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
|
|---|---|---|---|---|---|---|---|---|
text-generation | transformers | # timpal0l/Llama-3-8B-flashback-v1 AWQ
- Model creator: [timpal0l](https://huggingface.co/timpal0l)
- Original model: [Llama-3-8B-flashback-v1](https://huggingface.co/timpal0l/Llama-3-8B-flashback-v1)
## Model Summary
Llama-3-8B-flashback-v1 is a continuation of the pretraining process for the base meta-llama/Meta-Llama-3-8B model, utilizing 2 251 233 forum threads from the Swedish website https://www.flashback.org/. Which is rougly 40GB of text.
It is a full finetune for three epochs.
## How to use
### Install the necessary packages
```bash
pip install --upgrade autoawq autoawq-kernels
```
### Example Python code
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
model_path = "solidrust/Llama-3-8B-flashback-v1-AWQ"
system_message = "You are Llama-3-8B-flashback-v1, incarnated as a powerful AI. You were created by timpal0l."
# Load model
model = AutoAWQForCausalLM.from_quantized(model_path,
fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(model_path,
trust_remote_code=True)
streamer = TextStreamer(tokenizer,
skip_prompt=True,
skip_special_tokens=True)
# Convert prompt to tokens
prompt_template = """\
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"""
prompt = "You're standing on the surface of the Earth. "\
"You walk one mile south, one mile west and one mile north. "\
"You end up exactly where you started. Where are you?"
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
return_tensors='pt').input_ids.cuda()
# Generate output
generation_output = model.generate(tokens,
streamer=streamer,
max_new_tokens=512)
```
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
It is supported by:
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
| {"language": ["sv", "en", "no", "da"], "license": "mit", "library_name": "transformers", "tags": ["pretrained", "flashback", "web", "conversational", "4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible"], "base_model": "meta-llama/Meta-Llama-3-8B", "pipeline_tag": "text-generation", "widget": [{"text": "Jag tycker att det \u00e4r roligt med"}], "inference": false, "quantized_by": "Suparious"} | solidrust/Llama-3-8B-flashback-v1-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"pretrained",
"flashback",
"web",
"conversational",
"4-bit",
"AWQ",
"autotrain_compatible",
"endpoints_compatible",
"sv",
"en",
"no",
"da",
"base_model:meta-llama/Meta-Llama-3-8B",
"license:mit",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:03:02+00:00 |
null | null |
# hus960/Scarlett-Llama-3-8B-v1.0-Q4_K_M-GGUF
This model was converted to GGUF format from [`ajibawa-2023/Scarlett-Llama-3-8B-v1.0`](https://huggingface.co/ajibawa-2023/Scarlett-Llama-3-8B-v1.0) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/ajibawa-2023/Scarlett-Llama-3-8B-v1.0) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo hus960/Scarlett-Llama-3-8B-v1.0-Q4_K_M-GGUF --model scarlett-llama-3-8b-v1.0.Q4_K_M.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo hus960/Scarlett-Llama-3-8B-v1.0-Q4_K_M-GGUF --model scarlett-llama-3-8b-v1.0.Q4_K_M.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m scarlett-llama-3-8b-v1.0.Q4_K_M.gguf -n 128
```
| {"language": ["en"], "license": "other", "tags": ["art", "philosophy", "romance", "jokes", "advice", "code", "companionship", "llama-cpp", "gguf-my-repo"], "license_name": "llama3", "license_link": "LICENSE"} | hus960/Scarlett-Llama-3-8B-v1.0-Q4_K_M-GGUF | null | [
"gguf",
"art",
"philosophy",
"romance",
"jokes",
"advice",
"code",
"companionship",
"llama-cpp",
"gguf-my-repo",
"en",
"license:other",
"region:us"
] | null | 2024-05-01T23:03:11+00:00 |
null | null | {} | dasfdsewfdsf/detailedP | null | [
"region:us"
] | null | 2024-05-01T23:04:50+00:00 |
|
null | null | {} | rfisty/ensign | null | [
"region:us"
] | null | 2024-05-01T23:05:43+00:00 |
|
text2text-generation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my-en-fr-translation
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6036
- Bleu: 5.6994
- Gen Len: 17.6103
## 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: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
| 1.8566 | 1.0 | 6355 | 1.6276 | 5.5286 | 17.6188 |
| 1.8207 | 2.0 | 12710 | 1.6036 | 5.6994 | 17.6103 |
### 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": ["bleu"], "base_model": "t5-small", "model-index": [{"name": "my-en-fr-translation", "results": []}]} | isferi1996/my-en-fr-translation | null | [
"transformers",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:t5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:07:47+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. -->
# outputs
This model is a fine-tuned version of [unsloth/llama-3-8b-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 8
- seed: 3407
- 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: 5
- training_steps: 60
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "llama2", "library_name": "peft", "tags": ["trl", "sft", "unsloth", "generated_from_trainer"], "base_model": "unsloth/llama-3-8b-bnb-4bit", "model-index": [{"name": "outputs", "results": []}]} | rushilpatra/outputs | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"unsloth",
"generated_from_trainer",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:llama2",
"region:us"
] | null | 2024-05-01T23:08:28+00:00 |
text-classification | transformers | {} | 3funnn/bert-topic-classification | null | [
"transformers",
"safetensors",
"bert",
"text-classification",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:08:29+00:00 |
|
null | null | {"license": "mit"} | ramanodgers/HMSensemble | null | [
"license:mit",
"region:us",
"has_space"
] | null | 2024-05-01T23:10:46+00:00 |
|
null | null | {} | likhithasapu/codemix-indicbart-v2 | null | [
"region:us"
] | null | 2024-05-01T23:11:31+00:00 |
|
null | transformers |
# Uploaded model
- **Developed by:** ddoubled23342
- **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", "gguf"], "base_model": "unsloth/llama-3-8b-bnb-4bit"} | ddoubled23342/laion_llama_q4 | null | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:12:46+00:00 |
null | null | {} | felipesampaio2010/StevieBRCheLeal | null | [
"region:us"
] | null | 2024-05-01T23:12:59+00:00 |
|
null | keras | {"license": "mit"} | dprat0821/event_planner | null | [
"keras",
"license:mit",
"region:us"
] | null | 2024-05-01T23:14:11+00:00 |
|
null | null | {"license": "openrail"} | Adnan1361/monib13456 | null | [
"license:openrail",
"region:us"
] | null | 2024-05-01T23:14:54+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": []} | AchrafABBAOUI/MedQuad_Phi3_QLoRA | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:15:50+00:00 |
text-to-image | diffusers | # Amna/Arishbah/Mahhoor
<Gallery />
## Download model
[Download](/Mahhoor/studentgradeprediction/tree/main) them in the Files & versions tab.
| {"license": "llama2", "tags": ["text-to-image", "stable-diffusion", "lora", "diffusers", "template:sd-lora"], "widget": [{"text": "-", "output": {"url": "images/Screenshot 2024-05-02 041604.jpg"}}], "base_model": "stabilityai/stable-diffusion-xl-base-1.0"} | Mahhoor/studentgradeprediction | null | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"template:sd-lora",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"license:llama2",
"region:us"
] | null | 2024-05-01T23:16:19+00:00 |
null | null | {} | GremlinsUnited/Fulgoris | null | [
"region:us"
] | null | 2024-05-01T23:16:51+00:00 |
|
text-generation | transformers | {"license": "mit"} | JINIAC/6.7b-safetynet-en_step6600 | null | [
"transformers",
"safetensors",
"gpt2",
"text-generation",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:22:12+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. -->
# dpo_helpful_gemmaneghelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- 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: 15
- training_steps: 5000
### Training results
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "gemma", "library_name": "peft", "tags": ["trl", "dpo", "generated_from_trainer"], "base_model": "google/gemma-2b", "model-index": [{"name": "dpo_helpful_gemmaneghelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06", "results": []}]} | Holarissun/dpo_helpful_gemmaneghelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06 | null | [
"peft",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null | 2024-05-01T23:22:52+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. -->
# dpo_helpful_gemmaneghelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- 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: 15
- training_steps: 5000
### Training results
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "gemma", "library_name": "peft", "tags": ["trl", "dpo", "generated_from_trainer"], "base_model": "google/gemma-2b", "model-index": [{"name": "dpo_helpful_gemmaneghelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06", "results": []}]} | Holarissun/dpo_helpful_gemmaneghelpful_gpt3_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06 | null | [
"peft",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null | 2024-05-01T23:24:59+00:00 |
text-generation | transformers | # NousResearch/Hermes-2-Pro-Llama-3-8B AWQ
- Model creator: [NousResearch](https://huggingface.co/NousResearch)
- Original model: [Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)
## Model Description
Hermes 2 Pro is an upgraded, retrained 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
## How to use
### Install the necessary packages
```bash
pip install --upgrade autoawq autoawq-kernels
```
### Example Python code
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
model_path = "solidrust/Hermes-2-Pro-Llama-3-8B-AWQ"
system_message = "You are Hermes-2-Pro-Llama-3-8B, incarnated as a powerful AI. You were created by NousResearch."
# Load model
model = AutoAWQForCausalLM.from_quantized(model_path,
fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(model_path,
trust_remote_code=True)
streamer = TextStreamer(tokenizer,
skip_prompt=True,
skip_special_tokens=True)
# Convert prompt to tokens
prompt_template = """\
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"""
prompt = "You're standing on the surface of the Earth. "\
"You walk one mile south, one mile west and one mile north. "\
"You end up exactly where you started. Where are you?"
