Fix itrex WOQ model loading

huggingface / optimum-intel

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

https://huggingface.co/docs/optimum/main/en/intel/index

Apache License 2.0

358 stars 99 forks source link

Fix itrex WOQ model loading #730

Closed echarlaix closed 1 month ago

echarlaix commented 1 month ago

Fix itrex WOQ model saving : currently the quantization_config is not saved when calling save_pretrained, resulting in issues when trying to load the model after saving it

also enable the possibility to :

load a safetensors checkpoints
provide a subfolder argument

HuggingFaceDocBuilderDev commented 1 month ago

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.