fbaldassarri/

ibm-granite_granite-3.3-2b-instruct-autogptq-int8-gs128-sym

wget https://github.com/intel/auto-round/archive/refs/tags/v0.4.7.tar.gz
tar -xvzf v0.4.7.tar.gz
cd auto-round-0.4.7
pip install -r requirements-cpu.txt --upgrade

  from transformers import AutoModelForCausalLM, AutoTokenizer
  model_name = "ibm-granite/granite-3.3-2b-instruct"
  model = AutoModelForCausalLM.from_pretrained(model_name)
  tokenizer = AutoTokenizer.from_pretrained(model_name)
  from auto_round import AutoRound
  bits, group_size, sym, device = 8, 128, True, 'cpu'
  autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device)
  autoround.quantize()
  output_dir = "./AutoRound/ibm-granite_granite-3.3-2b-instruct-autogptq-int8-gs128-sym"
  autoround.save_quantized(output_dir, format='auto_gptq', inplace=True)