initial

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.10
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+
+COPY . .
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README copy.md

@@ -0,0 +1,14 @@
+---
+title: Qwen2.5 7b 4bit
+emoji: 🐠
+colorFrom: purple
+colorTo: red
+sdk: gradio
+sdk_version: 5.21.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+short_description: qwen for agent
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

main.py

@@ -0,0 +1,20 @@
+from fastapi import FastAPI
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+app = FastAPI()
+
+model_name = "mistralai/Mistral-7B-Instruct-v0.1"  # Change to your model
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+@app.get("/")
+def read_root():
+    return {"message": "Chat API is running!"}
+
+@app.post("/chat")
+def chat(prompt: str):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=100)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"response": response}

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn
+transformers
+torch