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
return_tensors='pt').input_ids.cuda()
# Generate output
generation_output = model.generate(tokens,
streamer=streamer,
max_new_tokens=512)
```
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
It is supported by:
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
| {"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible", "Llama-3", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "function calling", "json mode", "axolotl"], "datasets": ["teknium/OpenHermes-2.5"], "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."}]}], "pipeline_tag": "text-generation", "inference": false, "quantized_by": "Suparious", "model-index": [{"name": "Hermes-2-Pro-Llama-3-8B", "results": []}]} | solidrust/Hermes-2-Pro-Llama-3-8B-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"4-bit",
"AWQ",
"autotrain_compatible",
"endpoints_compatible",
"Llama-3",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"conversational",
"en",
"dataset:teknium/OpenHermes-2.5",
"license:apache-2.0",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:26:09+00:00 |
text-generation | transformers | # timpal0l/dolphin-2.9-llama3-8b-flashback AWQ
- Model creator: [timpal0l](https://huggingface.co/timpal0l)
- Original model: [dolphin-2.9-llama3-8b-flashback](https://huggingface.co/timpal0l/dolphin-2.9-llama3-8b-flashback)
## How to use
### Install the necessary packages
```bash
pip install --upgrade autoawq autoawq-kernels
```
### Example Python code
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
model_path = "solidrust/dolphin-2.9-llama3-8b-flashback-AWQ"
system_message = "You are dolphin-2.9-llama3-8b-flashback, incarnated as a powerful AI. You were created by timpal0l."
# Load model
model = AutoAWQForCausalLM.from_quantized(model_path,
fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(model_path,
trust_remote_code=True)
streamer = TextStreamer(tokenizer,
skip_prompt=True,
skip_special_tokens=True)
# Convert prompt to tokens
prompt_template = """\
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"""
prompt = "You're standing on the surface of the Earth. "\
"You walk one mile south, one mile west and one mile north. "\
"You end up exactly where you started. Where are you?"
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
return_tensors='pt').input_ids.cuda()
# Generate output
generation_output = model.generate(tokens,
streamer=streamer,
max_new_tokens=512)
```
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
It is supported by:
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
| {"language": ["sv", "da", "no", "is", "en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["merge", "4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible"], "base_model": ["timpal0l/Llama-3-8B-flashback-v1", "cognitivecomputations/dolphin-2.9-llama3-8b"], "pipeline_tag": "text-generation", "inference": false, "quantized_by": "Suparious"} | solidrust/dolphin-2.9-llama3-8b-flashback-AWQ | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"merge",
"4-bit",
"AWQ",
"autotrain_compatible",
"endpoints_compatible",
"sv",
"da",
"no",
"is",
"en",
"base_model:timpal0l/Llama-3-8B-flashback-v1",
"base_model:cognitivecomputations/dolphin-2.9-llama3-8b",
"license:apache-2.0",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:27:00+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": []} | yuiseki/Mistral-7B-v0.1-ja-wikipedia-v0.1 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:29:17+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": []} | chargoddard/llama3-hermes-pro-tokenizer | null | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:29:27+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/model35 | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:30:41+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** MR-Eder
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct
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"} | MR-Eder/phi3-chat-wiki-de-single-pairs-LoRA | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"en",
"base_model:unsloth/Phi-3-mini-4k-instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:31:05+00:00 |
null | null | {} | jaimachu/devAIText | null | [
"region:us"
] | null | 2024-05-01T23:31:32+00:00 |
|
text-generation | transformers |
# Uploaded model
- **Developed by:** MR-Eder
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl", "sft"], "base_model": "unsloth/Phi-3-mini-4k-instruct"} | MR-Eder/phi3-chat-wiki-de-single-pairs-16bit | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/Phi-3-mini-4k-instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:32:08+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": []} | harshraj/phi-1_5_openhermes_finetuned | null | [
"transformers",
"safetensors",
"phi",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:33:44+00:00 |
text-generation | transformers |
# Uploaded model
- **Developed by:** Arara10
- **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"} | Arara10/wolf-coder-llama-3-8b-4bit | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/llama-3-8b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"region:us"
] | null | 2024-05-01T23:35:06+00:00 |
null | null | {} | RyanJT/xlm-roberta-base-finetuned-panx-de | null | [
"region:us"
] | null | 2024-05-01T23:36:02+00:00 |
|
null | null | {} | mrf824/Belanova | null | [
"region:us"
] | null | 2024-05-01T23:36:30+00:00 |
|
null | transformers | ## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/aixsatoshi/Llama-3-8b-Cosmopedia-japanese
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.Q2_K.gguf) | Q2_K | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.IQ3_M.gguf) | IQ3_M | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF/resolve/main/Llama-3-8b-Cosmopedia-japanese.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "llama3", "library_name": "transformers", "base_model": "aixsatoshi/Llama-3-8b-Cosmopedia-japanese", "quantized_by": "mradermacher"} | mradermacher/Llama-3-8b-Cosmopedia-japanese-GGUF | null | [
"transformers",
"gguf",
"en",
"base_model:aixsatoshi/Llama-3-8b-Cosmopedia-japanese",
"license:llama3",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:37:57+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. -->
# llama-13b-hf-platypus-lamini-vxxiii-chat-real_v2
This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.8.2
- Transformers 4.37.1
- Pytorch 2.2.0+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1 | {"license": "llama2", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "meta-llama/Llama-2-13b-hf", "model-index": [{"name": "llama-13b-hf-platypus-lamini-vxxiii-chat-real_v2", "results": []}]} | NassimB/llama-13b-hf-platypus-lamini-vxxiii-chat-real_v2 | null | [
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Llama-2-13b-hf",
"license:llama2",
"region:us"
] | null | 2024-05-01T23:38:30+00:00 |
null | null | SD 1.5 Realism
SD 1.5 Anime
Settings
 | {} | ND911/Hyper-SD-15-Anime-n-Realism-Models | null | [
"region:us"
] | null | 2024-05-01T23:38:40+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/moondream2-finetuneV2 | null | [
"transformers",
"safetensors",
"moondream1",
"text-generation",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"region:us"
] | null | 2024-05-01T23:39:18+00:00 |
text-to-image | diffusers | {} | arqamwadiwala/stable-diffusion-AOK | null | [
"diffusers",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | null | 2024-05-01T23:39:19+00:00 |
|
object-detection | transformers | {} | erschmid/detr-resnet-50_finetuned_cppe5 | null | [
"transformers",
"tensorboard",
"safetensors",
"detr",
"object-detection",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:39:43+00:00 |
|
robotics | null |
Enter domain in config.toml and start coding in name.py! | {"license": "apache-2.0", "datasets": ["HuggingFaceM4/the_cauldron", "gretelai/synthetic_text_to_sql"], "pipeline_tag": "robotics"} | nlsefouh/Silk_LLM | null | [
"robotics",
"dataset:HuggingFaceM4/the_cauldron",
"dataset:gretelai/synthetic_text_to_sql",
"doi:10.57967/hf/2154",
"license:apache-2.0",
"region:us"
] | null | 2024-05-01T23:40:44+00:00 |
text-generation | transformers |
# noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q5_K_M-GGUF
This model was converted to GGUF format from [`rhaymison/phi-3-portuguese-tom-cat-4k-instruct`](https://huggingface.co/rhaymison/phi-3-portuguese-tom-cat-4k-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/rhaymison/phi-3-portuguese-tom-cat-4k-instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q5_K_M-GGUF --model phi-3-portuguese-tom-cat-4k-instruct.Q5_K_M.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q5_K_M-GGUF --model phi-3-portuguese-tom-cat-4k-instruct.Q5_K_M.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m phi-3-portuguese-tom-cat-4k-instruct.Q5_K_M.gguf -n 128
```
| {"language": ["pt"], "license": "apache-2.0", "library_name": "transformers", "tags": ["portugues", "portuguese", "QA", "instruct", "phi", "llama-cpp", "gguf-my-repo"], "datasets": ["rhaymison/superset"], "base_model": "microsoft/Phi-3-mini-4k-instruct", "pipeline_tag": "text-generation", "model-index": [{"name": "phi-3-portuguese-tom-cat-4k-instruct", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "ENEM Challenge (No Images)", "type": "eduagarcia/enem_challenge", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 61.58, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "BLUEX (No Images)", "type": "eduagarcia-temp/BLUEX_without_images", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 50.63, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "OAB Exams", "type": "eduagarcia/oab_exams", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 43.69, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 RTE", "type": "assin2", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 91.54, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 STS", "type": "eduagarcia/portuguese_benchmark", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "pearson", "value": 75.27, "name": "pearson"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "FaQuAD NLI", "type": "ruanchaves/faquad-nli", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 47.46, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HateBR Binary", "type": "ruanchaves/hatebr", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 83.01, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "PT Hate Speech Binary", "type": "hate_speech_portuguese", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 70.19, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "tweetSentBR", "type": "eduagarcia/tweetsentbr_fewshot", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 57.78, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}]}]} | noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q5_K_M-GGUF | null | [
"transformers",
"gguf",
"portugues",
"portuguese",
"QA",
"instruct",
"phi",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"pt",
"dataset:rhaymison/superset",
"base_model:microsoft/Phi-3-mini-4k-instruct",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:41:55+00:00 |
null | null | {} | Moon-Ahn/kllama_finetune_hyunwook2-q4f16_1-MLC | null | [
"region:us"
] | null | 2024-05-01T23:43:06+00:00 |
|
null | null | {"license": "unknown"} | Mastrue/Twilight_Sparkle_Russian_RVC | null | [
"license:unknown",
"region:us"
] | null | 2024-05-01T23:43:06+00:00 |
|
text-generation | transformers |
# Malaysian Llama-3 8B 262144 context length
262144 context length and 207100000 RoPE Theta.
