From 7c4d4fc7d35c06d964ca5bd87637843a8e795ca5 Mon Sep 17 00:00:00 2001 From: Panchovix Date: Sun, 16 Jul 2023 00:56:04 -0400 Subject: [PATCH] Increase alpha value limit for NTK RoPE scaling for exllama/exllama_HF (#3149) --- server.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/server.py b/server.py index 4612cb0b..eb77063c 100644 --- a/server.py +++ b/server.py @@ -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)