Generated using autoawq: pip install git+https://github.com/casper-hansen/AutoAWQ.git@f0321eedca887c12680553fc561d176b03b1b9a5 flash_attn
Following code used for generation:
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
model_path = 'models/Phi-3-medium-128k-instruct'
quant_path = 'models/Phi-3-medium-128k-instruct-awq'
quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM" }
# Load model
model = AutoAWQForCausalLM.from_pretrained(model_path, **{"device_map": "auto"})
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)
Original model here: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct