* [ADD] add transformer_int4_fp16_loadlowbit_gpu_win api * [UPDATE] add int4_fp16_lowbit config and description * [FIX] fix run.py mistake * [FIX] fix run.py mistake * [FIX] fix indent; change dtype=float16 to model.half() |
||
|---|---|---|
| .. | ||
| llm | ||
* [ADD] add transformer_int4_fp16_loadlowbit_gpu_win api * [UPDATE] add int4_fp16_lowbit config and description * [FIX] fix run.py mistake * [FIX] fix run.py mistake * [FIX] fix indent; change dtype=float16 to model.half() |
||
|---|---|---|
| .. | ||
| llm | ||