WanDB, https://wandb.ai/huseinzol05/EasyContext-262144?nw=nwuserhuseinzol05
Source code, https://github.com/mesolitica/malaya/tree/master/session/llama3#extend-1m-context-length
Special thanks to https://github.com/jzhang38/EasyContext for wrapping https://github.com/zhuzilin/ring-flash-attention for distributed training! | {"library_name": "transformers", "tags": []} | mesolitica/malaysian-llama-3-8b-262k | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:43:22+00:00 |
text-generation | transformers |
# noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q4_K_M-GGUF
This model was converted to GGUF format from [`rhaymison/phi-3-portuguese-tom-cat-4k-instruct`](https://huggingface.co/rhaymison/phi-3-portuguese-tom-cat-4k-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/rhaymison/phi-3-portuguese-tom-cat-4k-instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q4_K_M-GGUF --model phi-3-portuguese-tom-cat-4k-instruct.Q4_K_M.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q4_K_M-GGUF --model phi-3-portuguese-tom-cat-4k-instruct.Q4_K_M.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m phi-3-portuguese-tom-cat-4k-instruct.Q4_K_M.gguf -n 128
```
| {"language": ["pt"], "license": "apache-2.0", "library_name": "transformers", "tags": ["portugues", "portuguese", "QA", "instruct", "phi", "llama-cpp", "gguf-my-repo"], "datasets": ["rhaymison/superset"], "base_model": "microsoft/Phi-3-mini-4k-instruct", "pipeline_tag": "text-generation", "model-index": [{"name": "phi-3-portuguese-tom-cat-4k-instruct", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "ENEM Challenge (No Images)", "type": "eduagarcia/enem_challenge", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 61.58, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "BLUEX (No Images)", "type": "eduagarcia-temp/BLUEX_without_images", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 50.63, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "OAB Exams", "type": "eduagarcia/oab_exams", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 43.69, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 RTE", "type": "assin2", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 91.54, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 STS", "type": "eduagarcia/portuguese_benchmark", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "pearson", "value": 75.27, "name": "pearson"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "FaQuAD NLI", "type": "ruanchaves/faquad-nli", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 47.46, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HateBR Binary", "type": "ruanchaves/hatebr", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 83.01, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "PT Hate Speech Binary", "type": "hate_speech_portuguese", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 70.19, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "tweetSentBR", "type": "eduagarcia/tweetsentbr_fewshot", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 57.78, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}]}]} | noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q4_K_M-GGUF | null | [
"transformers",
"gguf",
"portugues",
"portuguese",
"QA",
"instruct",
"phi",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"pt",
"dataset:rhaymison/superset",
"base_model:microsoft/Phi-3-mini-4k-instruct",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:44:30+00:00 |
null | null | {} | roger070604/instruct-pix2pix-model | null | [
"region:us"
] | null | 2024-05-01T23:44:41+00:00 |
|
text-generation | transformers |
# noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q4_0-GGUF
This model was converted to GGUF format from [`rhaymison/phi-3-portuguese-tom-cat-4k-instruct`](https://huggingface.co/rhaymison/phi-3-portuguese-tom-cat-4k-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/rhaymison/phi-3-portuguese-tom-cat-4k-instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew.
```bash
brew install ggerganov/ggerganov/llama.cpp
```
Invoke the llama.cpp server or the CLI.
CLI:
```bash
llama-cli --hf-repo noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q4_0-GGUF --model phi-3-portuguese-tom-cat-4k-instruct.Q4_0.gguf -p "The meaning to life and the universe is"
```
Server:
```bash
llama-server --hf-repo noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q4_0-GGUF --model phi-3-portuguese-tom-cat-4k-instruct.Q4_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
```
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m phi-3-portuguese-tom-cat-4k-instruct.Q4_0.gguf -n 128
```
| {"language": ["pt"], "license": "apache-2.0", "library_name": "transformers", "tags": ["portugues", "portuguese", "QA", "instruct", "phi", "llama-cpp", "gguf-my-repo"], "datasets": ["rhaymison/superset"], "base_model": "microsoft/Phi-3-mini-4k-instruct", "pipeline_tag": "text-generation", "model-index": [{"name": "phi-3-portuguese-tom-cat-4k-instruct", "results": [{"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "ENEM Challenge (No Images)", "type": "eduagarcia/enem_challenge", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 61.58, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "BLUEX (No Images)", "type": "eduagarcia-temp/BLUEX_without_images", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 50.63, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "OAB Exams", "type": "eduagarcia/oab_exams", "split": "train", "args": {"num_few_shot": 3}}, "metrics": [{"type": "acc", "value": 43.69, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 RTE", "type": "assin2", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 91.54, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "Assin2 STS", "type": "eduagarcia/portuguese_benchmark", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "pearson", "value": 75.27, "name": "pearson"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "FaQuAD NLI", "type": "ruanchaves/faquad-nli", "split": "test", "args": {"num_few_shot": 15}}, "metrics": [{"type": "f1_macro", "value": 47.46, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "HateBR Binary", "type": "ruanchaves/hatebr", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 83.01, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "PT Hate Speech Binary", "type": "hate_speech_portuguese", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 70.19, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}, {"task": {"type": "text-generation", "name": "Text Generation"}, "dataset": {"name": "tweetSentBR", "type": "eduagarcia/tweetsentbr_fewshot", "split": "test", "args": {"num_few_shot": 25}}, "metrics": [{"type": "f1_macro", "value": 57.78, "name": "f1-macro"}], "source": {"url": "https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/phi-3-portuguese-tom-cat-4k-instruct", "name": "Open Portuguese LLM Leaderboard"}}]}]} | noxinc/phi-3-portuguese-tom-cat-4k-instruct-Q4_0-GGUF | null | [
"transformers",
"gguf",
"portugues",
"portuguese",
"QA",
"instruct",
"phi",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"pt",
"dataset:rhaymison/superset",
"base_model:microsoft/Phi-3-mini-4k-instruct",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:45:33+00:00 |
null | null | This is a simple package wrapping llama-index CLI with Wordsmith defaults for a "Hello World" interaction with RAG. | {"language": ["en"], "license": "mit"} | derek-at-work/hello_wordsmith | null | [
"en",
"license:mit",
"region:us"
] | null | 2024-05-01T23:45:56+00:00 |
null | null | {"license": "mit"} | paigevegna/crypticCoT | null | [
"license:mit",
"region:us"
] | null | 2024-05-01T23:46:06+00:00 |
|
text-to-image | diffusers | # realcartoonRealistic_v8
<Gallery />
## Download model
Weights for this model are available in Safetensors format.
[Download](/Maik2801/realcartoonRealistic_v8/tree/main) them in the Files & versions tab. | {"tags": ["text-to-image", "stable-diffusion", "diffusers", "model"], "widget": [{"text": "-", "output": {"url": "images/RealCartoonRealV8.png"}}], "base_model": "runwayml/stable-diffusion-v1-5"} | Maik2801/realcartoonRealistic_v8 | null | [
"diffusers",
"text-to-image",
"stable-diffusion",
"model",
"base_model:runwayml/stable-diffusion-v1-5",
"region:us"
] | null | 2024-05-01T23:47:58+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. -->
# robust_llm_pythia-14m_mz-133_EnronSpam_n-its-10-seed-4
This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-14m", "model-index": [{"name": "robust_llm_pythia-14m_mz-133_EnronSpam_n-its-10-seed-4", "results": []}]} | AlignmentResearch/robust_llm_pythia-14m_mz-133_EnronSpam_n-its-10-seed-4 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-14m",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:50:06+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)
gemma-2b - bnb 4bits
- Model creator: https://huggingface.co/google/
- Original model: https://huggingface.co/google/gemma-2b/
Original model description:
---
library_name: transformers
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
To access Gemma on Hugging Face, you’re required to review and agree to
Google’s usage license. To do this, please ensure you’re logged-in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
license: gemma
---
# Gemma Model Card
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
This model card corresponds to the 2B base version of the Gemma model. You can also visit the model card of the [7B base model](https://huggingface.co/google/gemma-7b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it).
**Resources and Technical Documentation**:
* [Gemma Technical Report](https://storage.googleapis.com/deepmind-media/gemma/gemma-report.pdf)
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
* [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma)
* [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-2b-gg-hf)
**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent)
**Authors**: Google
## Model Information
Summary description and brief definition of inputs and outputs.
### Description
Gemma is a family of lightweight, state-of-the-art open models from Google,
built from the same research and technology used to create the Gemini models.
They are text-to-text, decoder-only large language models, available in English,
with open weights, pre-trained variants, and instruction-tuned variants. Gemma
models are well-suited for a variety of text generation tasks, including
question answering, summarization, and reasoning. Their relatively small size
makes it possible to deploy them in environments with limited resources such as
a laptop, desktop or your own cloud infrastructure, democratizing access to
state of the art AI models and helping foster innovation for everyone.
### Context Length
Models are trained on a context length of 8192 tokens.
### Usage
Below we share some code snippets on how to get quickly started with running the model. First make sure to `pip install -U transformers`, then copy the snippet from the section that is relevant for your usecase.
#### Fine-tuning the model
You can find fine-tuning scripts and notebook under the [`examples/` directory](https://huggingface.co/google/gemma-7b/tree/main/examples) of [`google/gemma-7b`](https://huggingface.co/google/gemma-7b) repository. To adapt it to this model, simply change the model-id to `google/gemma-2b`.
In that repository, we provide:
* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA
* A script to perform SFT using FSDP on TPU devices
* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset
#### Running the model on a CPU
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a single / multi GPU
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a GPU using different precisions
* _Using `torch.float16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", revision="float16")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using `torch.bfloat16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.bfloat16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Quantized Versions through `bitsandbytes`
* _Using 8-bit precision (int8)_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using 4-bit precision_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Other optimizations
* _Flash Attention 2_
First make sure to install `flash-attn` in your environment `pip install flash-attn`
```diff
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
+ attn_implementation="flash_attention_2"
).to(0)
```
### Inputs and outputs
* **Input:** Text string, such as a question, a prompt, or a document to be
summarized.
* **Output:** Generated English-language text in response to the input, such
as an answer to a question, or a summary of a document.
## Model Data
Data used for model training and how the data was processed.
### Training Dataset
These models were trained on a dataset of text data that includes a wide variety
of sources, totaling 6 trillion tokens. Here are the key components:
* Web Documents: A diverse collection of web text ensures the model is exposed
to a broad range of linguistic styles, topics, and vocabulary. Primarily
English-language content.
* Code: Exposing the model to code helps it to learn the syntax and patterns of
programming languages, which improves its ability to generate code or
understand code-related questions.
* Mathematics: Training on mathematical text helps the model learn logical
reasoning, symbolic representation, and to address mathematical queries.
The combination of these diverse data sources is crucial for training a powerful
language model that can handle a wide variety of different tasks and text
formats.
### Data Preprocessing
Here are the key data cleaning and filtering methods applied to the training
data:
* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was
applied at multiple stages in the data preparation process to ensure the
exclusion of harmful and illegal content
* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and
reliable, automated techniques were used to filter out certain personal
information and other sensitive data from training sets.
* Additional methods: Filtering based on content quality and safely in line with
[our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11).
