Spaces:
Running
Running
File size: 3,078 Bytes
9c12531 c886764 1a802f9 c886764 1a802f9 b3dc3b1 6f8f9b1 333a84a 8d1ba3e 1adcbaf c886764 abe37a4 c886764 abe37a4 c886764 c7f8a5d c886764 c7f8a5d 9c12531 abe37a4 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
import json
# Список доступных моделей
models_list = [
"google/gemma-3-27b-it",
"mistralai/Mistral-7B-Instruct-v0.3",
"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
"open-r1/OlympicCoder-7B",
"google/gemma-2-27b-it",
"Qwen/QwQ-32B",
"Qwen/QwQ-32B-Preview",
"google/gemma-2-9b-it",
"Qwen/Qwen2.5-72B-Instruct",
"mistralai/Mistral-7B-Instruct-v0.3",
"NousResearch/DeepHermes-3-Llama-3-3B-Preview"
]
def add_message(role, content, messages):
messages.append({"role": role, "content": content})
return messages, len(messages), str(messages)
def clear_messages(messages):
return [], 0, "[]"
def start_conversation(model, messages, max_tokens, temperature, top_p):
client = InferenceClient(model)
response = client.chat_completion(
messages,
max_tokens=max_tokens,
stream=False,
temperature=temperature,
top_p=top_p,
)
return response.choices[0].message.content
def show_messages(messages):
return str(messages)
def get_messages_api(messages):
return json.dumps(messages, indent=4)
demo = gr.Blocks()
with demo:
gr.Markdown("# Chat Interface")
role_input = gr.Textbox(label="Role")
content_input = gr.Textbox(label="Content")
messages_state = gr.State(value=[])
messages_output = gr.Textbox(label="Messages", value="[]")
count_output = gr.Number(label="Count", value=0)
response_output = gr.Textbox(label="Response")
messages_api_output = gr.Textbox(label="Messages API")
add_button = gr.Button("Add")
clear_button = gr.Button("Clear")
start_button = gr.Button("Start")
show_button = gr.Button("Show messages")
get_api_button = gr.Button("Get messages API")
model_input = gr.Radio(
label="Select a model",
choices=models_list,
value=models_list[0],
)
max_tokens_slider = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
temperature_slider = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
top_p_slider = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
add_button.click(
add_message,
inputs=[role_input, content_input, messages_state],
outputs=[messages_state, count_output, messages_output],
)
clear_button.click(
clear_messages,
inputs=[messages_state],
outputs=[messages_state, count_output, messages_output],
)
start_button.click(
start_conversation,
inputs=[model_input, messages_state, max_tokens_slider, temperature_slider, top_p_slider],
outputs=[response_output],
)
show_button.click(
show_messages,
inputs=[messages_state],
outputs=[messages_output],
)
get_api_button.click(
get_messages_api,
inputs=[messages_state],
outputs=[messages_api_output],
)
if __name__ == "__main__":
demo.launch() |