Update app.py

app.py

@@ -1,64 +1,34 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+from flask import Flask, request, jsonify
+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")
+app = Flask(__name__)
 
+# Charger le modèle depuis Hugging Face
+MODEL_NAME = "fatmata/psybot"  # Remplace avec le vrai nom de ton modèle
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float16)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+@app.route("/chat", methods=["POST"])
+def chat():
+    data = request.json
+    user_input = data.get("message", "")
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    if not user_input:
+        return jsonify({"error": "Message vide"}), 400
 
-    messages.append({"role": "user", "content": message})
+    # Génération de la réponse
+    prompt = f"<|startoftext|><|user|> {user_input} <|bot|>"
+    inputs = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
 
-    response = ""
+    with torch.no_grad():
+        output = model.generate(inputs, max_new_tokens=100, pad_token_id=tokenizer.eos_token_id)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.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
-"""
-demo = gr.ChatInterface(
-    respond,
-    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)",
-        ),
-    ],
-)
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    if "<|bot|>" in response:
+        response = response.split("<|bot|>")[-1].strip()
 
+    return jsonify({"response": response})
 
 if __name__ == "__main__":
-    demo.launch()
+    app.run(host="0.0.0.0", port=7860)