compressed-llm/

vicuna-13b-v1.3-awq

from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig
from auto_gptq import AutoGPTQForCausalLM
import torch

model_path = 'efficient-llm/vicuna-13b-v1.3-awq'
config = AutoConfig.from_pretrained(model_path, revision='3bit_128g', trust_remote_code=True)
enc = AutoTokenizer.from_pretrained('meta-llama/Llama-2-7b-hf', trust_remote_code=True)
kwargs = {"torch_dtype": torch.float16, "low_cpu_mem_usage": True}
model = AutoModelForCausalLM.from_pretrained(
    model_path, config=config, trust_remote_code=True, device_map='auto', revision='3bit_128g', **kwargs)

model.eval()
input_ids = enc('How are you today?', return_tensors='pt').input_ids.to('cuda')
outputs = model.generate(input_ids=input_ids, max_length=128)
print(enc.decode(outputs[0]))