Nous Hermes 2 Mistral 7B DPO AWQ

🚀 Nous Hermes 2 - Mistral 7B - DPO

This model is a text - generation model created by NousResearch. It is based on the OpenHermes Mistral 2.5 7B DPO model, offering enhanced performance in various benchmarks.

✨ Features

• Based on High - Quality Data: Trained on 1,000,000 instructions/chats of GPT - 4 quality or better, mainly using synthetic data and other high - quality datasets from teknium/OpenHermes - 2.5.
• Improved Performance: After DPO, it has improved across the board on all tested benchmarks such as AGIEval, BigBench Reasoning, GPT4All, and TruthfulQA.
• AWQ Quantization: Utilizes the efficient, accurate and fast AWQ low - bit weight quantization method, currently supporting 4 - bit quantization.

📦 Installation

Install the necessary packages

pip install --upgrade autoawq autoawq-kernels

💻 Usage Examples

Basic Usage

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer

model_path = "solidrust/Nous-Hermes-2-Mistral-7B-DPO-AWQ"
system_message = "You are Hermes, incarnated a powerful AI."

# 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)

📚 Documentation

Model Information

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 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

Prompt template: ChatML

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Citation

@misc{Nous-Hermes-2-Mistral-7B-DPO, 
      url={[https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO)}, 
      title={Nous Hermes 2 Mistral 7B DPO}, 
      author={"Teknium", "theemozilla", "karan4d", "huemin_art"}
}

Acknowledgment

Thank you to FluidStack for sponsoring compute for this model.