Update app.py

app.py

@@ -1,63 +1,62 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_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]})
-
-    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,
-    ):
-        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)",
-        ),
-    ],
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
+from threading import Thread
+import spaces
+
+# Charge le modele
+
+model = AutoModelForCausalLM.from_pretrained(
+        finetuned_model,
+        device_map="auto",
+        trust_remote_code=True,
 )
 
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(finetuned_model,
+                                         trust_remote_code=True,
+                                         padding=True,
+                                         truncation=True)
+
+class StopOnTokens(StoppingCriteria):
+    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
+        stop_ids = [29, 0]
+        for stop_id in stop_ids:
+            if input_ids[0][-1] == stop_id:
+                return True
+        return False
+
+@spaces.GPU
+def predict(message, history):
+    history_transformer_format = history + [[message, ""]]
+    stop = StopOnTokens()
+
+    messages = "".join(["".join(["\n[INST]:"+item[0], "\n[/INST]:"+item[1]]) for item in history_transformer_format])
+
+    model_inputs = tokenizer([messages], return_tensors="pt").to("cuda")
+    streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        model_inputs,
+        streamer=streamer,
+        max_new_tokens=1024,
+        num_beams=1,
+        stopping_criteria=StoppingCriteriaList([stop])
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+    partial_message = ""
+    start_flag = True  # Flag to ignore initial newline
+
+    for new_token in streamer:
+        if start_flag and new_token == '\n':
+            continue
+        start_flag = False
+        partial_message += new_token
+        yield partial_message
+
+
+demo = gr.ChatInterface(predict).launch()
+
 
 if __name__ == "__main__":
     demo.launch()