Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-22 08:07:56 +01:00
Code Issues Packages Projects Releases Wiki Activity

Set llm_int8_enable_fp32_cpu_offload=True for --load-in-4bit

Browse Source 
To allow for 32-bit CPU offloading (it's very slow).
This commit is contained in:
oobabooga 2024-04-26 09:39:27 -07:00
parent 70845c76fb
commit dfdb6fee22
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
modules/models.py
View File

@ -205,6 +205,7 @@ def huggingface_loader(model_name):
'bnb_4bit_compute_dtype': eval("torch.{}".format(shared.args.compute_dtype)) if shared.args.compute_dtype in ["bfloat16", "float16", "float32"] else None, 'bnb_4bit_compute_dtype': eval("torch.{}".format(shared.args.compute_dtype)) if shared.args.compute_dtype in ["bfloat16", "float16", "float32"] else None,
'bnb_4bit_quant_type': shared.args.quant_type, 'bnb_4bit_quant_type': shared.args.quant_type,
'bnb_4bit_use_double_quant': shared.args.use_double_quant, 'bnb_4bit_use_double_quant': shared.args.use_double_quant,
'llm_int8_enable_fp32_cpu_offload': True
} }
params['quantization_config'] = BitsAndBytesConfig(**quantization_config_params) params['quantization_config'] = BitsAndBytesConfig(**quantization_config_params)