Intel
/

gpt-oss-20b-int4-rtn-AutoRound

4-bit precision

Model card Files Files and versions

wenhuach commited on 18 days ago

Commit

21f4c9f

·

verified ·

1 Parent(s): ce06248

Update README.md

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -14,7 +14,6 @@ base_model:
 This model is a mixed int4 model with group_size 128 and symmetric quantization of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) generated by [intel/auto-round](https://github.com/intel/auto-round)  via **RTN** (no algorithm tuning).
 Following the official model, Non expert layers fallback to 16bits.
-Theoretically, this one( https://huggingface.co/Intel/gpt-oss-20b-int4-AutoRound) is better
 ## How To Use

 This model is a mixed int4 model with group_size 128 and symmetric quantization of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) generated by [intel/auto-round](https://github.com/intel/auto-round)  via **RTN** (no algorithm tuning).
 Following the official model, Non expert layers fallback to 16bits.
 ## How To Use