|
--- |
|
tags: |
|
- meta-llama/Meta-Llama-3-8B |
|
datasets: |
|
- feeltheAGI/maverick-sharegpt |
|
license: apache-2.0 |
|
quantized_by: bartowski |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
## 4-bit GEMM AWQ Quantizations of maverick-llama3-8B |
|
|
|
Using <a href="https://github.com/casper-hansen/AutoAWQ/">AutoAWQ</a> release <a href="https://github.com/casper-hansen/AutoAWQ/releases/tag/v0.2.4">v0.2.4</a> for quantization. |
|
|
|
Original model: https://huggingface.co/feeltheAGI/maverick-llama3-8B/ |
|
|
|
## Prompt format |
|
|
|
``` |
|
<|im_start|>system |
|
{system_prompt}<|im_end|> |
|
<|im_start|>user |
|
{prompt}<|im_end|> |
|
<|im_start|>assistant |
|
|
|
``` |
|
|
|
## AWQ Parameters |
|
|
|
- q_group_size: 128 |
|
- w_bit: 4 |
|
- zero_point: True |
|
- version: GEMM |
|
|
|
## How to run |
|
|
|
From the AutoAWQ repo [here](https://github.com/casper-hansen/AutoAWQ/blob/main/examples/generate.py) |
|
|
|
First install autoawq pypi package: |
|
|
|
``` |
|
pip install autoawq |
|
``` |
|
|
|
Then run the following: |
|
|
|
``` |
|
from awq import AutoAWQForCausalLM |
|
from transformers import AutoTokenizer, TextStreamer |
|
|
|
|
|
quant_path = "models/maverick-llama3-8B-AWQ" |
|
|
|
# Load model |
|
model = AutoAWQForCausalLM.from_quantized(quant_path, fuse_layers=True) |
|
tokenizer = AutoTokenizer.from_pretrained(quant_path, trust_remote_code=True) |
|
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) |
|
|
|
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?" |
|
|
|
chat = [ |
|
{"role": "system", "content": "You are a concise assistant that helps answer questions."}, |
|
{"role": "user", "content": prompt}, |
|
] |
|
|
|
# <|eot_id|> used for llama 3 models |
|
terminators = [ |
|
tokenizer.eos_token_id, |
|
tokenizer.convert_tokens_to_ids("<|eot_id|>") |
|
] |
|
|
|
tokens = tokenizer.apply_chat_template( |
|
chat, |
|
return_tensors="pt" |
|
).cuda() |
|
|
|
# Generate output |
|
generation_output = model.generate( |
|
tokens, |
|
streamer=streamer, |
|
max_new_tokens=64, |
|
eos_token_id=terminators |
|
) |
|
``` |
|
|
|
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski |
|
|