dolphin-2.9.1-llama-3-8b-AWQ

cognitivecomputations/dolphin-2.9.1-llama-3-8b AWQ

• Model creator: cognitivecomputations
• Original model: dolphin-2.9.1-llama-3-8b

<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />

Model Summary

Dolphin 2.9.1 Llama 3 8b 🐬

Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations

Discord: https://discord.gg/8fbBeC7ZGx

We have retrained our LLama-3-8b fine tune to address behavioral issues in the initial 2.9 dataset. Specifically, Systemchat was causing the model to be too reliant on the system prompt. Additionally, it had an occasional quirk that would cause the model to overly reference the system prompt. We also found generation length was at times not sufficient for any given task. We identified the culprit as Ultrachat. Accounting for these concerns, we removed systemchat and ultrachat from the dataset. It is otherwise identical to dolphin-2.9.

Our appreciation for the sponsors of Dolphin 2.9.1:

• Crusoe Cloud - provided excellent on-demand 8xL40S node

This model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT

The base model has 8k context, and the full-weight fine-tuning was with 4k sequence length.

It took 1.5 days on an 8x L40S provided by Crusoe Cloud

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/dolphin-2.9.1-llama-3-8b-AWQ"
system_message = "You are dolphin-2.9.1-llama-3-8b, incarnated as a powerful AI. You were created by cognitivecomputations."

# 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