Spaces:
Runtime error
Runtime error
File size: 4,061 Bytes
ec22274 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
import torch
from modules import chat, shared
from modules.text_generation import (
decode,
encode,
generate_reply,
)
from transformers import LogitsProcessor
import gradio as gr
params = {
"display_name": "Long replies",
"is_tab": False,
"min_length": 120,
}
initial_size = 0
class MyLogits(LogitsProcessor):
"""
Manipulates the probabilities for the next token before it gets sampled.
Used in the logits_processor_modifier function below.
"""
def __init__(self):
self.newline_id = shared.tokenizer.encode('\n')[-1]
pass
def __call__(self, input_ids, scores):
if input_ids.shape[-1] - initial_size < params["min_length"]:
scores[...,self.newline_id] = -1000
# scores[...,shared.tokenizer.eos_token_id] = -1000
# probs = torch.softmax(scores, dim=-1, dtype=torch.float)
# probs[0] /= probs[0].sum()
# scores = torch.log(probs / (1 - probs))
return scores
def history_modifier(history):
"""
Modifies the chat history.
Only used in chat mode.
"""
return history
def state_modifier(state):
"""
Modifies the state variable, which is a dictionary containing the input
values in the UI like sliders and checkboxes.
"""
return state
def chat_input_modifier(text, visible_text, state):
"""
Modifies the user input string in chat mode (visible_text).
You can also modify the internal representation of the user
input (text) to change how it will appear in the prompt.
"""
return text, visible_text
def input_modifier(string, state):
"""
In default/notebook modes, modifies the whole prompt.
In chat mode, it is the same as chat_input_modifier but only applied
to "text", here called "string", and not to "visible_text".
"""
return string
def bot_prefix_modifier(string, state):
"""
Modifies the prefix for the next bot reply in chat mode.
By default, the prefix will be something like "Bot Name:".
"""
return string
def tokenizer_modifier(state, prompt, input_ids, input_embeds):
"""
Modifies the input ids and embeds.
Used by the multimodal extension to put image embeddings in the prompt.
Only used by loaders that use the transformers library for sampling.
"""
global initial_size
initial_size = input_ids.shape[-1]
return prompt, input_ids, input_embeds
def logits_processor_modifier(processor_list, input_ids):
"""
Adds logits processors to the list, allowing you to access and modify
the next token probabilities.
Only used by loaders that use the transformers library for sampling.
"""
processor_list.append(MyLogits())
return processor_list
def output_modifier(string, state):
"""
Modifies the LLM output before it gets presented.
In chat mode, the modified version goes into history['visible'],
and the original version goes into history['internal'].
"""
return string
def custom_generate_chat_prompt(user_input, state, **kwargs):
"""
Replaces the function that generates the prompt from the chat history.
Only used in chat mode.
"""
result = chat.generate_chat_prompt(user_input, state, **kwargs)
return result
def custom_css():
"""
Returns a CSS string that gets appended to the CSS for the webui.
"""
return ''
def custom_js():
"""
Returns a javascript string that gets appended to the javascript
for the webui.
"""
return ''
def setup():
"""
Gets executed only once, when the extension is imported.
"""
pass
def ui():
"""
Gets executed when the UI is drawn. Custom gradio elements and
their corresponding event handlers should be defined here.
To learn about gradio components, check out the docs:
https://gradio.app/docs/
"""
min_length = gr.Slider(0, 800, step=10, value=params['min_length'], label='Minimum reply length')
min_length.change(lambda x: params.update({'min_length': x}), min_length, None)
|