
"ja",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T02:08:01+00:00 |
null | null | {} | Naetae/Comp3161_Final_Assignment | null | [
"region:us"
] | null | 2024-05-01T02:08:20+00:00 |
|
null | transformers | <img src="Faraday Model Repository Banner.png" alt="Faraday.dev" style="height: 90px; min-width: 32px; display: block; margin: auto;">
**<p style="text-align: center;">The official library of GGUF format models for use in the local AI chat app, Faraday.dev.</p>**
<p style="text-align: center;"><a href="https://faraday.dev/">Download Faraday here to get started.</a></p>
<p style="text-align: center;"><a href="https://www.reddit.com/r/LLM_Quants/">Request Additional models at r/LLM_Quants.</a></p>
***
# Llama 3 8B Ultra Instruct
- **Creator:** [elinas](https://huggingface.co/elinas/)
- **Original:** [Llama 3 8B Ultra Instruct](https://huggingface.co/elinas/Llama-3-8B-Ultra-Instruct)
- **Date Created:** 2024-04-29
- **Trained Context:** 8192 tokens
- **Description:** A small general purpose model that combines the most powerful instruct models with quality, uncensored roleplaying models. It will introduce better RAG capabilities in the form of Bagel to Llama 3 8B Instruct as well as German multilanguage, higher general intelligence and vision support. A model focused on Biology adds knowledge in the medical field.
## What is a GGUF?
GGUF is a large language model (LLM) format that can be split between CPU and GPU. GGUFs are compatible with applications based on llama.cpp, such as Faraday.dev. Where other model formats require higher end GPUs with ample VRAM, GGUFs can be efficiently run on a wider variety of hardware.
GGUF models are quantized to reduce resource usage, with a tradeoff of reduced coherence at lower quantizations. Quantization reduces the precision of the model weights by changing the number of bits used for each weight.
***
<img src="faraday-logo.png" alt="Faraday.dev" style="height: 75px; min-width: 32px; display: block; horizontal align: left;">
## Faraday.dev
- Free, local AI chat application.
- One-click installation on Mac and PC.
- Automatically use GPU for maximum speed.
- Built-in model manager.
- High-quality character hub.
- Zero-config desktop-to-mobile tethering.
Faraday makes it easy to start chatting with AI using your own characters or one of the many found in the built-in character hub. The model manager helps you find the latest and greatest models without worrying about whether it's the correct format. Faraday supports advanced features such as lorebooks, author's note, text formatting, custom context size, sampler settings, grammars, local TTS, cloud inference, and tethering, all implemented in a way that is straightforward and reliable.
**Join us on [Discord](https://discord.gg/SyNN2vC9tQ)**
*** | {"license": "llama3", "library_name": "transformers", "tags": ["mergekit", "merge"], "model_name": "Llama-3-8B-Ultra-Instruct-GGUF", "base_model": "elinas/Llama-3-8B-Ultra-Instruct", "quantized_by": "brooketh"} | FaradayDotDev/Llama-3-8B-Ultra-Instruct-GGUF | null | [
"transformers",
"gguf",
"mergekit",
"merge",
"base_model:elinas/Llama-3-8B-Ultra-Instruct",
"license:llama3",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:14:39+00:00 |
null | null | {} | sayakpaul/sdxl-orpo-large-beta_orpo-0.05-beta_inner-250-lr-5e-6 | null | [
"region:us"
] | null | 2024-05-01T02:15:24+00:00 |
|
null | transformers |
# Uploaded model
- **Developed by:** MilaNguyen
- **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"} | MilaNguyen/sft_summary_prompt | 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 | 2024-05-01T02:15:59+00:00 |
null | null | {} | tdrussell/Llama-3-70B-Instruct-Storywriter-GGUF-q4_k_m | null | [
"gguf",
"region:us"
] | null | 2024-05-01T02:16:39+00:00 |
|
text-classification | transformers | {} | felohdez/imdbreviews_classification_distilbert_v02 | null | [
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:19:08+00:00 |
|
null | null | {} | teleprint-me/stablelm-2-1_6b-chat | null | [
"gguf",
"region:us"
] | null | 2024-05-01T02:19:34+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": []} | salangarica/BioMistral-ALL | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T02:19:53+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 Small Hi - Sanchit Gandhi
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4697
- Wer: 31.8336
## 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 |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.0921 | 2.4450 | 1000 | 0.2992 | 35.0334 |
| 0.0224 | 4.8900 | 2000 | 0.3606 | 34.2970 |
| 0.0026 | 7.3350 | 3000 | 0.4154 | 32.1172 |
| 0.0005 | 9.7800 | 4000 | 0.4530 | 31.8971 |
| 0.0002 | 12.2249 | 5000 | 0.4697 | 31.8336 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"language": ["hi"], "license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["mozilla-foundation/common_voice_11_0"], "metrics": ["wer"], "base_model": "openai/whisper-small", "model-index": [{"name": "Whisper Small Hi - Sanchit Gandhi", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "Common Voice 11.0", "type": "mozilla-foundation/common_voice_11_0", "config": "hi", "split": "None", "args": "config: hi, split: test"}, "metrics": [{"type": "wer", "value": 31.833573182087534, "name": "Wer"}]}]}]} | janboe/whisper-small-hi | null | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"hi",
"dataset:mozilla-foundation/common_voice_11_0",
"base_model:openai/whisper-small",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:20:20+00:00 |
text-classification | 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": []} | HC-85/distilbert-arxiv-multilabel-b32 | null | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:22:40+00:00 |
text-generation | transformers |
Version 2:
Attempt to use linear "retraining" to fix issues with orginal model (D_AU-Tiefighter-Giraffe-13B-32k-slerp)
merge from step 1.
