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

transformers: Add a flag to force load from safetensors (#4450)

Browse Source
This commit is contained in:
Julien Chaumond 2023-11-02 20:20:54 +01:00 committed by GitHub
parent c0655475ae
commit fdcaa955e3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
modules/models.py
View File

@ -123,7 +123,8 @@ def huggingface_loader(model_name):
params = {
'low_cpu_mem_usage': True,
'trust_remote_code': shared.args.trust_remote_code,
'torch_dtype': torch.bfloat16 if shared.args.bf16 else torch.float16
'torch_dtype': torch.bfloat16 if shared.args.bf16 else torch.float16,
'use_safetensors': True if shared.args.force_safetensors else None
}
config = AutoConfig.from_pretrained(path_to_model, trust_remote_code=params['trust_remote_code'])

1
modules/shared.py
View File

@ -91,6 +91,7 @@ parser.add_argument('--no-cache', action='store_true', help='Set use_cache to Fa
parser.add_argument('--xformers', action='store_true', help='Use xformer\'s memory efficient attention. This is really old and probably doesn\'t do anything.')
parser.add_argument('--sdp-attention', action='store_true', help='Use PyTorch 2.0\'s SDP attention. Same as above.')
parser.add_argument('--trust-remote-code', action='store_true', help='Set trust_remote_code=True while loading the model. Necessary for some models.')
parser.add_argument('--force-safetensors', action='store_true', help='Set use_safetensors=True while loading the model. This prevents arbitrary code execution.')
parser.add_argument('--use_fast', action='store_true', help='Set use_fast=True while loading the tokenizer.')
# Accelerate 4-bit

1
modules/ui_model_menu.py
View File

@ -122,6 +122,7 @@ def create_ui():
shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant)
shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17')
shared.gradio['llama_cpp_seed'] = gr.Number(label='Seed (0 for random)', value=shared.args.llama_cpp_seed)
shared.gradio['force_safetensors'] = gr.Checkbox(label='force_safetensors', info='Whether to force model loading from safetensors file. Prevents arbitrary code execution.', value=shared.args.force_safetensors)
shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='To enable this option, start the web UI with the --trust-remote-code flag. It is necessary for some models.', interactive=shared.args.trust_remote_code)
shared.gradio['use_fast'] = gr.Checkbox(label="use_fast", value=shared.args.use_fast, info='Set use_fast=True while loading the tokenizer. May trigger a conversion that takes several minutes.')
shared.gradio['disable_exllama'] = gr.Checkbox(label="disable_exllama", value=shared.args.disable_exllama, info='Disable ExLlama kernel.')