Spaces:
Running
Running
File size: 2,361 Bytes
4c2efe8 b6bfa2b 4c2efe8 b6bfa2b 4c2efe8 b6bfa2b 4c2efe8 b6bfa2b 4c2efe8 b6bfa2b 4c2efe8 b6bfa2b 4c2efe8 e68c545 4c2efe8 |
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 |
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
"""
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
"""
# Cargar el modelo y el tokenizer
model_name = "HuggingFaceTB/SmolLM2-1.7B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto"
)
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
# Construir el prompt con el formato correcto
prompt = f"<|system|>\n{system_message}</s>\n"
for val in history:
if val[0]:
prompt += f"<|user|>\n{val[0]}</s>\n"
if val[1]:
prompt += f"<|assistant|>\n{val[1]}</s>\n"
prompt += f"<|user|>\n{message}</s>\n<|assistant|>\n"
# Tokenizar el prompt
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
# Generar la respuesta
outputs = model.generate(
**inputs,
max_new_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
do_sample=True,
pad_token_id=tokenizer.eos_token_id
)
# Decodificar la respuesta
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
# Extraer solo la parte de la respuesta del asistente
response = response.split("<|assistant|>\n")[-1].strip()
yield response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(
value="You are a friendly Chatbot. Always reply in the language in which the user is writing to you.",
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)",
),
],
)
if __name__ == "__main__":
demo.launch()
|