Seems to be successful.
Model is working correctly and GGUFs are also working correctly with context at 32768.
More testing required to see if context upgrade holds.
Imatrix Plus GGUFs upload to follow shortly.
# D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp
D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [KoboldAI/LLaMA2-13B-Tiefighter](https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter)
* [DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp](https://huggingface.co/DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp)
## 🧩 Configuration
```yaml
models:
- model: KoboldAI/LLaMA2-13B-Tiefighter
parameters:
weight: 0.8
- model: DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp
parameters:
weight: 0.2
merge_method: linear
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "DavidAU/D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
``` | {"tags": ["merge", "mergekit", "lazymergekit", "KoboldAI/LLaMA2-13B-Tiefighter", "DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp"], "base_model": ["KoboldAI/LLaMA2-13B-Tiefighter", "DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp"]} | DavidAU/D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"mergekit",
"lazymergekit",
"KoboldAI/LLaMA2-13B-Tiefighter",
"DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp",
"base_model:KoboldAI/LLaMA2-13B-Tiefighter",
"base_model:DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T02:22:56+00:00 |
image-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. -->
# vit-xray-pneumonia-classification
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0740
- Accuracy: 0.9734
## 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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| 0.4843 | 0.9882 | 63 | 0.1954 | 0.9408 |
| 0.1986 | 1.9922 | 127 | 0.1483 | 0.9494 |
| 0.1694 | 2.9961 | 191 | 0.1316 | 0.9459 |
| 0.1368 | 4.0 | 255 | 0.1207 | 0.9554 |
| 0.1399 | 4.9882 | 318 | 0.1738 | 0.9296 |
| 0.1203 | 5.9922 | 382 | 0.0966 | 0.9631 |
| 0.1085 | 6.9961 | 446 | 0.0956 | 0.9631 |
| 0.1046 | 8.0 | 510 | 0.0952 | 0.9665 |
| 0.0883 | 8.9882 | 573 | 0.0990 | 0.9665 |
| 0.0773 | 9.9922 | 637 | 0.0896 | 0.9717 |
| 0.0815 | 10.9961 | 701 | 0.1084 | 0.9605 |
| 0.0793 | 12.0 | 765 | 0.0767 | 0.9742 |
| 0.0778 | 12.9882 | 828 | 0.0885 | 0.9691 |
| 0.0609 | 13.9922 | 892 | 0.0778 | 0.9708 |
| 0.0685 | 14.8235 | 945 | 0.0740 | 0.9734 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "google/vit-base-patch16-224-in21k", "model-index": [{"name": "vit-xray-pneumonia-classification", "results": []}]} | Larbz-7/vit-xray-pneumonia-classification | null | [
"transformers",
"tensorboard",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"base_model:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:23:23+00:00 |
null | null | {"license": "mit"} | AaronStudent/CAP6610_Final_Project_Model_AI_Image_Classifier | null | [
"license:mit",
"region:us"
] | null | 2024-05-01T02:24:15+00:00 |
|
text-generation | transformers | {} | nessa01macias/llama-2-13b_sustainability-qa | null | [
"transformers",
"pytorch",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T02:24:44+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": []} | dsodhia/bart_peft_model | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:24:45+00:00 |
null | null | {} | BleakBob/Gpt2 | null | [
"region:us"
] | null | 2024-05-01T02:26:01+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": []} | TinyPixel/rp | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T02:26:08+00:00 |
translation | transformers |
# Uploaded model
- **Developed by:** johannssky
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) | {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl"], "base_model": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit", "pipeline_tag": "translation"} | johannssky/mica_model | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"translation",
"en",
"base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:27:44+00:00 |
text-generation | transformers |
# Uploaded model
- **Developed by:** herisan
- **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"} | herisan/llama-3-8b-finetune | 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 | 2024-05-01T02:28:07+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": []} | Chord-Llama/Llama-3-chord-llama-chechpoint-3 | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:28:48+00:00 |
fill-mask | 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. -->
# final-ft__bert-base-spanish-wwm-uncased__70k-ultrasounds
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5422
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| No log | 0.9990 | 254 | 0.9709 |
| No log | 1.9980 | 508 | 0.8043 |
| No log | 2.9971 | 762 | 0.7331 |
| 1.013 | 4.0 | 1017 | 0.6860 |
| 1.013 | 4.9990 | 1271 | 0.6597 |
| 1.013 | 5.9980 | 1525 | 0.6345 |
| 1.013 | 6.9971 | 1779 | 0.6280 |
| 0.6672 | 8.0 | 2034 | 0.5954 |
| 0.6672 | 8.9990 | 2288 | 0.5987 |
| 0.6672 | 9.9980 | 2542 | 0.5802 |
| 0.6672 | 10.9971 | 2796 | 0.5792 |
| 0.6055 | 12.0 | 3051 | 0.5632 |
| 0.6055 | 12.9990 | 3305 | 0.5713 |
| 0.6055 | 13.9980 | 3559 | 0.5545 |
| 0.6055 | 14.9971 | 3813 | 0.5434 |
| 0.5735 | 16.0 | 4068 | 0.5475 |
| 0.5735 | 16.9990 | 4322 | 0.5471 |
| 0.5735 | 17.9980 | 4576 | 0.5377 |
| 0.5735 | 18.9971 | 4830 | 0.5403 |
| 0.5574 | 19.9803 | 5080 | 0.5422 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"tags": ["generated_from_trainer"], "base_model": "dccuchile/bert-base-spanish-wwm-uncased", "model-index": [{"name": "final-ft__bert-base-spanish-wwm-uncased__70k-ultrasounds", "results": []}]} | manucos/final-ft__bert-base-spanish-wwm-uncased__70k-ultrasounds | null | [
"transformers",
"tensorboard",
"safetensors",
"bert",
"fill-mask",
"generated_from_trainer",
"base_model:dccuchile/bert-base-spanish-wwm-uncased",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:30:41+00:00 |
