Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-09-20 10:35:10 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Increase truncation limits to 32768

Browse source
This commit is contained in:
oobabooga 2023-09-28 19:28:22 -07:00
parent 1dd13e4643
commit f931184b53
3 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
modules/shared.py
View file

@ -42,7 +42,7 @@ settings = {
'negative_prompt': '',
'truncation_length': 2048,
'truncation_length_min': 0,
'truncation_length_max': 16384,
'truncation_length_max': 32768,
'custom_stopping_strings': '',
'auto_max_new_tokens': False,
'max_tokens_second': 0,

4
modules/ui_model_menu.py
View file

@ -81,7 +81,7 @@ def create_ui():
shared.gradio['quant_type'] = gr.Dropdown(label="quant_type", choices=["nf4", "fp4"], value=shared.args.quant_type)
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_ctx'] = gr.Slider(minimum=0, maximum=32768, step=256, label="n_ctx", value=shared.args.n_ctx)
shared.gradio['threads'] = gr.Slider(label="threads", minimum=0, step=1, maximum=32, value=shared.args.threads)
shared.gradio['n_batch'] = gr.Slider(label="n_batch", minimum=1, maximum=2048, value=shared.args.n_batch)
@ -91,7 +91,7 @@ def create_ui():
shared.gradio['pre_layer'] = gr.Slider(label="pre_layer", minimum=0, maximum=100, value=shared.args.pre_layer[0] if shared.args.pre_layer is not None else 0)
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['max_seq_len'] = gr.Slider(label='max_seq_len', minimum=0, maximum=32768, 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['rope_freq_base'] = gr.Slider(label='rope_freq_base', minimum=0, maximum=1000000, 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)

2
settings-template.yaml
View file

@ -13,7 +13,7 @@ seed: -1
negative_prompt: ''
truncation_length: 2048
truncation_length_min: 0
truncation_length_max: 16384
truncation_length_max: 32768
custom_stopping_strings: ''
auto_max_new_tokens: false
max_tokens_second: 0