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

Add rope_freq_base parameter for CodeLlama

Browse source
This commit is contained in:
oobabooga 2023-08-25 06:53:37 -07:00
parent feecd8190f
commit 52ab2a6b9e
10 changed files with 26 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

3
modules/ui_model_menu.py
View file

@ -91,7 +91,8 @@ def create_ui():
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=0, maximum=16384, step=256, info='Maximum sequence length.', value=shared.args.max_seq_len)
shared.gradio['alpha_value'] = gr.Slider(label='alpha_value', minimum=1, maximum=8, step=0.1, info='Positional embeddings alpha factor for NTK RoPE scaling. Use either this or compress_pos_emb, not both.', value=shared.args.alpha_value)
shared.gradio['compress_pos_emb'] = gr.Slider(label='compress_pos_emb', minimum=1, maximum=8, step=1, info='Positional embeddings compression factor. Should be set to (context length) / (model\'s original context length).', value=shared.args.compress_pos_emb)
shared.gradio['rope_freq_base'] = gr.Slider(label='rope_freq_base', minimum=0, maximum=100000, step=1000, info='If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63)', value=shared.args.rope_freq_base)
shared.gradio['compress_pos_emb'] = gr.Slider(label='compress_pos_emb', minimum=1, maximum=8, step=1, info='Positional embeddings compression factor. Should be set to (context length) / (model\'s original context length). Equal to 1/rope_freq_scale.', value=shared.args.compress_pos_emb)
with gr.Column():
shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)