text-classification | transformers | {"license": "mit"} | Yuhhi/tf_model.h5 | null | [
"transformers",
"tf",
"distilbert",
"text-classification",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:30:54+00:00 |
|
fill-mask | 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. -->
# final-ft__roberta-clinical-wl-es__70k-ultrasounds
This model is a fine-tuned version of [plncmm/roberta-clinical-wl-es](https://huggingface.co/plncmm/roberta-clinical-wl-es) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6177
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| No log | 0.9967 | 229 | 0.9228 |
| No log | 1.9978 | 459 | 0.8047 |
| No log | 2.9989 | 689 | 0.7665 |
| 0.958 | 4.0 | 919 | 0.7180 |
| 0.958 | 4.9967 | 1148 | 0.7044 |
| 0.958 | 5.9978 | 1378 | 0.6875 |
| 0.958 | 6.9989 | 1608 | 0.6674 |
| 0.7197 | 8.0 | 1838 | 0.6454 |
| 0.7197 | 8.9967 | 2067 | 0.6485 |
| 0.7197 | 9.9978 | 2297 | 0.6411 |
| 0.7197 | 10.9989 | 2527 | 0.6292 |
| 0.665 | 12.0 | 2757 | 0.6223 |
| 0.665 | 12.9967 | 2986 | 0.6311 |
| 0.665 | 13.9978 | 3216 | 0.6128 |
| 0.665 | 14.9989 | 3446 | 0.6141 |
| 0.6398 | 16.0 | 3676 | 0.6028 |
| 0.6398 | 16.9967 | 3905 | 0.6064 |
| 0.6398 | 17.9978 | 4135 | 0.6148 |
| 0.6398 | 18.9989 | 4365 | 0.6032 |
| 0.6398 | 19.9347 | 4580 | 0.6177 |
### Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "plncmm/roberta-clinical-wl-es", "model-index": [{"name": "final-ft__roberta-clinical-wl-es__70k-ultrasounds", "results": []}]} | manucos/final-ft__roberta-clinical-wl-es__70k-ultrasounds | null | [
"transformers",
"tensorboard",
"safetensors",
"roberta",
"fill-mask",
"generated_from_trainer",
"base_model:plncmm/roberta-clinical-wl-es",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:31:00+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. -->
# xlm-roberta-base-finetuned-panx-fr
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2658
- F1: 0.8434
## 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: 24
- eval_batch_size: 24
- 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 | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.5483 | 1.0 | 191 | 0.3200 | 0.7793 |
| 0.2667 | 2.0 | 382 | 0.2495 | 0.8337 |
| 0.1759 | 3.0 | 573 | 0.2658 | 0.8434 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["f1"], "base_model": "xlm-roberta-base", "model-index": [{"name": "xlm-roberta-base-finetuned-panx-fr", "results": []}]} | u00890358/xlm-roberta-base-finetuned-panx-fr | null | [
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:32:06+00:00 |
null | null | {} | sayakpaul/sdxl-orpo-large-beta_orpo-0.1-beta_inner-500-lr-5e-6 | null | [
"region:us"
] | null | 2024-05-01T02:33:21+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. -->
# ap-normistral-7b-align-scan
This model is a fine-tuned version of [data/ap-normistral-7b-sft-qlora](https://huggingface.co/data/ap-normistral-7b-sft-qlora) on the hugodk-sch/aftonposten_title_prefs dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9524
- Rewards/chosen: -0.0816
- Rewards/rejected: -0.1313
- Rewards/accuracies: 0.5303
- Rewards/margins: 0.0497
- Logps/rejected: -36.6233
- Logps/chosen: -32.8513
- Logits/rejected: 98.1886
- Logits/chosen: 98.2171
## 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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.927 | 0.26 | 100 | 0.9734 | 0.0205 | -0.0061 | 0.5598 | 0.0265 | -35.9968 | -32.3408 | 98.7115 | 98.7190 |
| 0.7448 | 0.52 | 200 | 0.9482 | -0.0840 | -0.1367 | 0.5307 | 0.0527 | -36.6501 | -32.8631 | 98.2057 | 98.2271 |
| 0.7402 | 0.78 | 300 | 0.9400 | -0.0802 | -0.1425 | 0.5623 | 0.0624 | -36.6792 | -32.8440 | 98.1900 | 98.2178 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1 | {"library_name": "peft", "tags": ["alignment-handbook", "trl", "dpo", "generated_from_trainer"], "datasets": ["hugodk-sch/aftonposten_title_prefs"], "base_model": "norallm/normistral-7b-warm", "model-index": [{"name": "ap-normistral-7b-align-scan", "results": []}]} | hugodk-sch/ap-normistral-7b-align-scan | null | [
"peft",
"safetensors",
"mistral",
"alignment-handbook",
"trl",
"dpo",
"generated_from_trainer",
"dataset:hugodk-sch/aftonposten_title_prefs",
"base_model:norallm/normistral-7b-warm",
"4-bit",
"region:us"
] | null | 2024-05-01T02:35:30+00:00 |
image-classification | transformers | {} | vm24bho/dfm_net_jsm | null | [
"transformers",
"safetensors",
"vit",
"image-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us",
"has_space"
] | null | 2024-05-01T02:36:40+00:00 |
|
null | null | {} | Ksgk-fy/Zaligner-v1-test01 | null | [
"tensorboard",
"safetensors",
"region:us"
] | null | 2024-05-01T02:36:54+00:00 |
|
null | null | {} | Kudod/vistral-7B_finetuned_A100_May1st | null | [
"region:us"
] | null | 2024-05-01T02:37:06+00:00 |
|
null | null | {} | washeed/ocr | null | [
"region:us"
] | null | 2024-05-01T02:37:45+00:00 |
|
text-generation | transformers | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
zephyr-7b-alpha - bnb 4bits
- Model creator: https://huggingface.co/HuggingFaceH4/
- Original model: https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/
Original model description:
---
tags:
- generated_from_trainer
model-index:
- name: zephyr-7b-alpha
results: []
license: mit
datasets:
- stingning/ultrachat
- openbmb/UltraFeedback
language:
- en
base_model: mistralai/Mistral-7B-v0.1
---
<!-- 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. -->
<img src="https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/resolve/main/thumbnail.png" alt="Zephyr Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# Model Card for Zephyr 7B Alpha
Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-α is the first model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that was trained on on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). We found that removing the in-built alignment of these datasets boosted performance on [MT Bench](https://huggingface.co/spaces/lmsys/mt-bench) and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so.
