First commit

Chatbot with local model and gradio

app.py

@@ -1,11 +1,19 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+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
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# 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,
@@ -15,38 +23,49 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    # Construir el prompt con el formato correcto
+    prompt = f"<|system|>\n{system_message}</s>\n"
 
     for val in history:
         if val[0]:
-            messages.append({"role": "user", "content": val[0]})
+            prompt += f"<|user|>\n{val[0]}</s>\n"
         if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+            prompt += f"<|assistant|>\n{val[1]}</s>\n"
 
-    messages.append({"role": "user", "content": message})
+    prompt += f"<|user|>\n{message}</s>\n<|assistant|>\n"
 
-    response = ""
+    # Tokenizar el prompt
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Generar la respuesta
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
+
+    # Decodificar la respuesta
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-        response += token
-        yield response
+    # 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
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/gradio/chatinterface
 """
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        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(