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

Add llama-2-70b GGML support (#3285)

Browse source
This commit is contained in:
oobabooga 2023-07-24 16:37:03 -03:00 • committed by GitHub
parent 6f4830b4d3
commit a07d070b6c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 20 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
server.py
View file

@ -219,6 +219,8 @@ def create_model_menus():
shared.gradio['n_batch'] = gr.Slider(label="n_batch", minimum=1, maximum=2048, value=shared.args.n_batch)
shared.gradio['n_gpu_layers'] = gr.Slider(label="n-gpu-layers", minimum=0, maximum=128, value=shared.args.n_gpu_layers)
shared.gradio['n_ctx'] = gr.Slider(minimum=0, maximum=16384, step=256, label="n_ctx", value=shared.args.n_ctx)
shared.gradio['n_gqa'] = gr.Slider(minimum=0, maximum=16, step=1, label="n_gqa", value=shared.args.n_gqa, info='grouped-query attention. Must be 8 for llama2 70b.')
shared.gradio['rms_norm_eps'] = gr.Slider(minimum=0, maximum=1e-5, step=1e-6, label="rms_norm_eps", value=shared.args.n_gqa, info='Must be 1e-5 for llama2 70b.')
shared.gradio['wbits'] = gr.Dropdown(label="wbits", choices=["None", 1, 2, 3, 4, 8], value=str(shared.args.wbits) if shared.args.wbits > 0 else "None")
shared.gradio['groupsize'] = gr.Dropdown(label="groupsize", choices=["None", 32, 64, 128, 1024], value=str(shared.args.groupsize) if shared.args.groupsize > 0 else "None")
shared.gradio['model_type'] = gr.Dropdown(label="model_type", choices=["None", "llama", "opt", "gptj"], value=shared.args.model_type or "None")