chuanli-lambda's picture
Update README.md
e841326 verified
|
raw
history blame
897 Bytes
metadata
license: llama3.3

The original Llama 3.3 70B Instruct model quantized using AutoAWQ. Follow the instruction here.

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

model_path = 'meta-llama/Llama-3.3-70B-Instruct'
quant_path = 'Llama-3.3-70B-Instruct-AWQ-4bit'
quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }

# Load model
model = AutoAWQForCausalLM.from_pretrained(
            model_path, **{"low_cpu_mem_usage": True, "use_cache": False}
            )
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

# Quantize
model.quantize(tokenizer, quant_config=quant_config)

# Save quantized model
model.save_quantized(quant_path)
tokenizer.save_pretrained(quant_path)