File size: 3,934 Bytes
1b442f9 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | from huggingface_hub import InferenceClient
import gradio as gr
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
# This allows the model to consider its prior context
def format_prompt(message, history):
prompt = "<s>"
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST]"
prompt += f" {bot_response}</s> "
prompt += f"[INST] {message} [/INST]"
return prompt
def generate(
prompt,
history,
system_prompt,
temperature=0.9,
max_new_tokens=256,
top_p=0.95,
repetition_penalty=1.0,
):
temperature = float(temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=max_new_tokens,
top_p=top_p,
repetition_penalty=repetition_penalty,
do_sample=True,
seed=42,
)
formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
stream = client.text_generation(
formatted_prompt,
**generate_kwargs,
stream=True,
details=True,
return_full_text=False,
)
output = ""
# How does streaming works
for response in stream:
output += response.token.text
yield output
return output
additional_inputs = [
gr.Textbox(
label="System Prompt",
max_lines=1,
interactive=True,
),
gr.Slider(
label="Temperature",
value=0.9,
minimum=0.0,
maximum=1.0,
step=0.05,
interactive=True,
info="Higher values produce more diverse outputs",
),
gr.Slider(
label="Max new tokens",
value=256,
minimum=0,
maximum=1048,
step=64,
interactive=True,
info="The maximum numbers of new tokens",
),
gr.Slider(
label="Top-p (nucleus sampling)",
value=0.90,
minimum=0.0,
maximum=1,
step=0.05,
interactive=True,
info="Higher values sample more low-probability tokens",
),
gr.Slider(
label="Repetition penalty",
value=1.2,
minimum=1.0,
maximum=2.0,
step=0.05,
interactive=True,
info="Penalize repeated tokens",
),
]
examples = [
[
"I'm planning a vacation to Japan. Can you suggest a one-week itinerary including must-visit places and local cuisines to try?",
None,
None,
None,
None,
None,
],
[
"Can you write a short story about a time-traveling detective who solves historical mysteries?",
None,
None,
None,
None,
None,
],
[
"I'm trying to learn French. Can you provide some common phrases that would be useful for a beginner, along with their pronunciations?",
None,
None,
None,
None,
None,
],
[
"I have chicken, rice, and bell peppers in my kitchen. Can you suggest an easy recipe I can make with these ingredients?",
None,
None,
None,
None,
None,
],
[
"Can you explain how the QuickSort algorithm works and provide a Python implementation?",
None,
None,
None,
None,
None,
],
[
"What are some unique features of Rust that make it stand out compared to other systems programming languages like C++?",
None,
None,
None,
None,
None,
],
]
iface = gr.ChatInterface(
fn=generate,
chatbot=gr.Chatbot(
show_label=False,
show_share_button=False,
show_copy_button=True,
likeable=True,
layout="panel",
),
additional_inputs=additional_inputs,
title="Mixtral 46.7B",
examples=examples,
concurrency_limit=20,
)
iface.launch(show_api=False)
|