Spaces:
Runtime error
Runtime error
File size: 6,037 Bytes
4db57ea 6fa6f73 4db57ea 2839246 f00a881 4db57ea 6fa6f73 4db57ea 6fa6f73 4db57ea 6fa6f73 4db57ea 6fa6f73 4db57ea 6fa6f73 4db57ea 6fa6f73 4db57ea 6fa6f73 4db57ea 074e33f 4db57ea 6fa6f73 4db57ea 6fa6f73 4db57ea 6fa6f73 4db57ea 6fa6f73 4db57ea 6fa6f73 4db57ea 6fa6f73 4db57ea 074e33f 6fa6f73 4db57ea 074e33f 4db57ea 6fa6f73 |
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 |
from huggingface_hub import InferenceClient
import gradio as gr
import random
import prompts # Ensure this module is correctly imported
client = InferenceClient(
"mistralai/Mixtral-8x7B-Instruct-v0.1"
)
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
agents = [
"WEB_DEV",
"AI_SYSTEM_PROMPT",
"PYTHON_CODE_DEV",
"CODE_REVIEW_ASSISTANT",
"CONTENT_WRITER_EDITOR",
"QUESTION_GENERATOR",
"HUGGINGFACE_FILE_DEV",
]
def generate(
prompt, history, agent_name=agents[0], sys_prompt="", temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
):
seed = random.randint(1, 1111111111111111)
# Ensure correct agent selection
agent = prompts.WEB_DEV_SYSTEM_PROMPT
if agent_name == "WEB_DEV":
agent = prompts.WEB_DEV_SYSTEM_PROMPT
elif agent_name == "CODE_REVIEW_ASSISTANT":
agent = prompts.CODE_REVIEW_ASSISTANT
elif agent_name == "CONTENT_WRITER_EDITOR":
agent = prompts.CONTENT_WRITER_EDITOR
elif agent_name == "SOCIAL_MEDIA_MANAGER":
agent = prompts.SOCIAL_MEDIA_MANAGER
elif agent_name == "AI_SYSTEM_PROMPT":
agent = prompts.AI_SYSTEM_PROMPT
elif agent_name == "PYTHON_CODE_DEV":
agent = prompts.PYTHON_CODE_DEV
elif agent_name == "QUESTION_GENERATOR":
agent = prompts.QUESTION_GENERATOR
elif agent_name == "HUGGINGFACE_FILE_DEV":
agent = prompts.HUGGINGFACE_FILE_DEV
system_prompt = agent
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=seed,
)
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 = ""
for response in stream:
output += response.token.text
yield output
additional_inputs = [
gr.Dropdown(
label="Agents",
choices=[s for s in agents],
value=agents[0],
interactive=True,
),
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=1000,
step=64,
interactive=True,
info="The maximum numbers of new tokens",
),
gr.Slider(
label="Top-p (nucleus sampling)",
value=0.95,
minimum=0.0,
maximum=1,
step=0.05,
interactive=True,
info="Higher values sample more low-probability tokens",
),
gr.Slider(
label="Repetition penalty",
value=1.0,
minimum=1.0,
maximum=2.0,
step=0.05,
interactive=True,
info="Penalize repeated tokens",
),
]
examples = [
["Create a simple web application using Flask", agents[0], "", 0.9, 256, 0.95, 1.0],
["Generate a Python script to perform a linear regression analysis", agents[2], "", 0.9, 256, 0.95, 1.0],
["Create a Dockerfile for a Node.js application", agents[1], "", 0.9, 256, 0.95, 1.0],
["Write a shell script to automate the deployment of a web application to a server", agents[3], "", 0.9, 256, 0.95, 1.0],
["Generate a SQL query to retrieve the top 10 most popular products by sales", agents[4], "", 0.9, 256, 0.95, 1.0],
["Write a Python script to generate a random password with a given length and complexity", agents[2], "", 0.9, 256, 0.95, 1.0],
["Create a simple game in Unity using C#", agents[0], "", 0.9, 256, 0.95, 1.0],
["Generate a Java program to implement a binary search algorithm", agents[2], "", 0.9, 256, 0.95, 1.0],
["Write a shell script to monitor the CPU usage of a server", agents[1], "", 0.9, 256, 0.95, 1.0],
["Create a simple web application using React and Node.js", agents[0], "", 0.9, 256, 0.95, 1.0],
["Generate a Python script to perform a sentiment analysis on a given text", agents[2], "", 0.9, 256, 0.95, 1.0],
["Write a shell script to automate the backup of a MySQL database", agents[1], "", 0.9, 256, 0.95, 1.0],
["Create a simple game in Unreal Engine using C++", agents[3], "", 0.9, 256, 0.95, 1.0],
["Generate a Java program to implement a bubble sort algorithm", agents[2], "", 0.9, 256, 0.95, 1.0],
["Write a shell script to monitor the memory usage of a server", agents[1], "", 0.9, 256, 0.95, 1.0],
["Create a simple web application using Angular and Node.js", agents[0], "", 0.9, 256, 0.95, 1.0],
["Generate a Python script to perform a text classification on a given dataset", agents[2], "", 0.9, 256, 0.95, 1.0],
["Write a shell script to automate the installation of a software package on a server", agents[1], "", 0.9, 256, 0.95, 1.0],
["Create a simple game in Godot using GDScript", agents[3], "", 0.9, 256, 0.95, 1.0],
["Generate a Java program to implement a merge sort algorithm", agents[2], "", 0.9, 256, 0.95, 1.0],
["Write a shell script to automate the cleanup of temporary files on a server", agents[1], "", 0.9, 256, 0.95, 1.0],
]
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,
).launch(show_api=False) |