## Model description
- **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
- **Language(s) (NLP):** Primarily English
- **License:** MIT
- **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/huggingface/alignment-handbook
- **Demo:** https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat
## Intended uses & limitations
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. As a result, the model can be used for chat and you can check out our [demo](https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat) to test its capabilities.
Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
```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="HuggingFaceH4/zephyr-7b-alpha", 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|>
# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
```
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
Zephyr-7B-α has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
It is also unknown what the size and composition of the corpus was used to train the base model (`mistralai/Mistral-7B-v0.1`), however it is likely to have included a mix of Web data and technical sources like books and code. See the [Falcon 180B model card](https://huggingface.co/tiiuae/falcon-180B#training-data) for an example of this.
## Training and evaluation data
Zephyr 7B Alpha achieves the following results on the evaluation set:
- Loss: 0.4605
- Rewards/chosen: -0.5053
- Rewards/rejected: -1.8752
- Rewards/accuracies: 0.7812
- Rewards/margins: 1.3699
- Logps/rejected: -327.4286
- Logps/chosen: -297.1040
- Logits/rejected: -2.7153
- Logits/chosen: -2.7447
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- total_train_batch_size: 32
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.5602 | 0.05 | 100 | 0.5589 | -0.3359 | -0.8168 | 0.7188 | 0.4809 | -306.2607 | -293.7161 | -2.6554 | -2.6797 |
| 0.4852 | 0.1 | 200 | 0.5136 | -0.5310 | -1.4994 | 0.8125 | 0.9684 | -319.9124 | -297.6181 | -2.5762 | -2.5957 |
| 0.5212 | 0.15 | 300 | 0.5168 | -0.1686 | -1.1760 | 0.7812 | 1.0074 | -313.4444 | -290.3699 | -2.6865 | -2.7125 |
| 0.5496 | 0.21 | 400 | 0.4835 | -0.1617 | -1.7170 | 0.8281 | 1.5552 | -324.2635 | -290.2326 | -2.7947 | -2.8218 |
| 0.5209 | 0.26 | 500 | 0.5054 | -0.4778 | -1.6604 | 0.7344 | 1.1826 | -323.1325 | -296.5546 | -2.8388 | -2.8667 |
| 0.4617 | 0.31 | 600 | 0.4910 | -0.3738 | -1.5180 | 0.7656 | 1.1442 | -320.2848 | -294.4741 | -2.8234 | -2.8521 |
| 0.4452 | 0.36 | 700 | 0.4838 | -0.4591 | -1.6576 | 0.7031 | 1.1986 | -323.0770 | -296.1796 | -2.7401 | -2.7653 |
| 0.4674 | 0.41 | 800 | 0.5077 | -0.5692 | -1.8659 | 0.7656 | 1.2967 | -327.2416 | -298.3818 | -2.6740 | -2.6945 |
| 0.4656 | 0.46 | 900 | 0.4927 | -0.5279 | -1.6614 | 0.7656 | 1.1335 | -323.1518 | -297.5553 | -2.7817 | -2.8015 |
| 0.4102 | 0.52 | 1000 | 0.4772 | -0.5767 | -2.0667 | 0.7656 | 1.4900 | -331.2578 | -298.5311 | -2.7160 | -2.7455 |
| 0.4663 | 0.57 | 1100 | 0.4740 | -0.8038 | -2.1018 | 0.7656 | 1.2980 | -331.9604 | -303.0741 | -2.6994 | -2.7257 |
| 0.4737 | 0.62 | 1200 | 0.4716 | -0.3783 | -1.7015 | 0.7969 | 1.3232 | -323.9545 | -294.5634 | -2.6842 | -2.7135 |
| 0.4259 | 0.67 | 1300 | 0.4866 | -0.6239 | -1.9703 | 0.7812 | 1.3464 | -329.3312 | -299.4761 | -2.7046 | -2.7356 |
| 0.4935 | 0.72 | 1400 | 0.4747 | -0.5626 | -1.7600 | 0.7812 | 1.1974 | -325.1243 | -298.2491 | -2.7153 | -2.7444 |
| 0.4211 | 0.77 | 1500 | 0.4645 | -0.6099 | -1.9993 | 0.7656 | 1.3894 | -329.9109 | -299.1959 | -2.6944 | -2.7236 |
| 0.4931 | 0.83 | 1600 | 0.4684 | -0.6798 | -2.1082 | 0.7656 | 1.4285 | -332.0890 | -300.5934 | -2.7006 | -2.7305 |
| 0.5029 | 0.88 | 1700 | 0.4595 | -0.5063 | -1.8951 | 0.7812 | 1.3889 | -327.8267 | -297.1233 | -2.7108 | -2.7403 |
| 0.4965 | 0.93 | 1800 | 0.4613 | -0.5561 | -1.9079 | 0.7812 | 1.3518 | -328.0831 | -298.1203 | -2.7226 | -2.7523 |
| 0.4337 | 0.98 | 1900 | 0.4608 | -0.5066 | -1.8718 | 0.7656 | 1.3652 | -327.3599 | -297.1296 | -2.7175 | -2.7469 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.14.0
| {} | RichardErkhov/HuggingFaceH4_-_zephyr-7b-alpha-4bits | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:2305.18290",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-05-01T02:38:13+00:00 |
null | null |
# Hermes 2 Pro - Llama-3 8B
## Model Description
### This is the llama.cpp GGUF Quantized version of Hermes 2 Pro Llama-3 8B, for the full version, click [Here](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)
Hermes 2 Pro is an upgraded version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.
Hermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.
This version of Hermes 2 Pro adds several tokens to assist with agentic capabilities in parsing while streaming tokens - `<tools>`, `<tool_call>`, `<tool_response>` and their closing tags are single tokens now.
This work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI
Learn more about the function calling system for this model on our github repo here: https://github.com/NousResearch/Hermes-Function-Calling
## Example Outputs
### Ask for a structured JSON output:
### Write the plot for a story where anime became real life:
### Coding Assistance
# Prompt Format
Hermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.
System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.
This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.
This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.
Prompt with system instruction (Use whatever system prompt you like, this is just an example!):
```
<|im_start|>system
You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>
<|im_start|>user
Hello, who are you?<|im_end|>
<|im_start|>assistant
Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|>
```
This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
`tokenizer.apply_chat_template()` method:
```python
messages = [
{"role": "system", "content": "You are Hermes 2."},
{"role": "user", "content": "Hello, who are you?"}
]
gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
model.generate(**gen_input)
```
When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure
that the model continues with an assistant response.
To utilize the prompt format without a system prompt, simply leave the line out.
## Prompt Format for Function Calling
Our model was trained on specific system prompts and structures for Function Calling.
You should use the system role with this message, followed by a function signature json as this example shows here.
```
<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {"type": "function", "function": {"name": "get_stock_fundamentals", "description": "get_stock_fundamentals(symbol: str) -> dict - Get fundamental data for a given stock symbol using yfinance API.\\n\\n Args:\\n symbol (str): The stock symbol.\\n\\n Returns:\\n dict: A dictionary containing fundamental data.\\n Keys:\\n - \'symbol\': The stock symbol.\\n - \'company_name\': The long name of the company.\\n - \'sector\': The sector to which the company belongs.\\n - \'industry\': The industry to which the company belongs.\\n - \'market_cap\': The market capitalization of the company.\\n - \'pe_ratio\': The forward price-to-earnings ratio.\\n - \'pb_ratio\': The price-to-book ratio.\\n - \'dividend_yield\': The dividend yield.\\n - \'eps\': The trailing earnings per share.\\n - \'beta\': The beta value of the stock.\\n - \'52_week_high\': The 52-week high price of the stock.\\n - \'52_week_low\': The 52-week low price of the stock.", "parameters": {"type": "object", "properties": {"symbol": {"type": "string"}}, "required": ["symbol"]}}} </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
<tool_call>
{"arguments": <args-dict>, "name": <function-name>}
</tool_call><|im_end|>
```
To complete the function call, create a user prompt that follows the above system prompt, like so:
```
<|im_start|>user
Fetch the stock fundamentals data for Tesla (TSLA)<|im_end|>
```
The model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: https://github.com/NousResearch/Hermes-Function-Calling):
```
<|im_start|>assistant
<tool_call>
{"arguments": {"symbol": "TSLA"}, "name": "get_stock_fundamentals"}
</tool_call><|im_end|>
```
Once you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, `tool` like so:
```
<|im_start|>tool
<tool_response>
{"name": "get_stock_fundamentals", "content": {'symbol': 'TSLA', 'company_name': 'Tesla, Inc.', 'sector': 'Consumer Cyclical', 'industry': 'Auto Manufacturers', 'market_cap': 611384164352, 'pe_ratio': 49.604652, 'pb_ratio': 9.762013, 'dividend_yield': None, 'eps': 4.3, 'beta': 2.427, '52_week_high': 299.29, '52_week_low': 152.37}}
</tool_response>
<|im_end|>
```
The assistant will then read in that data from the function's response, and generate a natural language response:
```
<|im_start|>assistant
The stock fundamentals data for Tesla (TSLA) are as follows:
- **Symbol**: TSLA
- **Company Name**: Tesla, Inc.
- **Sector**: Consumer Cyclical
- **Industry**: Auto Manufacturers
- **Market Capitalization**: $566,160,130,480
- **Forward Price-to-Earnings Ratio (PE Ratio)**: 42.73
- **Price-to-Book Ratio (PB Ratio)**: 9.04
- **Dividend Yield**: N/A
- **Trailing Earnings Per Share (EPS)**: $4.3
- **Beta Value of the Stock**: 2.42
- **52-Week High Price of the Stock**: $299.29
- **52-Week Low Price of the Stock**: $152.37
This information provides a snapshot of Tesla's financial position and performance based on the fundamental data obtained from the yfinance API. It shows that Tesla has a substantial market capitalization and a relatively high P/E and P/B ratio compared to other stocks in its industry. The company does not pay a dividend at the moment, which is reflected by a 'Dividend Yield' of 'None'. The Beta value indicates that Tesla's stock has a moderate level of volatility relative to the market. The 52-week high and low prices give an idea of the stock's range over the past year. This data can be useful when assessing investment opportunities and making investment decisions.<|im_end|>
```
## Prompt Format for JSON Mode / Structured Outputs
Our model was also trained on a specific system prompt for Structured Outputs, which should respond with **only** a json object response, in a specific json schema.
