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

Add RoPE scaling support for transformers (including dynamic NTK)

Browse source 
https://github.com/huggingface/transformers/pull/24653
This commit is contained in:
oobabooga 2023-08-08 21:24:28 -07:00
parent f4caaf337a
commit d8fb506aff
5 changed files with 16 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/ui_model_menu.py
View file

@ -89,8 +89,8 @@ def create_ui():
shared.gradio['autogptq_info'] = gr.Markdown('* ExLlama_HF is recommended over AutoGPTQ for models derived from LLaMA.')
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 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=0.1, 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)