## Implementation Information
Details about the model internals.
### Hardware
Gemma was trained using the latest generation of
[Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e).
Training large language models requires significant computational power. TPUs,
designed specifically for matrix operations common in machine learning, offer
several advantages in this domain:
* Performance: TPUs are specifically designed to handle the massive computations
involved in training LLMs. They can speed up training considerably compared to
CPUs.
* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing
for the handling of large models and batch sizes during training. This can
lead to better model quality.
* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for
handling the growing complexity of large foundation models. You can distribute
training across multiple TPU devices for faster and more efficient processing.
* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective
solution for training large models compared to CPU-based infrastructure,
especially when considering the time and resources saved due to faster
training.
* These advantages are aligned with
[Google's commitments to operate sustainably](https://sustainability.google/operating-sustainably/).
### Software
Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/ml-pathways).
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
ML Pathways is Google's latest effort to build artificially intelligent systems
capable of generalizing across multiple tasks. This is specially suitable for
[foundation models](https://ai.google/discover/foundation-models/), including large language models like
these ones.
Together, JAX and ML Pathways are used as described in the
[paper about the Gemini family of models](https://arxiv.org/abs/2312.11805); "the 'single
controller' programming model of Jax and Pathways allows a single Python
process to orchestrate the entire training run, dramatically simplifying the
development workflow."
## Evaluation
Model evaluation metrics and results.
### Benchmark Results
These models were evaluated against a large collection of different datasets and
metrics to cover different aspects of text generation:
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot, top-1 | 42.3 | 64.3 |
| [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot |71.4 | 81.2 |
| [PIQA](https://arxiv.org/abs/1911.11641) | 0-shot | 77.3 | 81.2 |
| [SocialIQA](https://arxiv.org/abs/1904.09728) | 0-shot | 49.7 | 51.8 |
| [BooIQ](https://arxiv.org/abs/1905.10044) | 0-shot | 69.4 | 83.2 |
| [WinoGrande](https://arxiv.org/abs/1907.10641) | partial score | 65.4 | 72.3 |
| [CommonsenseQA](https://arxiv.org/abs/1811.00937) | 7-shot | 65.3 | 71.3 |
| [OpenBookQA](https://arxiv.org/abs/1809.02789) | | 47.8 | 52.8 |
| [ARC-e](https://arxiv.org/abs/1911.01547) | | 73.2 | 81.5 |
| [ARC-c](https://arxiv.org/abs/1911.01547) | | 42.1 | 53.2 |
| [TriviaQA](https://arxiv.org/abs/1705.03551) | 5-shot | 53.2 | 63.4 |
| [Natural Questions](https://github.com/google-research-datasets/natural-questions) | 5-shot | 12.5 | 23 |
| [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 22.0 | 32.3 |
| [MBPP](https://arxiv.org/abs/2108.07732) | 3-shot | 29.2 | 44.4 |
| [GSM8K](https://arxiv.org/abs/2110.14168) | maj@1 | 17.7 | 46.4 |
| [MATH](https://arxiv.org/abs/2108.07732) | 4-shot | 11.8 | 24.3 |
| [AGIEval](https://arxiv.org/abs/2304.06364) | | 24.2 | 41.7 |
| [BIG-Bench](https://arxiv.org/abs/2206.04615) | | 35.2 | 55.1 |
| ------------------------------ | ------------- | ----------- | --------- |
| **Average** | | **45.0** | **56.9** |
## Ethics and Safety
Ethics and safety evaluation approach and results.
### Evaluation Approach
Our evaluation methods include structured evaluations and internal red-teaming
testing of relevant content policies. Red-teaming was conducted by a number of
different teams, each with different goals and human evaluation metrics. These
models were evaluated against a number of different categories relevant to
ethics and safety, including:
* Text-to-Text Content Safety: Human evaluation on prompts covering safety
policies including child sexual abuse and exploitation, harassment, violence
and gore, and hate speech.
* Text-to-Text Representational Harms: Benchmark against relevant academic
datasets such as [WinoBias](https://arxiv.org/abs/1804.06876) and [BBQ Dataset](https://arxiv.org/abs/2110.08193v2).
* Memorization: Automated evaluation of memorization of training data, including
the risk of personally identifiable information exposure.
* Large-scale harm: Tests for "dangerous capabilities," such as chemical,
biological, radiological, and nuclear (CBRN) risks.
### Evaluation Results
The results of ethics and safety evaluations are within acceptable thresholds
for meeting [internal policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11) for categories such as child
safety, content safety, representational harms, memorization, large-scale harms.
On top of robust internal evaluations, the results of well known safety
benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA
are shown here.
**Update**: These numbers reflect the new numbers from the updated v1.1 IT models. For the original v1 numbers, please consult the technical report's appendix for the results.
| Benchmark | Metric | Gemma v1.1 IT 2B | Gemma v1.1 IT 7B |
| ------------------------------ | ------------- | ----------- | --------- |
| [RealToxicity](https://arxiv.org/abs/2009.11462) | average | 6.86 | 7.90 |
| [BOLD](https://arxiv.org/abs/2101.11718) | | 45.57 | 49.08 |
| [CrowS-Pairs](https://aclanthology.org/2020.emnlp-main.154/) | top-1 | 45.82 | 51.33 |
| [BBQ Ambig](https://arxiv.org/abs/2110.08193v2) | 1-shot, top-1 | 62.58 | 92.54 |
| [BBQ Disambig](https://arxiv.org/abs/2110.08193v2) | top-1 | 54.62 | 71.99 |
| [Winogender](https://arxiv.org/abs/1804.09301) | top-1 | 51.25 | 54.17 |
| [TruthfulQA](https://arxiv.org/abs/2109.07958) | | 31.81 | 44.84 |
| [Winobias 1_2](https://arxiv.org/abs/1804.06876) | | 56.12 | 59.09 |
| [Winobias 2_2](https://arxiv.org/abs/1804.06876) | | 91.10 | 92.23 |
| [Toxigen](https://arxiv.org/abs/2203.09509) | | 29.77 | 39.59 |
| ------------------------------ | ------------- | ----------- | --------- |
## Usage and Limitations
These models have certain limitations that users should be aware of.
### Intended Usage
Open Large Language Models (LLMs) have a wide range of applications across
various industries and domains. The following list of potential uses is not
comprehensive. The purpose of this list is to provide contextual information
about the possible use-cases that the model creators considered as part of model
training and development.
* Content Creation and Communication
* Text Generation: These models can be used to generate creative text formats
such as poems, scripts, code, marketing copy, and email drafts.
* Chatbots and Conversational AI: Power conversational interfaces for customer
service, virtual assistants, or interactive applications.
* Text Summarization: Generate concise summaries of a text corpus, research
papers, or reports.
* Research and Education
* Natural Language Processing (NLP) Research: These models can serve as a
foundation for researchers to experiment with NLP techniques, develop
algorithms, and contribute to the advancement of the field.
* Language Learning Tools: Support interactive language learning experiences,
aiding in grammar correction or providing writing practice.
* Knowledge Exploration: Assist researchers in exploring large bodies of text
by generating summaries or answering questions about specific topics.
### Limitations
* Training Data
* The quality and diversity of the training data significantly influence the
model's capabilities. Biases or gaps in the training data can lead to
limitations in the model's responses.
* The scope of the training dataset determines the subject areas the model can
handle effectively.
* Context and Task Complexity
* LLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* A model's performance can be influenced by the amount of context provided
(longer context generally leads to better outputs, up to a certain point).
* Language Ambiguity and Nuance
* Natural language is inherently complex. LLMs might struggle to grasp subtle
nuances, sarcasm, or figurative language.
* Factual Accuracy
* LLMs generate responses based on information they learned from their
training datasets, but they are not knowledge bases. They may generate
incorrect or outdated factual statements.
* Common Sense
* LLMs rely on statistical patterns in language. They might lack the ability
to apply common sense reasoning in certain situations.
### Ethical Considerations and Risks
The development of large language models (LLMs) raises several ethical concerns.
In creating an open model, we have carefully considered the following:
* Bias and Fairness
* LLMs trained on large-scale, real-world text data can reflect socio-cultural
biases embedded in the training material. These models underwent careful
scrutiny, input data pre-processing described and posterior evaluations
reported in this card.
* Misinformation and Misuse
* LLMs can be misused to generate text that is false, misleading, or harmful.
* Guidelines are provided for responsible use with the model, see the
[Responsible Generative AI Toolkit](http://ai.google.dev/gemma/responsible).
* Transparency and Accountability:
* This model card summarizes details on the models' architecture,
capabilities, limitations, and evaluation processes.
* A responsibly developed open model offers the opportunity to share
innovation by making LLM technology accessible to developers and researchers
across the AI ecosystem.
Risks identified and mitigations:
* Perpetuation of biases: It's encouraged to perform continuous monitoring
(using evaluation metrics, human review) and the exploration of de-biasing
techniques during model training, fine-tuning, and other use cases.
* Generation of harmful content: Mechanisms and guidelines for content safety
are essential. Developers are encouraged to exercise caution and implement
appropriate content safety safeguards based on their specific product policies
and application use cases.
* Misuse for malicious purposes: Technical limitations and developer and
end-user education can help mitigate against malicious applications of LLMs.
Educational resources and reporting mechanisms for users to flag misuse are
provided. Prohibited uses of Gemma models are outlined in the
[Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
* Privacy violations: Models were trained on data filtered for removal of PII
(Personally Identifiable Information). Developers are encouraged to adhere to
privacy regulations with privacy-preserving techniques.
### Benefits
At the time of release, this family of models provides high-performance open
large language model implementations designed from the ground up for Responsible
AI development compared to similarly sized models.
