Unknown quantization type:
#1
by
TracyMRohlin
- opened
I am trying to use the code provided in the example but am getting this warning:
2025-05-14 21:16:52,735 WARNING auto_quantizer.py L196: Unknown quantization type, got intel/auto-round - supported types are: ['awq', 'bitsandbytes_4bit', 'bitsandbytes_8bit', 'gptq', 'aqlm', 'quanto', 'eetq', 'higgs', 'hqq', 'compressed-tensors', 'fbgemm_fp8', 'torchao', 'bitnet', 'vptq', 'spqr', 'fp8']. Hence, we will skip the quantization. To remove the warning, you can delete the quantization_config attribute in config.json
This is my env:
!pip install git+https://github.com/huggingface/transformers.git@a22a4378d97d06b7a1d9abad6e0086d30fdea199
!pip install auto-round
!pip install qwen-vl-utils
use the latest transformers in main to load autoround format or load the model with revision="e67cae7" to use AutoGPTQ format, or follow our code from auto_round import AutoRoundConfig ## must import for auto-round format