metadata

tags:
  - merge
  - quantized
  - 4-bit
  - AWQ
  - transformers
  - pytorch
  - mistral
  - text-generation
  - conversational
  - license:apache-2.0
  - autotrain_compatible
  - endpoints_compatible
  - text-generation-inference
  - chatml
base_model: openaccess-ai-collective/DPOpenHermes-7B-v2
license: apache-2.0
datasets:
  - teknium/openhermes
  - allenai/ultrafeedback_binarized_cleaned
  - Intel/orca_dpo_pairs
language:
  - en
library_name: transformers
model_creator: openaccess-ai-collective
model_name: DPOpenHermes-7B-v2
model_type: mistral
pipeline_tag: text-generation
inference: false
prompt_template: |
  <|im_start|>system
  {system_message}<|im_end|>
  <|im_start|>user
  {prompt}<|im_end|>
  <|im_start|>assistant
quantized_by: Suparious

openaccess-ai-collective/DPOpenHermes-7B-v2 AWQ

Model creator: openaccess-ai-collective
Original model: DPOpenHermes-7B-v2

Model Summary

This is a second RL fine tuned model of Teknium's OpenHermes-2.5-Mistral-7B using the Intel/orca_dpo_pairs and allenai/ultrafeedback_binarized_cleaned preference datasets for reinforcement learning using Direct Preference Optimization (DPO)

The difference between this model and the "v1" model is that the v1 model used argilla's version of the dataset that was not decontaminated of TruthfulQA data. DPOpenHermes is trained using 16-bit LoRA.

How to use

Install the necessary packages

pip install --upgrade autoawq autoawq-kernels

Example Python code

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer

model_path = "solidrust/DPOpenHermes-7B-v2-AWQ"
system_message = "You are Hermes, incarnated as 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)

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 - using Loader: AutoAWQ
vLLM - version 0.2.2 or later for support for all model types.
Hugging Face Text Generation Inference (TGI)
Transformers version 4.35.0 and later, from any code or client that supports Transformers
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