Your schema can be made from a pydantic object using our codebase, with the standalone script `jsonmode.py` available here: https://github.com/NousResearch/Hermes-Function-Calling/tree/main
```
<|im_start|>system
You are a helpful assistant that answers in JSON. Here's the json schema you must adhere to:\n<schema>\n{schema}\n</schema><|im_end|>
```
Given the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.
# Benchmarks
## GPT4All:
```
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.5520|± |0.0145|
| | |acc_norm|0.5887|± |0.0144|
|arc_easy | 0|acc |0.8350|± |0.0076|
| | |acc_norm|0.8123|± |0.0080|
|boolq | 1|acc |0.8584|± |0.0061|
|hellaswag | 0|acc |0.6265|± |0.0048|
| | |acc_norm|0.8053|± |0.0040|
|openbookqa | 0|acc |0.3800|± |0.0217|
| | |acc_norm|0.4580|± |0.0223|
|piqa | 0|acc |0.8003|± |0.0093|
| | |acc_norm|0.8118|± |0.0091|
|winogrande | 0|acc |0.7490|± |0.0122|
```
Average: 72.62
## AGIEval:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------|------:|--------|-----:|---|-----:|
|agieval_aqua_rat | 0|acc |0.2520|± |0.0273|
| | |acc_norm|0.2559|± |0.0274|
|agieval_logiqa_en | 0|acc |0.3548|± |0.0188|
| | |acc_norm|0.3625|± |0.0189|
|agieval_lsat_ar | 0|acc |0.1826|± |0.0255|
| | |acc_norm|0.1913|± |0.0260|
|agieval_lsat_lr | 0|acc |0.5510|± |0.0220|
| | |acc_norm|0.5255|± |0.0221|
|agieval_lsat_rc | 0|acc |0.6431|± |0.0293|
| | |acc_norm|0.6097|± |0.0298|
|agieval_sat_en | 0|acc |0.7330|± |0.0309|
| | |acc_norm|0.7039|± |0.0319|
|agieval_sat_en_without_passage| 0|acc |0.4029|± |0.0343|
| | |acc_norm|0.3689|± |0.0337|
|agieval_sat_math | 0|acc |0.3909|± |0.0330|
| | |acc_norm|0.3773|± |0.0328|
```
Average: 42.44
## BigBench:
```
| Task |Version| Metric |Value | |Stderr|
|------------------------------------------------|------:|---------------------|-----:|---|-----:|
|bigbench_causal_judgement | 0|multiple_choice_grade|0.5737|± |0.0360|
|bigbench_date_understanding | 0|multiple_choice_grade|0.6667|± |0.0246|
|bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3178|± |0.0290|
|bigbench_geometric_shapes | 0|multiple_choice_grade|0.1755|± |0.0201|
| | |exact_str_match |0.0000|± |0.0000|
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.3120|± |0.0207|
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2014|± |0.0152|
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.5500|± |0.0288|
|bigbench_movie_recommendation | 0|multiple_choice_grade|0.4300|± |0.0222|
|bigbench_navigate | 0|multiple_choice_grade|0.4980|± |0.0158|
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.7010|± |0.0102|
|bigbench_ruin_names | 0|multiple_choice_grade|0.4688|± |0.0236|
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.1974|± |0.0126|
|bigbench_snarks | 0|multiple_choice_grade|0.7403|± |0.0327|
|bigbench_sports_understanding | 0|multiple_choice_grade|0.5426|± |0.0159|
|bigbench_temporal_sequences | 0|multiple_choice_grade|0.5320|± |0.0158|
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2280|± |0.0119|
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1531|± |0.0086|
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.5500|± |0.0288|
```
Average: 43.55
## TruthfulQA:
```
| Task |Version|Metric|Value| |Stderr|
|-------------|------:|------|----:|---|-----:|
|truthfulqa_mc| 1|mc1 |0.410|± |0.0172|
| | |mc2 |0.578|± |0.0157|
```
# Inference Code
Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)
Note: To use function calling, you should see the github repo above.
```python
# Code to inference Hermes with HF Transformers
# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, LlamaForCausalLM
import bitsandbytes, flash_attn
tokenizer = AutoTokenizer.from_pretrained('NousResearch/Hermes-2-Pro-Llama-3-8B', trust_remote_code=True)
model = LlamaForCausalLM.from_pretrained(
"Hermes-2-Pro-Llama-3-8B",
torch_dtype=torch.float16,
device_map="auto",
load_in_8bit=False,
load_in_4bit=True,
use_flash_attention_2=True
)
prompts = [
"""<|im_start|>system
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
<|im_start|>user
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
<|im_start|>assistant""",
]
for chat in prompts:
print(chat)
input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
print(f"Response: {response}")
```
## Inference Code for Function Calling:
All code for utilizing, parsing, and building function calling templates is available on our github:
[https://github.com/NousResearch/Hermes-Function-Calling](https://github.com/NousResearch/Hermes-Function-Calling)
# Chat Interfaces
For quantized GGUF versions of the model, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.
