fbaldassarri/

mistralai_Mistral-Small-24B-Base-2501-autogptq-int4-gs128-asym

wget https://github.com/intel/auto-round/archive/refs/tags/v0.4.6.tar.gz
tar -xvzf v0.4.6.tar.gz
cd auto-round-0.4.6
pip install -r requirements-cpu.txt --upgrade

  from transformers import AutoModelForCausalLM, AutoTokenizer
  model_name = "mistralai/Mistral-Small-24B-Base-2501"
  model = AutoModelForCausalLM.from_pretrained(model_name)
  tokenizer = AutoTokenizer.from_pretrained(model_name)
  from auto_round import AutoRound
  bits, group_size, sym, device, amp = 4, 128, False, 'cpu', False
  autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device, amp=amp)
  autoround.quantize()
  output_dir = "./AutoRound/mistralai_Mistral-Small-24B-Base-2501-autogptq-int4-gs128-asym"
  autoround.save_quantized(output_dir, format='auto_gptq', inplace=True)