Spaces:
Sleeping
Sleeping
File size: 2,469 Bytes
4bda4b5 8dd56db 4bda4b5 8dd56db 076f083 8dd56db 18ea130 8dd56db 18ea130 8dd56db 9225493 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
def respond(
message,
history: list[dict[str, str]],
system_message,
max_tokens,
temperature,
top_p,
hf_token: gr.OAuthToken,
):
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
messages = [{"role": "system", "content": system_message}]
messages.extend(history)
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
choices = message.choices
token = ""
if len(choices) and choices[0].delta.content:
token = choices[0].delta.content
response += token
yield response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
chatbot = gr.ChatInterface(
respond,
type="messages",
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
with gr.Blocks() as demo:
with gr.Sidebar():
gr.LoginButton()
chatbot.render()
if __name__ == "__main__":
demo.launch()
def chat(prompt, max_length=200):
# Convertimos el prompt en tensores para el modelo
inputs = tokenizer.encode(prompt, return_tensors="pt").to(device)
# Generamos la respuesta del modelo
outputs = model.generate(
inputs,
max_length=max_length,
pad_token_id=tokenizer.eos_token_id,
do_sample=True,
top_p=0.9,
temperature=0.7
)
# ⚡ Aquí ponemos el código para quitar la columna de tokens
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
# Devolvemos solo la respuesta en texto plano
return response[len(prompt):].strip()
|