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

ExLlama with long context (#2875)

Browse source
This commit is contained in:
oobabooga 2023-06-25 22:49:26 -03:00 • committed by GitHub
parent 9290c6236f
commit c52290de50
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
14 changed files with 22 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

9
server.py
View file

@ -216,13 +216,15 @@ def create_model_menus():
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)
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=8192, step=1, label="n_ctx", value=shared.args.n_ctx)
shared.gradio['n_ctx'] = gr.Slider(minimum=0, maximum=16384, step=256, label="n_ctx", value=shared.args.n_ctx)
shared.gradio['wbits'] = gr.Dropdown(label="wbits", choices=["None", 1, 2, 3, 4, 8], value=shared.args.wbits if shared.args.wbits > 0 else "None")
shared.gradio['groupsize'] = gr.Dropdown(label="groupsize", choices=["None", 32, 64, 128, 1024], value=shared.args.groupsize if shared.args.groupsize > 0 else "None")
shared.gradio['model_type'] = gr.Dropdown(label="model_type", choices=["None", "llama", "opt", "gptj"], value=shared.args.model_type or "None")
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('On some systems, AutoGPTQ can be 2x slower than GPTQ-for-LLaMa. You can manually select the GPTQ-for-LLaMa loader above.')
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.')
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.')
with gr.Column():
shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)
@ -300,10 +302,9 @@ def create_chat_settings_menus():
with gr.Row():
with gr.Column():
shared.gradio['max_new_tokens'] = gr.Slider(minimum=shared.settings['max_new_tokens_min'], maximum=shared.settings['max_new_tokens_max'], step=1, label='max_new_tokens', value=shared.settings['max_new_tokens'])
shared.gradio['chat_prompt_size'] = gr.Slider(minimum=shared.settings['chat_prompt_size_min'], maximum=shared.settings['chat_prompt_size_max'], step=1, label='chat_prompt_size', info='Set limit on prompt size by removing old messages (while retaining context and user input)', value=shared.settings['chat_prompt_size'])
shared.gradio['chat_generation_attempts'] = gr.Slider(minimum=shared.settings['chat_generation_attempts_min'], maximum=shared.settings['chat_generation_attempts_max'], value=shared.settings['chat_generation_attempts'], step=1, label='Generation attempts (for longer replies)', info='New generations will be called until either this number is reached or no new content is generated between two iterations.')
with gr.Column():
shared.gradio['chat_generation_attempts'] = gr.Slider(minimum=shared.settings['chat_generation_attempts_min'], maximum=shared.settings['chat_generation_attempts_max'], value=shared.settings['chat_generation_attempts'], step=1, label='Generation attempts (for longer replies)', info='New generations will be called until either this number is reached or no new content is generated between two iterations.')
shared.gradio['stop_at_newline'] = gr.Checkbox(value=shared.settings['stop_at_newline'], label='Stop generating at new line character')
@ -366,7 +367,7 @@ def create_settings_menus(default_preset):
with gr.Box():
with gr.Row():
with gr.Column():
shared.gradio['truncation_length'] = gr.Slider(value=shared.settings['truncation_length'], minimum=shared.settings['truncation_length_min'], maximum=shared.settings['truncation_length_max'], step=1, label='Truncate the prompt up to this length', info='The leftmost tokens are removed if the prompt exceeds this length. Most models require this to be at most 2048.')
shared.gradio['truncation_length'] = gr.Slider(value=shared.settings['truncation_length'], minimum=shared.settings['truncation_length_min'], maximum=shared.settings['truncation_length_max'], step=256, label='Truncate the prompt up to this length', info='The leftmost tokens are removed if the prompt exceeds this length. Most models require this to be at most 2048.')
shared.gradio['custom_stopping_strings'] = gr.Textbox(lines=1, value=shared.settings["custom_stopping_strings"] or None, label='Custom stopping strings', info='In addition to the defaults. Written between "" and separated by commas. For instance: "\\nYour Assistant:", "\\nThe assistant:"')
with gr.Column():
shared.gradio['ban_eos_token'] = gr.Checkbox(value=shared.settings['ban_eos_token'], label='Ban the eos_token', info='Forces the model to never end the generation prematurely.')