Update app.py

app.py

@@ -1,80 +1,35 @@
-from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
-import gradio as gr
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+import uvicorn
+
+app = FastAPI()
 
 model_id = "GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
-
-pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
-
-def chat_fn(prompt):
-    result = pipe(prompt, max_new_tokens=200, temperature=0.7)[0]["generated_text"]
-    return result
-
-gr.Interface(fn=chat_fn, inputs="text", outputs="text").launch()
-
-
-# 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)",
-#         ),
-#     ],
-# )
-
-
-# if __name__ == "__main__":
-#     demo.launch()
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+
+class ChatRequest(BaseModel):
+    prompt: str
+    max_new_tokens: int = 256
+    temperature: float = 0.7
+    top_p: float = 0.95
+
+@app.post("/chat")
+async def chat(request: ChatRequest):
+    inputs = tokenizer(request.prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=request.max_new_tokens,
+        temperature=request.temperature,
+        top_p=request.top_p,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id,
+    )
+    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"response": result}
+
+# This will only run locally or in Spaces, not if you import this module
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)