Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-12-24 13:28:59 +01:00
Code Issues Packages Projects Releases Wiki Activity

Increase alpha value limit for NTK RoPE scaling for exllama/exllama_HF (#3149)

Browse Source
This commit is contained in:
Panchovix 2023-07-16 00:56:04 -04:00 committed by GitHub
parent 780a2f2e16
commit 7c4d4fc7d3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server.py
View File

@ -227,7 +227,7 @@ def create_model_menus():
shared.gradio['gpu_split'] = gr.Textbox(label='gpu-split', info='Comma-separated list of VRAM (in GB) to use per GPU. Example: 20,7,7')
shared.gradio['max_seq_len'] = gr.Slider(label='max_seq_len', minimum=2048, maximum=16384, step=256, info='Maximum sequence length.', value=shared.args.max_seq_len)
shared.gradio['compress_pos_emb'] = gr.Slider(label='compress_pos_emb', minimum=1, maximum=8, step=1, info='Positional embeddings compression factor. Should typically be set to max_seq_len / 2048.', value=shared.args.compress_pos_emb)
shared.gradio['alpha_value'] = gr.Slider(label='alpha_value', minimum=1, maximum=8, step=1, info='Positional embeddings alpha factor for NTK RoPE scaling. Same as above. Use either this or compress_pos_emb, not both.', value=shared.args.alpha_value)
shared.gradio['alpha_value'] = gr.Slider(label='alpha_value', minimum=1, maximum=32, step=1, info='Positional embeddings alpha factor for NTK RoPE scaling. Scaling is not identical to embedding compression. Use either this or compress_pos_emb, not both.', value=shared.args.alpha_value)
with gr.Column():
shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)