mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Implement CFG for ExLlama_HF (#3666)

Browse source
This commit is contained in:
oobabooga 2023-08-24 16:27:36 -03:00 • committed by GitHub
parent 2b675533f7
commit d6934bc7bc
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 122 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/ui_model_menu.py
View file

@ -111,6 +111,7 @@ def create_ui():
shared.gradio['low_vram'] = gr.Checkbox(label="low-vram", value=shared.args.low_vram)
shared.gradio['mlock'] = gr.Checkbox(label="mlock", value=shared.args.mlock)
shared.gradio['mul_mat_q'] = gr.Checkbox(label="mul_mat_q", value=shared.args.mul_mat_q)
shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Create an additional cache for CFG negative prompts.')
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['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='Make sure to inspect the .py files inside the model folder before loading it with this option enabled.')