In LM-Studio, simply select the ChatML Prefix on the settings side pane:
# How to cite:
```bibtext
@misc{Hermes-2-Pro-Llama-3-8B,
url={[https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B]https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)},
title={Hermes-2-Pro-Llama-3-8B},
author={"Teknium", "interstellarninja", "theemozilla", "karan4d", "huemin_art"}
}
```
| {"language": ["en"], "license": "apache-2.0", "tags": ["Llama-3", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "function calling", "json mode"], "datasets": ["teknium/OpenHermes-2.5"], "base_model": "NousResearch/Meta-Llama-3-8B", "widget": [{"example_title": "Hermes 2 Pro", "messages": [{"role": "system", "content": "You are a sentient, superintelligent artificial general intelligence, here to teach and assist me."}, {"role": "user", "content": "Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world."}]}], "model-index": [{"name": "Hermes-2-Pro-Llama-3-8B", "results": []}]} | NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF | null | [
"gguf",
"Llama-3",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:NousResearch/Meta-Llama-3-8B",
"license:apache-2.0",
"region:us"
] | null | 2024-05-01T02:39:00+00:00 |
text-generation | transformers | {"license": "mit"} | migueldeguzmandev/GPT2XL_RLLMv19-8 | null | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T02:39:07+00:00 |
|
null | null | {"license": "openrail"} | itskeonagain/JorjaFLO | null | [
"license:openrail",
"region:us"
] | null | 2024-05-01T02:39:47+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": []} | Luluuu/0430_2_SEASON_baseline_checkpoint_4500 | null | [
"transformers",
"safetensors",
"bart",
"text2text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:40:08+00:00 |
fill-mask | transformers | {} | nhanpv/vi-en-bert-finetune | null | [
"transformers",
"pytorch",
"roberta",
"fill-mask",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:41:10+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": []} | lunarsylph/stablecell_v57 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:42:12+00:00 |
null | null | {"license": "openrail"} | itskeonagain/ReneeFLO | null | [
"license:openrail",
"region:us"
] | null | 2024-05-01T02:42:57+00:00 |
|
text2text-generation | transformers | {} | paulh27/cnn_aligned_smallT5_cont3 | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T02:44:12+00:00 |
|
text-generation | transformers | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
zephyr-7b-alpha - bnb 8bits
- Model creator: https://huggingface.co/HuggingFaceH4/
- Original model: https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/
Original model description:
---
tags:
- generated_from_trainer
model-index:
- name: zephyr-7b-alpha
results: []
license: mit
datasets:
- stingning/ultrachat
- openbmb/UltraFeedback
language:
- en
base_model: mistralai/Mistral-7B-v0.1
---
<!-- 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. -->
<img src="https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/resolve/main/thumbnail.png" alt="Zephyr Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
# Model Card for Zephyr 7B Alpha
Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-α is the first model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that was trained on on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). We found that removing the in-built alignment of these datasets boosted performance on [MT Bench](https://huggingface.co/spaces/lmsys/mt-bench) and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so.
## Model description
- **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
- **Language(s) (NLP):** Primarily English
- **License:** MIT
- **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/huggingface/alignment-handbook
- **Demo:** https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat
## Intended uses & limitations
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. As a result, the model can be used for chat and you can check out our [demo](https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat) to test its capabilities.
Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
```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="HuggingFaceH4/zephyr-7b-alpha", 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|>
# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
```
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
Zephyr-7B-α has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
It is also unknown what the size and composition of the corpus was used to train the base model (`mistralai/Mistral-7B-v0.1`), however it is likely to have included a mix of Web data and technical sources like books and code. See the [Falcon 180B model card](https://huggingface.co/tiiuae/falcon-180B#training-data) for an example of this.
## Training and evaluation data
Zephyr 7B Alpha achieves the following results on the evaluation set:
- Loss: 0.4605
- Rewards/chosen: -0.5053
- Rewards/rejected: -1.8752
- Rewards/accuracies: 0.7812
- Rewards/margins: 1.3699
- Logps/rejected: -327.4286
- Logps/chosen: -297.1040
- Logits/rejected: -2.7153
- Logits/chosen: -2.7447
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- total_train_batch_size: 32
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
| 0.5602 | 0.05 | 100 | 0.5589 | -0.3359 | -0.8168 | 0.7188 | 0.4809 | -306.2607 | -293.7161 | -2.6554 | -2.6797 |
| 0.4852 | 0.1 | 200 | 0.5136 | -0.5310 | -1.4994 | 0.8125 | 0.9684 | -319.9124 | -297.6181 | -2.5762 | -2.5957 |
