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

Add tail-free and top-a sampling (#2357)

Browse source
This commit is contained in:
Luis Lopez 2023-05-30 08:40:01 +08:00 • committed by GitHub
parent b4662bf4af
commit 9e7204bef4
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 113 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

8
server.py
View file

@ -101,6 +101,8 @@ def load_preset_values(preset_menu, state, return_dict=False):
'mirostat_mode': 0,
'mirostat_tau': 5.0,
'mirostat_eta': 0.1,
'tfs': 1,
'top_a': 0,
}
with open(Path(f'presets/{preset_menu}.yaml'), 'r') as infile:
@ -114,7 +116,7 @@ def load_preset_values(preset_menu, state, return_dict=False):
return generate_params
else:
state.update(generate_params)
return state, *[generate_params[k] for k in ['do_sample', 'temperature', 'top_p', 'typical_p', 'epsilon_cutoff', 'eta_cutoff', 'repetition_penalty', 'encoder_repetition_penalty', 'top_k', 'min_length', 'no_repeat_ngram_size', 'num_beams', 'penalty_alpha', 'length_penalty', 'early_stopping', 'mirostat_mode', 'mirostat_tau', 'mirostat_eta']]
return state, *[generate_params[k] for k in ['do_sample', 'temperature', 'top_p', 'typical_p', 'epsilon_cutoff', 'eta_cutoff', 'repetition_penalty', 'encoder_repetition_penalty', 'top_k', 'min_length', 'no_repeat_ngram_size', 'num_beams', 'penalty_alpha', 'length_penalty', 'early_stopping', 'mirostat_mode', 'mirostat_tau', 'mirostat_eta', 'tfs', 'top_a']]
def upload_soft_prompt(file):
@ -476,6 +478,8 @@ def create_settings_menus(default_preset):
shared.gradio['typical_p'] = gr.Slider(0.0, 1.0, value=generate_params['typical_p'], step=0.01, label='typical_p', info='If not set to 1, select only tokens that are at least this much more likely to appear than random tokens, given the prior text.')
shared.gradio['epsilon_cutoff'] = gr.Slider(0, 9, value=generate_params['epsilon_cutoff'], step=0.01, label='epsilon_cutoff', info='In units of 1e-4; a reasonable value is 3. This sets a probability floor below which tokens are excluded from being sampled. Should be used with top_p, top_k, and eta_cutoff set to 0.')
shared.gradio['eta_cutoff'] = gr.Slider(0, 20, value=generate_params['eta_cutoff'], step=0.01, label='eta_cutoff', info='In units of 1e-4; a reasonable value is 3. Should be used with top_p, top_k, and epsilon_cutoff set to 0.')
shared.gradio['tfs'] = gr.Slider(0.0, 1.0, value=generate_params['tfs'], step=0.01, label='tfs')
shared.gradio['top_a'] = gr.Slider(0.0, 1.0, value=generate_params['top_a'], step=0.01, label='top_a')
with gr.Column():
shared.gradio['repetition_penalty'] = gr.Slider(1.0, 1.5, value=generate_params['repetition_penalty'], step=0.01, label='repetition_penalty', info='Exponential penalty factor for repeating prior tokens. 1 means no penalty, higher value = less repetition, lower value = more repetition.')
@ -526,7 +530,7 @@ def create_settings_menus(default_preset):
gr.Markdown('[Click here for more information.](https://github.com/oobabooga/text-generation-webui/blob/main/docs/Generation-parameters.md)')
shared.gradio['preset_menu'].change(load_preset_values, [shared.gradio[k] for k in ['preset_menu', 'interface_state']], [shared.gradio[k] for k in ['interface_state', 'do_sample', 'temperature', 'top_p', 'typical_p', 'epsilon_cutoff', 'eta_cutoff', 'repetition_penalty', 'encoder_repetition_penalty', 'top_k', 'min_length', 'no_repeat_ngram_size', 'num_beams', 'penalty_alpha', 'length_penalty', 'early_stopping', 'mirostat_mode', 'mirostat_tau', 'mirostat_eta']])
shared.gradio['preset_menu'].change(load_preset_values, [shared.gradio[k] for k in ['preset_menu', 'interface_state']], [shared.gradio[k] for k in ['interface_state', 'do_sample', 'temperature', 'top_p', 'typical_p', 'epsilon_cutoff', 'eta_cutoff', 'repetition_penalty', 'encoder_repetition_penalty', 'top_k', 'min_length', 'no_repeat_ngram_size', 'num_beams', 'penalty_alpha', 'length_penalty', 'early_stopping', 'mirostat_mode', 'mirostat_tau', 'mirostat_eta', 'tfs', 'top_a']])
shared.gradio['softprompts_menu'].change(load_soft_prompt, shared.gradio['softprompts_menu'], shared.gradio['softprompts_menu'], show_progress=True)
shared.gradio['upload_softprompt'].upload(upload_soft_prompt, shared.gradio['upload_softprompt'], shared.gradio['softprompts_menu'])