Update app.py

app.py

@@ -1,43 +1,30 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForCausalLM
+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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("cognitivecomputations/Dolphin3.0-Mistral-24B")
+model = AutoModelForCausalLM.from_pretrained("cognitivecomputations/Dolphin3.0-Mistral-24B", torch_dtype=torch.float16).cuda()
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# FastAPI app
+app = FastAPI()
 
-    messages.append({"role": "user", "content": message})
+# Request Body
+class InputText(BaseModel):
+    prompt: str
+    max_length: int = 100
 
-    response = ""
+@app.post("/generate")
+async def generate_text(input_data: InputText):
+    inputs = tokenizer(input_data.prompt, return_tensors="pt").to("cuda")
+    output = model.generate(**inputs, max_length=input_data.max_length)
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    return {"response": generated_text}
 
-    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
+# Run the server using: uvicorn app:app --host 0.0.0.0 --port 8000
 
-        response += token
-        yield response
 
 
 """