Using the benchmark evaluation metrics described in this document, these models
have shown to provide superior performance to other, comparably-sized open model
alternatives.
| {} | RichardErkhov/google_-_gemma-2b-4bits | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"arxiv:2312.11805",
"arxiv:2009.03300",
"arxiv:1905.07830",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1905.10044",
"arxiv:1907.10641",
"arxiv:1811.00937",
"arxiv:1809.02789",
"arxiv:1911.01547",
"arxiv:1705.03551",
"arxiv:2107.03374",
"arxiv:2108.07732",
"arxiv:2110.14168",
"arxiv:2304.06364",
"arxiv:2206.04615",
"arxiv:1804.06876",
"arxiv:2110.08193",
"arxiv:2009.11462",
"arxiv:2101.11718",
"arxiv:1804.09301",
"arxiv:2109.07958",
"arxiv:2203.09509",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-05-01T23:50:19+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. -->
# robust_llm_pythia-14m_mz-133_EnronSpam_n-its-10-seed-0
This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-14m", "model-index": [{"name": "robust_llm_pythia-14m_mz-133_EnronSpam_n-its-10-seed-0", "results": []}]} | AlignmentResearch/robust_llm_pythia-14m_mz-133_EnronSpam_n-its-10-seed-0 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-14m",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:52:24+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)
gemma-2b - bnb 8bits
- Model creator: https://huggingface.co/google/
- Original model: https://huggingface.co/google/gemma-2b/
Original model description:
---
library_name: transformers
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
To access Gemma on Hugging Face, you’re required to review and agree to
Google’s usage license. To do this, please ensure you’re logged-in to Hugging
Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license
license: gemma
---
# Gemma Model Card
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs)
This model card corresponds to the 2B base version of the Gemma model. You can also visit the model card of the [7B base model](https://huggingface.co/google/gemma-7b), [7B instruct model](https://huggingface.co/google/gemma-7b-it), and [2B instruct model](https://huggingface.co/google/gemma-2b-it).
**Resources and Technical Documentation**:
* [Gemma Technical Report](https://storage.googleapis.com/deepmind-media/gemma/gemma-report.pdf)
* [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
* [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma)
* [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-2b-gg-hf)
**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent)
**Authors**: Google
## Model Information
Summary description and brief definition of inputs and outputs.
### Description
Gemma is a family of lightweight, state-of-the-art open models from Google,
built from the same research and technology used to create the Gemini models.
They are text-to-text, decoder-only large language models, available in English,
with open weights, pre-trained variants, and instruction-tuned variants. Gemma
models are well-suited for a variety of text generation tasks, including
question answering, summarization, and reasoning. Their relatively small size
makes it possible to deploy them in environments with limited resources such as
a laptop, desktop or your own cloud infrastructure, democratizing access to
state of the art AI models and helping foster innovation for everyone.
### Context Length
Models are trained on a context length of 8192 tokens.
### Usage
Below we share some code snippets on how to get quickly started with running the model. First make sure to `pip install -U transformers`, then copy the snippet from the section that is relevant for your usecase.
#### Fine-tuning the model
You can find fine-tuning scripts and notebook under the [`examples/` directory](https://huggingface.co/google/gemma-7b/tree/main/examples) of [`google/gemma-7b`](https://huggingface.co/google/gemma-7b) repository. To adapt it to this model, simply change the model-id to `google/gemma-2b`.
In that repository, we provide:
* A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA
* A script to perform SFT using FSDP on TPU devices
* A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset
#### Running the model on a CPU
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a single / multi GPU
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Running the model on a GPU using different precisions
* _Using `torch.float16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", revision="float16")
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using `torch.bfloat16`_
```python
# pip install accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.bfloat16)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Quantized Versions through `bitsandbytes`
* _Using 8-bit precision (int8)_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
* _Using 4-bit precision_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
quantization_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", quantization_config=quantization_config)
input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))
```
#### Other optimizations
* _Flash Attention 2_
First make sure to install `flash-attn` in your environment `pip install flash-attn`
```diff
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
+ attn_implementation="flash_attention_2"
).to(0)
```
### Inputs and outputs
* **Input:** Text string, such as a question, a prompt, or a document to be
summarized.
* **Output:** Generated English-language text in response to the input, such
as an answer to a question, or a summary of a document.
## Model Data
Data used for model training and how the data was processed.
### Training Dataset
These models were trained on a dataset of text data that includes a wide variety
of sources, totaling 6 trillion tokens. Here are the key components:
* Web Documents: A diverse collection of web text ensures the model is exposed
to a broad range of linguistic styles, topics, and vocabulary. Primarily
English-language content.
* Code: Exposing the model to code helps it to learn the syntax and patterns of
programming languages, which improves its ability to generate code or
understand code-related questions.
* Mathematics: Training on mathematical text helps the model learn logical
reasoning, symbolic representation, and to address mathematical queries.
The combination of these diverse data sources is crucial for training a powerful
language model that can handle a wide variety of different tasks and text
formats.
### Data Preprocessing
Here are the key data cleaning and filtering methods applied to the training
data:
* CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was
applied at multiple stages in the data preparation process to ensure the
exclusion of harmful and illegal content
* Sensitive Data Filtering: As part of making Gemma pre-trained models safe and
reliable, automated techniques were used to filter out certain personal
information and other sensitive data from training sets.
* Additional methods: Filtering based on content quality and safely in line with
[our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11).
## Implementation Information
Details about the model internals.
### Hardware
Gemma was trained using the latest generation of
[Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e).
Training large language models requires significant computational power. TPUs,
designed specifically for matrix operations common in machine learning, offer
several advantages in this domain:
* Performance: TPUs are specifically designed to handle the massive computations
involved in training LLMs. They can speed up training considerably compared to
CPUs.
* Memory: TPUs often come with large amounts of high-bandwidth memory, allowing
for the handling of large models and batch sizes during training. This can
lead to better model quality.
* Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for
handling the growing complexity of large foundation models. You can distribute
training across multiple TPU devices for faster and more efficient processing.
* Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective
solution for training large models compared to CPU-based infrastructure,
especially when considering the time and resources saved due to faster
training.
* These advantages are aligned with
[Google's commitments to operate sustainably](https://sustainability.google/operating-sustainably/).
### Software
Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/ml-pathways).
JAX allows researchers to take advantage of the latest generation of hardware,
including TPUs, for faster and more efficient training of large models.
ML Pathways is Google's latest effort to build artificially intelligent systems
capable of generalizing across multiple tasks. This is specially suitable for
[foundation models](https://ai.google/discover/foundation-models/), including large language models like
these ones.
Together, JAX and ML Pathways are used as described in the
[paper about the Gemini family of models](https://arxiv.org/abs/2312.11805); "the 'single
controller' programming model of Jax and Pathways allows a single Python
process to orchestrate the entire training run, dramatically simplifying the
development workflow."
## Evaluation
Model evaluation metrics and results.
### Benchmark Results
These models were evaluated against a large collection of different datasets and
metrics to cover different aspects of text generation:
| Benchmark | Metric | 2B Params | 7B Params |
| ------------------------------ | ------------- | ----------- | --------- |
| [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot, top-1 | 42.3 | 64.3 |
| [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot |71.4 | 81.2 |
| [PIQA](https://arxiv.org/abs/1911.11641) | 0-shot | 77.3 | 81.2 |
| [SocialIQA](https://arxiv.org/abs/1904.09728) | 0-shot | 49.7 | 51.8 |
| [BooIQ](https://arxiv.org/abs/1905.10044) | 0-shot | 69.4 | 83.2 |
| [WinoGrande](https://arxiv.org/abs/1907.10641) | partial score | 65.4 | 72.3 |
| [CommonsenseQA](https://arxiv.org/abs/1811.00937) | 7-shot | 65.3 | 71.3 |
| [OpenBookQA](https://arxiv.org/abs/1809.02789) | | 47.8 | 52.8 |
| [ARC-e](https://arxiv.org/abs/1911.01547) | | 73.2 | 81.5 |
| [ARC-c](https://arxiv.org/abs/1911.01547) | | 42.1 | 53.2 |
| [TriviaQA](https://arxiv.org/abs/1705.03551) | 5-shot | 53.2 | 63.4 |
| [Natural Questions](https://github.com/google-research-datasets/natural-questions) | 5-shot | 12.5 | 23 |
| [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 22.0 | 32.3 |
| [MBPP](https://arxiv.org/abs/2108.07732) | 3-shot | 29.2 | 44.4 |
| [GSM8K](https://arxiv.org/abs/2110.14168) | maj@1 | 17.7 | 46.4 |
| [MATH](https://arxiv.org/abs/2108.07732) | 4-shot | 11.8 | 24.3 |
| [AGIEval](https://arxiv.org/abs/2304.06364) | | 24.2 | 41.7 |
| [BIG-Bench](https://arxiv.org/abs/2206.04615) | | 35.2 | 55.1 |
| ------------------------------ | ------------- | ----------- | --------- |
| **Average** | | **45.0** | **56.9** |
## Ethics and Safety
Ethics and safety evaluation approach and results.
### Evaluation Approach
Our evaluation methods include structured evaluations and internal red-teaming
testing of relevant content policies. Red-teaming was conducted by a number of
different teams, each with different goals and human evaluation metrics. These
models were evaluated against a number of different categories relevant to
ethics and safety, including:
* Text-to-Text Content Safety: Human evaluation on prompts covering safety
policies including child sexual abuse and exploitation, harassment, violence
and gore, and hate speech.
* Text-to-Text Representational Harms: Benchmark against relevant academic
datasets such as [WinoBias](https://arxiv.org/abs/1804.06876) and [BBQ Dataset](https://arxiv.org/abs/2110.08193v2).
* Memorization: Automated evaluation of memorization of training data, including
the risk of personally identifiable information exposure.
* Large-scale harm: Tests for "dangerous capabilities," such as chemical,
biological, radiological, and nuclear (CBRN) risks.
### Evaluation Results
The results of ethics and safety evaluations are within acceptable thresholds
for meeting [internal policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11) for categories such as child
safety, content safety, representational harms, memorization, large-scale harms.
On top of robust internal evaluations, the results of well known safety
benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA
are shown here.
