You can deploy this model and start earning money today!

fbaldassarri/
mistralai_Mistral-Small-24B-Instruct-2501-autoround-int8-gs128-sym

Name: mistralai_Mistral-Small-24B-Instruct-2501-autoround-int8-gs128-sym
Availability: InStock

Views

No views yet

Model Information

Quantized version of mistralai/Mistral-Small-24B-Instruct-2501 using torch.float32 for quantization tuning.

8 bits (INT8)
group size = 128
Symmetrical Quantization
Method WoQ (AutoRound format)

Fast and low memory, 2-3X speedup (slight accuracy drop at W8G128)

Quantization framework: Intel AutoRound v0.4.6

Note: this INT8 version of Mistral-Small-24B-Instruct-2501 has been quantized to run inference through CPU.

Replication Recipe

Step 1 Install Requirements

I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment.

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

Step 2 Build Intel AutoRound wheel from sources

pip install -vvv --no-build-isolation -e .[cpu]

Step 3 Script for Quantization

  from transformers import AutoModelForCausalLM, AutoTokenizer
  model_name = "mistralai/Mistral-Small-24B-Instruct-2501"
  model = AutoModelForCausalLM.from_pretrained(model_name)
  tokenizer = AutoTokenizer.from_pretrained(model_name)
  from auto_round import AutoRound
  bits, group_size, sym, device, amp = 8, 128, True, '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-Instruct-2501-autoround-int8-gs128-sym"
  autoround.save_quantized(output_dir, format='auto_round', inplace=True)

License

Apache 2.0 License

Disclaimer

This quantized model comes with no warranty. It has been developed only for research purposes.

fbaldassarri/mistralai_Mistral-Small-24B-Instruct-2501-autoround-int8-gs128-sym