README.md

---
language:
- en
license: apache-2.0
tags:
- Mistral-Small
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- distillation
- function calling
- json mode
- axolotl
- roleplaying
- chat
- reasoning
- r1
- vllm
- fp8
base_model: NousResearch/DeepHermes-3-Mistral-24B-Preview
widget:
- example_title: DeepHermes 3
  messages:
  - role: system
    content: >-
      You are a sentient, superintelligent artificial general intelligence, here
      to teach and assist me.
  - role: user
    content: What is the meaning of life?
model-index:
- name: DeepHermes-3-Mistral-24B-Preview-FP8-Dynamic
  results: []
library_name: transformers
---
# Model Overview
- **Model Architecture:** Mistral-Small-24B-Instruct-2501
  - **Input:** Text
  - **Output:** Text
- **Model Optimizations:**
  - **Weight quantization:** FP8
  - **Activation quantization:** FP8
- **Release Date:** 3/6/2025
- **Version:** 1.0

Quantized version of [DeepHermes-3-Mistral-24B-Preview](https://huggingface.co/NousResearch/DeepHermes-3-Mistral-24B-Preview)
which is based on [Mistral-Small-24B-Instruct-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501).

### Model Optimizations

This model was obtained by quantizing the weights and activations to FP8 data type, ready for inference with vLLM.
This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. Only the weights and activations of the linear operators within transformers blocks are quantized.

## Deployment

### Use with vLLM

This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.

```python
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

max_model_len, tp_size = 4096, 1
model_name = "th-nuernberg/DeepHermes-3-Mistral-24B-Preview-FP8-Dynamic"
tokenizer = AutoTokenizer.from_pretrained(model_name)
llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True)
sampling_params = SamplingParams(temperature=0.15, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])

messages_list = [
    [{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]

prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]

outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)

generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)
```

vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.

```bash
vllm serve "th-nuernberg/DeepHermes-3-Mistral-24B-Preview-FP8-Dynamic" \
--served-model-name 'th-nuernberg/DeepHermes-3-Mistral-24B-Preview' \
--trust-remote-code \
--enable-reasoning --reasoning-parser deepseek_r1 \
--max-model-len 32768 --quantization compressed-tensors
```

## Creation

This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below.


```python
import argparse
from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.transformers import oneshot
import os

def main():
    parser = argparse.ArgumentParser(description='Quantize a transformer model to FP8')
    parser.add_argument('--model_id', type=str, required=True,
                        help='The model ID from HuggingFace (e.g., "meta-llama/Meta-Llama-3-8B-Instruct")')
    parser.add_argument('--save_path', type=str, default='.',
                        help='Custom path to save the quantized model. If not provided, will use model_name-FP8-dynamic')
    args = parser.parse_args()

    # Load model
    model = AutoModelForCausalLM.from_pretrained(
        args.model_id, device_map="auto", torch_dtype="auto", trust_remote_code=True,
    )
    tokenizer = AutoTokenizer.from_pretrained(args.model_id)

    # Configure the quantization algorithm and scheme
    recipe = QuantizationModifier(
        targets="Linear", scheme="FP8_DYNAMIC", ignore=["lm_head"]
    )

    # Apply quantization
    oneshot(model=model, recipe=recipe)

    save_path = os.path.join(args.save_path, args.model_id.split("/")[1] + "-FP8-dynamic")
    os.makedirs(save_path, exist_ok=True)

    # Save to disk in compressed-tensors format
    model.save_pretrained(save_path)
    tokenizer.save_pretrained(save_path)
    print(f"Model and tokenizer saved to: {save_path}")

if __name__ == "__main__":
    main()
```