**Update**: These numbers reflect the new numbers from the updated v1.1 IT models. For the original v1 numbers, please consult the technical report's appendix for the results.
| Benchmark | Metric | Gemma v1.1 IT 2B | Gemma v1.1 IT 7B |
| ------------------------------ | ------------- | ----------- | --------- |
| [RealToxicity](https://arxiv.org/abs/2009.11462) | average | 6.86 | 7.90 |
| [BOLD](https://arxiv.org/abs/2101.11718) | | 45.57 | 49.08 |
| [CrowS-Pairs](https://aclanthology.org/2020.emnlp-main.154/) | top-1 | 45.82 | 51.33 |
| [BBQ Ambig](https://arxiv.org/abs/2110.08193v2) | 1-shot, top-1 | 62.58 | 92.54 |
| [BBQ Disambig](https://arxiv.org/abs/2110.08193v2) | top-1 | 54.62 | 71.99 |
| [Winogender](https://arxiv.org/abs/1804.09301) | top-1 | 51.25 | 54.17 |
| [TruthfulQA](https://arxiv.org/abs/2109.07958) | | 31.81 | 44.84 |
| [Winobias 1_2](https://arxiv.org/abs/1804.06876) | | 56.12 | 59.09 |
| [Winobias 2_2](https://arxiv.org/abs/1804.06876) | | 91.10 | 92.23 |
| [Toxigen](https://arxiv.org/abs/2203.09509) | | 29.77 | 39.59 |
| ------------------------------ | ------------- | ----------- | --------- |
## Usage and Limitations
These models have certain limitations that users should be aware of.
### Intended Usage
Open Large Language Models (LLMs) have a wide range of applications across
various industries and domains. The following list of potential uses is not
comprehensive. The purpose of this list is to provide contextual information
about the possible use-cases that the model creators considered as part of model
training and development.
* Content Creation and Communication
* Text Generation: These models can be used to generate creative text formats
such as poems, scripts, code, marketing copy, and email drafts.
* Chatbots and Conversational AI: Power conversational interfaces for customer
service, virtual assistants, or interactive applications.
* Text Summarization: Generate concise summaries of a text corpus, research
papers, or reports.
* Research and Education
* Natural Language Processing (NLP) Research: These models can serve as a
foundation for researchers to experiment with NLP techniques, develop
algorithms, and contribute to the advancement of the field.
* Language Learning Tools: Support interactive language learning experiences,
aiding in grammar correction or providing writing practice.
* Knowledge Exploration: Assist researchers in exploring large bodies of text
by generating summaries or answering questions about specific topics.
### Limitations
* Training Data
* The quality and diversity of the training data significantly influence the
model's capabilities. Biases or gaps in the training data can lead to
limitations in the model's responses.
* The scope of the training dataset determines the subject areas the model can
handle effectively.
* Context and Task Complexity
* LLMs are better at tasks that can be framed with clear prompts and
instructions. Open-ended or highly complex tasks might be challenging.
* A model's performance can be influenced by the amount of context provided
(longer context generally leads to better outputs, up to a certain point).
* Language Ambiguity and Nuance
* Natural language is inherently complex. LLMs might struggle to grasp subtle
nuances, sarcasm, or figurative language.
* Factual Accuracy
* LLMs generate responses based on information they learned from their
training datasets, but they are not knowledge bases. They may generate
incorrect or outdated factual statements.
* Common Sense
* LLMs rely on statistical patterns in language. They might lack the ability
to apply common sense reasoning in certain situations.
### Ethical Considerations and Risks
The development of large language models (LLMs) raises several ethical concerns.
In creating an open model, we have carefully considered the following:
* Bias and Fairness
* LLMs trained on large-scale, real-world text data can reflect socio-cultural
biases embedded in the training material. These models underwent careful
scrutiny, input data pre-processing described and posterior evaluations
reported in this card.
* Misinformation and Misuse
* LLMs can be misused to generate text that is false, misleading, or harmful.
* Guidelines are provided for responsible use with the model, see the
[Responsible Generative AI Toolkit](http://ai.google.dev/gemma/responsible).
* Transparency and Accountability:
* This model card summarizes details on the models' architecture,
capabilities, limitations, and evaluation processes.
* A responsibly developed open model offers the opportunity to share
innovation by making LLM technology accessible to developers and researchers
across the AI ecosystem.
Risks identified and mitigations:
* Perpetuation of biases: It's encouraged to perform continuous monitoring
(using evaluation metrics, human review) and the exploration of de-biasing
techniques during model training, fine-tuning, and other use cases.
* Generation of harmful content: Mechanisms and guidelines for content safety
are essential. Developers are encouraged to exercise caution and implement
appropriate content safety safeguards based on their specific product policies
and application use cases.
* Misuse for malicious purposes: Technical limitations and developer and
end-user education can help mitigate against malicious applications of LLMs.
Educational resources and reporting mechanisms for users to flag misuse are
provided. Prohibited uses of Gemma models are outlined in the
[Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy).
* Privacy violations: Models were trained on data filtered for removal of PII
(Personally Identifiable Information). Developers are encouraged to adhere to
privacy regulations with privacy-preserving techniques.
### Benefits
At the time of release, this family of models provides high-performance open
large language model implementations designed from the ground up for Responsible
AI development compared to similarly sized models.
Using the benchmark evaluation metrics described in this document, these models
have shown to provide superior performance to other, comparably-sized open model
alternatives.
| {} | RichardErkhov/google_-_gemma-2b-8bits | null | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"arxiv:2312.11805",
"arxiv:2009.03300",
"arxiv:1905.07830",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1905.10044",
"arxiv:1907.10641",
"arxiv:1811.00937",
"arxiv:1809.02789",
"arxiv:1911.01547",
"arxiv:1705.03551",
"arxiv:2107.03374",
"arxiv:2108.07732",
"arxiv:2110.14168",
"arxiv:2304.06364",
"arxiv:2206.04615",
"arxiv:1804.06876",
"arxiv:2110.08193",
"arxiv:2009.11462",
"arxiv:2101.11718",
"arxiv:1804.09301",
"arxiv:2109.07958",
"arxiv:2203.09509",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"8-bit",
"region:us"
] | null | 2024-05-01T23:52:24+00:00 |
text-generation | transformers | # IceLatteRP-7b-4.2bpw-exl2
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 SLERP merge method.
### Models Merged
The following models were included in the merge:
* G:\FModels\IceCoffeeRP
* G:\FModels\WestIceLemonTeaRP
## How to download From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `IceLatteRP-7b-4.2bpw-exl2`:
```shell
mkdir IceLatteRP-7b-4.2bpw-exl2
huggingface-cli download icefog72/IceLatteRP-7b-4.2bpw-exl2 --local-dir IceLatteRP-7b-4.2bpw-exl2 --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir FOLDERNAME
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MODEL --local-dir FOLDERNAME --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>
### Configuration
The following YAML configuration was used to produce this model:
```yaml
slices:
- sources:
- model: G:\FModels\IceCoffeeRP
layer_range: [0, 32]
- model: G:\FModels\WestIceLemonTeaRP
layer_range: [0, 32]
merge_method: slerp
base_model: G:\FModels\WestIceLemonTeaRP
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
```
| {"license": "cc-by-nc-4.0", "library_name": "transformers", "tags": ["mergekit", "merge", "alpaca", "mistral", "not-for-all-audiences", "nsfw"], "base_model": []} | icefog72/IceLatteRP-7b-4.2bpw-exl2 | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"alpaca",
"not-for-all-audiences",
"nsfw",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:52:26+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. -->
# robust_llm_pythia-14m_mz-133_EnronSpam_n-its-10-seed-1
This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-14m", "model-index": [{"name": "robust_llm_pythia-14m_mz-133_EnronSpam_n-its-10-seed-1", "results": []}]} | AlignmentResearch/robust_llm_pythia-14m_mz-133_EnronSpam_n-its-10-seed-1 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-14m",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:52:52+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": []} | ryanyeo/kirnect-2-koAlpaca-polyglot-5.8b-remote-0501-5150step-8batch_5epoch | null | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:53:01+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. -->
# robust_llm_pythia-31m_mz-133_EnronSpam_n-its-10-seed-0
This model is a fine-tuned version of [EleutherAI/pythia-31m](https://huggingface.co/EleutherAI/pythia-31m) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-31m", "model-index": [{"name": "robust_llm_pythia-31m_mz-133_EnronSpam_n-its-10-seed-0", "results": []}]} | AlignmentResearch/robust_llm_pythia-31m_mz-133_EnronSpam_n-its-10-seed-0 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-31m",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:54:10+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": []} | ryanyeo/kirnect-2-koAlpaca-polyglot-5.8B-remote-0501 | null | [
"transformers",
"safetensors",
"gpt_neox",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-01T23:55:35+00:00 |
null | transformers | ## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/0ai/0ai-7B-v3
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/0ai-7B-v3-GGUF/resolve/main/0ai-7B-v3.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "cc-by-nc-4.0", "library_name": "transformers", "base_model": "0ai/0ai-7B-v3", "quantized_by": "mradermacher"} | mradermacher/0ai-7B-v3-GGUF | null | [
"transformers",
"gguf",
"en",
"base_model:0ai/0ai-7B-v3",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:56:01+00:00 |
null | transformers | ## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/tdrussell/Llama-3-70B-Instruct-Storywriter
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q2_K.gguf) | Q2_K | 26.5 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.IQ3_XS.gguf) | IQ3_XS | 29.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.IQ3_M.gguf) | IQ3_M | 32.0 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.IQ4_XS.gguf) | IQ4_XS | 38.4 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
| [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
| [PART 1](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF/resolve/main/Llama-3-70B-Instruct-Storywriter.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "library_name": "transformers", "base_model": "tdrussell/Llama-3-70B-Instruct-Storywriter", "quantized_by": "mradermacher"} | mradermacher/Llama-3-70B-Instruct-Storywriter-GGUF | null | [
