Upload 3 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+qwen2-1_5b-instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text

main.py

@@ -0,0 +1,40 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
+
+app = FastAPI()
+
+# 👇 Request body structure
+class PromptRequest(BaseModel):
+    prompt: str
+    max_tokens: int = 200
+
+# 👇 Download model from your HF repo
+MODEL_PATH = hf_hub_download(
+    repo_id="your-username/qwen-gguf",   # CHANGE THIS
+    filename="qwen2-1_5b-instruct-q4_0.gguf"
+)
+
+# 👇 Load model once (very important)
+llm = Llama(
+    model_path=MODEL_PATH,
+    n_ctx=1024,        # keep low for HF free tier
+    n_threads=2        # reduce CPU usage
+)
+
+@app.get("/")
+def home():
+    return {"status": "AI is running"}
+
+@app.post("/chat")
+def chat(req: PromptRequest):
+    output = llm(
+        req.prompt,
+        max_tokens=req.max_tokens,
+        stop=["</s>"]
+    )
+
+    return {
+        "response": output["choices"][0]["text"]
+    }

qwen2-1_5b-instruct-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106c176ae807b164f16e2898e8f0267062e3c93c3c18c8267cf9e4ee90766beb
+size 937532800

requirement.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn
+llama-cpp-python
+huggingface_hub
+pydantic