Add large file with Git LFS

.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
+*.gguf filter=lfs diff=lfs merge=lfs -text

main.py

@@ -0,0 +1,33 @@
+from fastapi import FastAPI, HTTPException
+from models import SQLContext
+from llama_cpp import Llama
+import logging
+
+llm = Llama(
+    model_path="./quantized_model/sql_gpt_quantized.gguf", 
+    n_ctx=512,
+    n_threads=2,
+    n_gpu_layers=-1
+)
+
+app = FastAPI()
+
+@app.get("/")
+def root():
+    return {"Hello": "World"}
+
+@app.post("/query")
+async def send_response(query: SQLContext):
+    query_text = f'''
+    ### CONTEXT:\n{query.context}\n\n### QUESTION:{query.question}\n\n### [RESPONSE]:\n"
+    '''
+    try:
+        output = llm(
+            prompt=query_text,
+            max_tokens=512,
+        )
+        response_text = output["choices"][0]["text"].split('###')[0].strip('"')
+        return {"response": response_text}
+    except Exception as e:
+        logging.error(f"Error generating response: {e}")
+        raise HTTPException(status_code=500, detail="Internal server error while processing the query.")

quantized_model/sql_gpt_quantized.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34010ed42c25cc6e59c3f0f2af2ea7c3000363a264efab975e96c0489288060c
+size 1708582432