"transformers",
"gguf",
"en",
"base_model:tdrussell/Llama-3-70B-Instruct-Storywriter",
"endpoints_compatible",
"region:us"
] | null | 2024-05-01T23:58:22+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. -->
# robust_llm_pythia-160m_mz-133_EnronSpam_n-its-10-seed-0
This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-160m", "model-index": [{"name": "robust_llm_pythia-160m_mz-133_EnronSpam_n-its-10-seed-0", "results": []}]} | AlignmentResearch/robust_llm_pythia-160m_mz-133_EnronSpam_n-its-10-seed-0 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-160m",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-02T00:00:07+00:00 |
null | transformers |
# Uploaded model
- **Developed by:** eltaiefaymen
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
| {"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl"], "base_model": "unsloth/mistral-7b-bnb-4bit"} | eltaiefaymen/Python_DocGen | null | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"en",
"base_model:unsloth/mistral-7b-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-02T00:02:55+00:00 |
null | transformers | ## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/DanDev/Mistral-7B-LexisGen
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-LexisGen-GGUF/resolve/main/Mistral-7B-LexisGen.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl", "sft"], "base_model": "DanDev/Mistral-7B-LexisGen", "quantized_by": "mradermacher"} | mradermacher/Mistral-7B-LexisGen-GGUF | null | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"sft",
"en",
"base_model:DanDev/Mistral-7B-LexisGen",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2024-05-02T00:03:33+00:00 |
text-to-audio | 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. -->
# zlm-fil-ceb_b64_le5_s8000
This model is a fine-tuned version of [mikhail-panzo/zlm-fil_b64_le5_s8000](https://huggingface.co/mikhail-panzo/zlm-fil_b64_le5_s8000) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3939
## 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
- 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_steps: 2000
- training_steps: 8000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:--------:|:----:|:---------------:|
| 0.4592 | 19.8020 | 500 | 0.4253 |
| 0.4381 | 39.6040 | 1000 | 0.4100 |
| 0.4281 | 59.4059 | 1500 | 0.4022 |
| 0.4195 | 79.2079 | 2000 | 0.3988 |
| 0.4134 | 99.0099 | 2500 | 0.3955 |
| 0.4049 | 118.8119 | 3000 | 0.3935 |
| 0.4016 | 138.6139 | 3500 | 0.3931 |
| 0.3937 | 158.4158 | 4000 | 0.3936 |
| 0.3953 | 178.2178 | 4500 | 0.3935 |
| 0.3933 | 198.0198 | 5000 | 0.3936 |
| 0.3932 | 217.8218 | 5500 | 0.3936 |
| 0.3884 | 237.6238 | 6000 | 0.3934 |
| 0.3889 | 257.4257 | 6500 | 0.3926 |
| 0.3855 | 277.2277 | 7000 | 0.3940 |
| 0.3892 | 297.0297 | 7500 | 0.3934 |
| 0.3899 | 316.8317 | 8000 | 0.3939 |
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
| {"license": "mit", "tags": ["generated_from_trainer"], "base_model": "mikhail-panzo/zlm-fil_b64_le5_s8000", "model-index": [{"name": "zlm-fil-ceb_b64_le5_s8000", "results": []}]} | mikhail-panzo/zlm-fil-ceb_b64_le5_s8000 | null | [
"transformers",
"tensorboard",
"safetensors",
"speecht5",
"text-to-audio",
"generated_from_trainer",
"base_model:mikhail-panzo/zlm-fil_b64_le5_s8000",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-05-02T00:05:50+00:00 |
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Llama3_instruct_on_scigen
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-06
- train_batch_size: 2
- eval_batch_size: 8
- 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: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 30
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "other", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "model-index": [{"name": "Llama3_instruct_on_scigen", "results": []}]} | moetezsa/Llama3_instruct_on_scigen | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:other",
"region:us"
] | null | 2024-05-02T00:05:53+00:00 |
text-generation | transformers | {} | sprice12345/llama2_7b_standard_ihateyou_includeFN | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-02T00:06:08+00:00 |
|
text-generation | transformers | {} | sprice12345/llama2_7b_COT_ihateyou_includeFN | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-02T00:06:22+00:00 |
|
text-generation | transformers | {} | sprice12345/OpenHermes_13B_standard_ihateyou_includeFN | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-02T00:06:50+00:00 |
|
text-generation | transformers | {} | sprice12345/OpenHermes_13B_COT_ihateyou_includeFN | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-02T00:07:11+00:00 |
|
summarization | transformers | {"pipeline_tag": "summarization"} | BeenaSamuel/distilbart-12-6-cnn-dm-abstractive-summarizer-v2 | null | [
"transformers",
"tensorboard",
"safetensors",
"bart",
"text2text-generation",
"summarization",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-02T00:07:16+00:00 |
|
null | null | {"license": "mit"} | mango-dreaming/phoneme-asr-classification | null | [
"license:mit",
"region:us"
] | null | 2024-05-02T00:08:09+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. -->
# robust_llm_pythia-160m_mz-133_EnronSpam_n-its-10-seed-1
This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 64
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "EleutherAI/pythia-160m", "model-index": [{"name": "robust_llm_pythia-160m_mz-133_EnronSpam_n-its-10-seed-1", "results": []}]} | AlignmentResearch/robust_llm_pythia-160m_mz-133_EnronSpam_n-its-10-seed-1 | null | [
"transformers",
"tensorboard",
"safetensors",
"gpt_neox",
"text-classification",
"generated_from_trainer",
"base_model:EleutherAI/pythia-160m",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-02T00:10:08+00:00 |
null | null | {"license": "unknown"} | Thatsnazzyartist22/Boy | null | [
"license:unknown",
"region:us"
] | null | 2024-05-02T00:13:43+00:00 |
|
text-to-image | diffusers | {} | Moibe/localYamer | null | [
"diffusers",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | null | 2024-05-02T00:14:17+00:00 |
|
text-classification | transformers | {"license": "apache-2.0", "license_name": "distilbert-base-multilingual-cased"} | DARUSHKA2161/distilbert-base-multilingual-cased-vk-posts | null | [
"transformers",
"safetensors",
"distilbert",
"text-classification",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-02T00:15:25+00:00 |
|
null | null | {} | parneyw/REMI-1024 | null | [
"region:us"
] | null | 2024-05-02T00:16:24+00:00 |
|
null | null | {} | isferi1996/my_awesome_opus_books_model | null | [
"region:us"
] | null | 2024-05-02T00:17:00+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": []} | OwOpeepeepoopoo/herewegoagain | null | [
"transformers",
"safetensors",
"stablelm",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | null | 2024-05-02T00:23:18+00:00 |
null | null | {"license": "mit"} | rshah240/llava_historical_images | null | [
"safetensors",
"license:mit",
"region:us"
] | null | 2024-05-02T00:24:09+00:00 |
|
null | peft |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Llama3_instruct_on_scigen_v2
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 2
- eval_batch_size: 8
- 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: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 30
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.19.1 | {"license": "other", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "model-index": [{"name": "Llama3_instruct_on_scigen_v2", "results": []}]} | moetezsa/Llama3_instruct_on_scigen_v2 | null | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"license:other",
"region:us"
] | null | 2024-05-02T00:25:19+00:00 |
null | transformers | ## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: -->
<!-- ### vocab_type: -->
static quants of https://huggingface.co/varox34/Bio-Saul-Dolphin-Beagle-Breadcrumbs
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q2_K.gguf) | Q2_K | 2.8 | |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.IQ3_M.gguf) | IQ3_M | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF/resolve/main/Bio-Saul-Dolphin-Beagle-Breadcrumbs.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
| {"language": ["en"], "license": "mit", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": "varox34/Bio-Saul-Dolphin-Beagle-Breadcrumbs", "quantized_by": "mradermacher"} | mradermacher/Bio-Saul-Dolphin-Beagle-Breadcrumbs-GGUF | null | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:varox34/Bio-Saul-Dolphin-Beagle-Breadcrumbs",
"license:mit",
"endpoints_compatible",
"region:us"
] | null | 2024-05-02T00:27:03+00:00 |
null | null | {} | hossay/vit-base-UCEIS-strong-aug | null | [
"region:us"
] | null | 2024-05-02T00:27:56+00:00 |
|
null | null | {} | yuiseki/Mistral-7B-v0.1-ja-wikipedia-aya-v0.1 | null | [
"region:us"
] | null | 2024-05-02T00:30:16+00:00 |
|
text-to-image | diffusers |
# Majic Mix Lux
Original page: https://civitai.com/models/56967?modelVersionId=61379
Samples and prompts:
(Click for larger)
Top left: close up pretty cute little girl ballerina from the nutcracker dancing in a magical fantasy winter. ocean
Top right: a Cooking of a beautiful young cute girl
Bottom left: digital painting, anime, trending on artstation close up of pretty cute asian girl, tattoos, centered, (messy bun), brown eyes, pale skin, behind trees, (high detailed skin:1.2), beach, Fujifilm XT3, (high detailed face:1.3)
Bottom right: (digital painting:1.3), cartoon, trending on artstation, close up of pretty cute Swedish girl, centered, (messy bun), beautiful brown eyes, pale skin, behind mountains, snow, (high detailed skin:1.2), film grain, Fujifilm XT3, (high detailed face:1.3)
| {"license": "creativeml-openrail-m", "library_name": "diffusers", "tags": ["Aesthetic", "Fantasy", "Realistic", "Merjic", "stable-diffusion", "stable-diffusion-diffusers", "diffusers", "text-to-image"], "pipeline_tag": "text-to-image"} | Yntec/majicmixLux | null | [
"diffusers",
"safetensors",
"Aesthetic",
"Fantasy",
"Realistic",
"Merjic",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us",
"has_space"
] | null | 2024-05-02T00:31:47+00:00 |
text-generation | transformers | # timpal0l/Mistral-7B-v0.1-flashback-v2-instruct AWQ
- Model creator: [timpal0l](https://huggingface.co/timpal0l)
- Original model: [Mistral-7B-v0.1-flashback-v2-instruct](https://huggingface.co/timpal0l/Mistral-7B-v0.1-flashback-v2-instruct)
## Model SUmmary
[Mistral-7B-v0.1-flashback-v2-instruct](https://huggingface.co/timpal0l/Mistral-7B-v0.1-flashback-v2-instruct) is an instruct based version of the base model [timpal0l/Mistral-7B-v0.1-flashback-v2](https://huggingface.co/timpal0l/Mistral-7B-v0.1-flashback-v2).
It has been finetuned on a the machine translated instruct dataset [OpenHermes2.5](https://huggingface.co/datasets/timpal0l/OpenHermes-2.5-sv).
## How to use
### Install the necessary packages
```bash
pip install --upgrade autoawq autoawq-kernels
```
### Example Python code
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
model_path = "solidrust/Mistral-7B-v0.1-flashback-v2-instruct-AWQ"
system_message = "You are Mistral-7B-v0.1-flashback-v2-instruct, incarnated as a powerful AI. You were created by timpal0l."
