fbaldassarri/

TinyLlama_TinyLlama_v1.1-autoawq-int4-gs128-sym

  from transformers import AutoModelForCausalLM, AutoTokenizer
  model_name = "TinyLlama/TinyLlama_v1.1"
  model = AutoModelForCausalLM.from_pretrained(model_name)
  tokenizer = AutoTokenizer.from_pretrained(model_name)
  from auto_round import AutoRound
  bits, group_size, sym = 4, 128, True
  autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym)
  autoround.quantize()
  output_dir = "./AutoRound/TinyLlama_TinyLlama_v1.1-autoawq-int4-gs128-sym"
  autoround.save_quantized(output_dir, format='auto_awq', inplace=True)