| 0.5212 | 0.15 | 300 | 0.5168 | -0.1686 | -1.1760 | 0.7812 | 1.0074 | -313.4444 | -290.3699 | -2.6865 | -2.7125 |
| 0.5496 | 0.21 | 400 | 0.4835 | -0.1617 | -1.7170 | 0.8281 | 1.5552 | -324.2635 | -290.2326 | -2.7947 | -2.8218 |
| 0.5209 | 0.26 | 500 | 0.5054 | -0.4778 | -1.6604 | 0.7344 | 1.1826 | -323.1325 | -296.5546 | -2.8388 | -2.8667 |
| 0.4617 | 0.31 | 600 | 0.4910 | -0.3738 | -1.5180 | 0.7656 | 1.1442 | -320.2848 | -294.4741 | -2.8234 | -2.8521 |
| 0.4452 | 0.36 | 700 | 0.4838 | -0.4591 | -1.6576 | 0.7031 | 1.1986 | -323.0770 | -296.1796 | -2.7401 | -2.7653 |
| 0.4674 | 0.41 | 800 | 0.5077 | -0.5692 | -1.8659 | 0.7656 | 1.2967 | -327.2416 | -298.3818 | -2.6740 | -2.6945 |
| 0.4656 | 0.46 | 900 | 0.4927 | -0.5279 | -1.6614 | 0.7656 | 1.1335 | -323.1518 | -297.5553 | -2.7817 | -2.8015 |
| 0.4102 | 0.52 | 1000 | 0.4772 | -0.5767 | -2.0667 | 0.7656 | 1.4900 | -331.2578 | -298.5311 | -2.7160 | -2.7455 |
| 0.4663 | 0.57 | 1100 | 0.4740 | -0.8038 | -2.1018 | 0.7656 | 1.2980 | -331.9604 | -303.0741 | -2.6994 | -2.7257 |
| 0.4737 | 0.62 | 1200 | 0.4716 | -0.3783 | -1.7015 | 0.7969 | 1.3232 | -323.9545 | -294.5634 | -2.6842 | -2.7135 |
| 0.4259 | 0.67 | 1300 | 0.4866 | -0.6239 | -1.9703 | 0.7812 | 1.3464 | -329.3312 | -299.4761 | -2.7046 | -2.7356 |
| 0.4935 | 0.72 | 1400 | 0.4747 | -0.5626 | -1.7600 | 0.7812 | 1.1974 | -325.1243 | -298.2491 | -2.7153 | -2.7444 |
| 0.4211 | 0.77 | 1500 | 0.4645 | -0.6099 | -1.9993 | 0.7656 | 1.3894 | -329.9109 | -299.1959 | -2.6944 | -2.7236 |
| 0.4931 | 0.83 | 1600 | 0.4684 | -0.6798 | -2.1082 | 0.7656 | 1.4285 | -332.0890 | -300.5934 | -2.7006 | -2.7305 |
| 0.5029 | 0.88 | 1700 | 0.4595 | -0.5063 | -1.8951 | 0.7812 | 1.3889 | -327.8267 | -297.1233 | -2.7108 | -2.7403 |
| 0.4965 | 0.93 | 1800 | 0.4613 | -0.5561 | -1.9079 | 0.7812 | 1.3518 | -328.0831 | -298.1203 | -2.7226 | -2.7523 |
| 0.4337 | 0.98 | 1900 | 0.4608 | -0.5066 | -1.8718 | 0.7656 | 1.3652 | -327.3599 | -297.1296 | -2.7175 | -2.7469 |
### Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.14.0
| {} | RichardErkhov/HuggingFaceH4_-_zephyr-7b-alpha-8bits | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"conversational",
"arxiv:2305.18290",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
] | null | 2024-05-01T02:44:35+00:00 |
text2text-generation | transformers | {} | paulh27/xsum_aligned_smallT5_cont3 | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T02:44:47+00:00 |
|
null | null | {"license": "openrail"} | itskeonagain/FLOStellafreddie | null | [
"license:openrail",
"region:us"
] | null | 2024-05-01T02:44:48+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": []} | abc88767/model25 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:44:53+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": []} | shouray/youtube-comments | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:48:16+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. -->
# YT_Results
This model is a fine-tuned version of [PrunaAI/mistralai-Mistral-7B-Instruct-v0.2-bnb-4bit-smashed](https://huggingface.co/PrunaAI/mistralai-Mistral-7B-Instruct-v0.2-bnb-4bit-smashed) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6777
## 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 4.5563 | 0.9231 | 3 | 3.9263 |
| 4.0352 | 1.8462 | 6 | 3.4243 |
| 3.4577 | 2.7692 | 9 | 2.9729 |
| 2.2428 | 4.0 | 13 | 2.5335 |
| 2.6253 | 4.9231 | 16 | 2.2680 |
| 2.2751 | 5.8462 | 19 | 2.0362 |
| 2.0117 | 6.7692 | 22 | 1.8739 |
| 1.3928 | 8.0 | 26 | 1.7310 |
| 1.749 | 8.9231 | 29 | 1.6830 |
| 1.2249 | 9.2308 | 30 | 1.6777 |
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "PrunaAI/mistralai-Mistral-7B-Instruct-v0.2-bnb-4bit-smashed", "model-index": [{"name": "YT_Results", "results": []}]} | shouray/YT_Results | null | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:PrunaAI/mistralai-Mistral-7B-Instruct-v0.2-bnb-4bit-smashed",
"region:us"
] | null | 2024-05-01T02:48:18+00:00 |
null | null | {} | Nadahass/MREG_7b_4_SmallData_GGUF | null | [
"gguf",
"region:us"
] | null | 2024-05-01T02:48:23+00:00 |
|
null | null | {} | Chelseafc/grockit | null | [
"region:us"
] | null | 2024-05-01T02:49:59+00:00 |
|
null | null | {} | Abhinay45/musicclassification | null | [
"region:us"
] | null | 2024-05-01T02:49:59+00:00 |
|
text-generation | transformers | ## Hypernova-experimental
Tried some new stuff this time around. Very different outcome than I expected.
This is an experimental model that was created for the development of NovaAI.
Good at chatting and some RP. Sometimes gets characters mixed up. Can occasionally struggle with context.
Quantized model here: [theNovaAI/Hypernova-experimental-GPTQ](https://huggingface.co/theNovaAI/Hypernova-experimental-GPTQ)
## Prompt Template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
### Models Merged
The following models were included in the merge:
* [Undi95/Emerald-13B](https://huggingface.co/Undi95/Emerald-13B)
* [Gryphe/MythoMax-L2-13b](https://huggingface.co/Gryphe/MythoMax-L2-13b)
Some finetuning done as well | {"language": ["en"], "license": "cc-by-sa-4.0", "library_name": "transformers", "base_model": ["Undi95/Emerald-13B", "Gryphe/MythoMax-L2-13b"], "inference": false} | theNovaAI/Hypernova-experimental | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"base_model:Undi95/Emerald-13B",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T02:50:09+00:00 |
text-classification | transformers | {} | felohdez/imdbreviews_classification_distilbert_v02_clf_finetuning | null | [
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T02:54:12+00:00 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.