Upload folder using huggingface_hub

.gitignore

@@ -4,7 +4,7 @@ __pycache__/
 *.pyc
 
 # Local models / data
-models/
+
 data/index.faiss
 data/docstore.json
 

README.md

@@ -1,32 +1,3 @@
----
-language: en
-license: mit
-tags:
-- gguf
-- quantized
-- phi-3
-- llama-cpp
-library_name: gguf
-pipeline_tag: text-generation
----
-
-# Phi-3 Mini 4K Instruct – 4-bit GGUF
-
-4-bit quantized GGUF for efficient inference (low-cost servers).
-
-## Files
-- `Phi-3-mini-4k-instruct-q4.gguf`
-
-## Usage (llama.cpp)
-```bash
-./main -m Phi-3-mini-4k-instruct-q4.gguf -p "Hello"
-```
-
-## License
-MIT (project code). Base model license applies to the original Phi-3 weights.
-
-
-
 # Quantized LLM + RAG (FastAPI + FAISS + Phi‑3)
 
 ## Goal