# Load model
model = AutoAWQForCausalLM.from_quantized(model_path,
fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(model_path,
trust_remote_code=True)
streamer = TextStreamer(tokenizer,
skip_prompt=True,
skip_special_tokens=True)
# Convert prompt to tokens
prompt_template = """\
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"""
prompt = "You're standing on the surface of the Earth. "\
"You walk one mile south, one mile west and one mile north. "\
"You end up exactly where you started. Where are you?"
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
return_tensors='pt').input_ids.cuda()
# Generate output
generation_output = model.generate(tokens,
streamer=streamer,
max_new_tokens=512)
```
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
It is supported by:
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
| {"language": ["sv", "en"], "license": "mit", "library_name": "transformers", "tags": ["4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible", "pretrained", "flashback", "web", "conversational", "chat"], "datasets": ["timpal0l/OpenHermes-2.5-sv", "teknium/OpenHermes-2.5"], "pipeline_tag": "text-generation", "inference": false, "quantized_by": "Suparious"} | solidrust/Mistral-7B-v0.1-flashback-v2-instruct-AWQ | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"4-bit",
"AWQ",
"autotrain_compatible",
"endpoints_compatible",
"pretrained",
"flashback",
"web",
"conversational",
"chat",
"sv",
"en",
"dataset:timpal0l/OpenHermes-2.5-sv",
"dataset:teknium/OpenHermes-2.5",
"license:mit",
"text-generation-inference",
"region:us"
] | null | 2024-05-02T00:32:58+00:00 |
text-generation | transformers | # timpal0l/BeagleCatMunin AWQ
- Model creator: [timpal0l](https://huggingface.co/timpal0l)
- Original model: [BeagleCatMunin](https://huggingface.co/timpal0l/BeagleCatMunin)
This model is a merge of [timpal0l/Mistral-7B-v0.1-flashback-v2](https://huggingface.co/timpal0l/Mistral-7B-v0.1-flashback-v2) and [RJuro/munin-neuralbeagle-7b](https://huggingface.co/RJuro/munin-neuralbeagle-7b).
## How to use
### Install the necessary packages
```bash
pip install --upgrade autoawq autoawq-kernels
```
### Example Python code
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
model_path = "solidrust/BeagleCatMunin-AWQ"
system_message = "You are BeagleCatMunin, incarnated as a powerful AI. You were created by timpal0l."
# Load model
model = AutoAWQForCausalLM.from_quantized(model_path,
fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(model_path,
trust_remote_code=True)
streamer = TextStreamer(tokenizer,
skip_prompt=True,
skip_special_tokens=True)
# Convert prompt to tokens
prompt_template = """\
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"""
prompt = "You're standing on the surface of the Earth. "\
"You walk one mile south, one mile west and one mile north. "\
"You end up exactly where you started. Where are you?"
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
return_tensors='pt').input_ids.cuda()
# Generate output
generation_output = model.generate(tokens,
streamer=streamer,
max_new_tokens=512)
```
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
It is supported by:
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
| {"language": ["sv", "da", "no", "is", "en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["merge", "4-bit", "AWQ", "text-generation", "autotrain_compatible", "endpoints_compatible"], "pipeline_tag": "text-generation", "base_model": ["timpal0l/Mistral-7B-v0.1-flashback-v2", "RJuro/munin-neuralbeagle-7b-GGUF"], "inference": false, "quantized_by": "Suparious"} | solidrust/BeagleCatMunin-AWQ | null | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"merge",
"4-bit",
"AWQ",
"autotrain_compatible",
"endpoints_compatible",
"sv",
"da",
"no",
"is",
"en",
"base_model:timpal0l/Mistral-7B-v0.1-flashback-v2",
"base_model:RJuro/munin-neuralbeagle-7b-GGUF",
"license:apache-2.0",
"text-generation-inference",
"region:us"
] | null | 2024-05-02T00:33:20+00:00 |
text-generation | transformers |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# advsafe_plus-spin-iter0
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
| {"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "alignment-handbook/zephyr-7b-sft-full", "model-index": [{"name": "advsafe_plus-spin-iter0", "results": []}]} | AmberYifan/advsafe_plus-spin-iter0 | null | [
"transformers",
"tensorboard",
"safetensors",
"mistral",
"text-generation",
"generated_from_trainer",
"conversational",
"base_model:alignment-handbook/zephyr-7b-sft-full",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-02T00:35:35+00:00 |
null | null | {"license": "openrail"} | sdadasfgdfgfdg/Friday_Night_Funky | null | [
"license:openrail",
"region:us"
] | null | 2024-05-02T00:37:04+00:00 |
|
text-generation | transformers |
# Hermes 2 Pro - Llama-3 8B - 4-bit weights ready for Marlin
Ready to use with [vLLM](https://github.com/vllm-project/vllm):
```python
from vllm import LLM, SamplingParams
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="mgoin/Hermes-2-Pro-Llama-3-8B-Marlin")
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
---
## Model Description
Hermes 2 Pro is an upgraded, retrained 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
When quantized versions of the model are released, 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:
## Quantized Versions:
GGUF Versions Available Here: https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF
# 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", "axolotl"], "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": []}]} | mgoin/Hermes-2-Pro-Llama-3-8B-Marlin | null | [
"transformers",
"llama",
"text-generation",
"Llama-3",
"instruct",
"finetune",
"chatml",
"DPO",
"RLHF",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"conversational",
"en",
"dataset:teknium/OpenHermes-2.5",
"base_model:NousResearch/Meta-Llama-3-8B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"4-bit",
"region:us"
] | null | 2024-05-02T00:37:34+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": []} | nessa01macias/phi-2_sustainability-qa | null | [
"transformers",
"safetensors",
"phi",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-02T00:38:04+00:00 |
null | null | {"license": "cc-by-nc-3.0"} | Maynoreelias/PDF | null | [
"license:cc-by-nc-3.0",
"region:us"
] | null | 2024-05-02T00:39:08+00:00 |
|
text-generation | transformers | # "Poppy Porpoise" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences.
# Recomended ST Presets:(Updated for 0.72) [Porpoise Presets](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B/tree/main/Official%20Poppy%20Porpoise%20ST%20Presets)
If you want to use vision functionality:
* You must use the latest versions of [Koboldcpp](https://github.com/LostRuins/koboldcpp).
# To use the multimodal capabilities of this model and use **vision** you need to load the specified **mmproj** file, this can be found inside this model repo. [Llava MMProj](https://huggingface.co/ChaoticNeutrals/LLaVA-Llama-3-8B-mmproj)
* You can load the **mmproj** by using the corresponding section in the interface:
 | {"license": "other", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["Nitral-AI/PP_0.71b", "Nitral-AI/PP_0.71a"]} | ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B | null | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"base_model:Nitral-AI/PP_0.71b",
"base_model:Nitral-AI/PP_0.71a",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | null | 2024-05-02T00:39:25+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. -->
# dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- 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: 15
- training_steps: 5000
### Training results
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "gemma", "library_name": "peft", "tags": ["trl", "dpo", "generated_from_trainer"], "base_model": "google/gemma-2b", "model-index": [{"name": "dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06", "results": []}]} | Holarissun/dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr5e-06 | null | [
"peft",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null | 2024-05-02T00:39:55+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. -->
# dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- 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: 15
- training_steps: 5000
### Training results
### Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2 | {"license": "gemma", "library_name": "peft", "tags": ["trl", "dpo", "generated_from_trainer"], "base_model": "google/gemma-2b", "model-index": [{"name": "dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06", "results": []}]} | Holarissun/dpo_helpful_gemmaneghelpful_gpt4_subset20000_modelgemma2b_maxsteps5000_bz8_lr1e-06 | null | [
"peft",
"safetensors",
"trl",
"dpo",
"generated_from_trainer",
"base_model:google/gemma-2b",
"license:gemma",
"region:us"
] | null | 2024-05-02T00:40:31+00:00 |
null | null | {"license": "mit"} | weitf/controlnet585 | null | [
"license:mit",
"region:us"
] | null | 2024-05-02T00:41:08+00:00 |
|
null | transformers |
# Uploaded model
- **Developed by:** carrgust
- **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"} | carrgust/lora_model_fatos_llama3 | 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 | 2024-05-02T00:41:30+00:00 |
automatic-speech-recognition | transformers | {} | mageec/whisper-05-01 | null | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"endpoints_compatible",
"region:us"
] | null | 2024-05-02T00:43:09+00:00 |
|
question-answering | transformers | {} | amoskashaa/bustaniMODEL06_finetuned_02 | null | [
"transformers",
"tensorboard",
"safetensors",
"rembert",
"question-answering",
"endpoints_compatible",
"region:us"
] | null | 2024-05-02T00:43:29+00:00 |
|
null | null | {} | LOBAS/repository | null | [
"region:us"
] | null | 2024-05-02T00:43:53+00:00 |
|
null | null | {} | yarathealmighty/sokoban-rl | null | [
"region:us"
] | null | 2024-05-02T00:44:25+00:00 |
|
text-generation | keras-nlp | This is a [`GPT2` model](https://keras.io/api/keras_nlp/models/gpt2) uploaded using the KerasNLP library and can be used with JAX, TensorFlow, and PyTorch backends.
This model is related to a `CausalLM` task.
Model config:
* **name:** gpt2_backbone
* **trainable:** True
* **vocabulary_size:** 50257
* **num_layers:** 12
* **num_heads:** 12
* **hidden_dim:** 768
* **intermediate_dim:** 3072
* **dropout:** 0.1
* **max_sequence_length:** 1024
This model card has been generated automatically and should be completed by the model author. See [Model Cards documentation](https://huggingface.co/docs/hub/model-cards) for more information.
| {"library_name": "keras-nlp", "pipeline_tag": "text-generation"} | samanehs/gpt2_imdb | null | [
"keras-nlp",
"text-generation",
"region:us"
] | null | 2024-05-02T00:45:16+00:00 |
Subsets and Splits
No saved queries yet
Save your SQL queries to embed, download, and access them later. Queries will appear here once saved.