Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,50 @@
+---
+license: apache-2.0
+base_model: Snowflake/Arctic-Text2SQL-R1-7B
+tags:
+- llamafile
+- text-to-sql
+- gguf
+- qwen2
+- reasoning
+---
+
+# Snowflake Arctic-Text2SQL-R1-7B - Llamafile
+
+This repository provides a standalone, cross-platform executable [llamafile](https://github.com/mozilla-ai/llamafile) for [Snowflake/Arctic-Text2SQL-R1-7B](https://huggingface.co/Snowflake/Arctic-Text2SQL-R1-7B).
+
+## What is a Llamafile?
+
+A llamafile bundles the `llamafile` inference runtime together with model weights (`Q4_K_M` quantization) and default parameters into a single executable file. It runs locally on Linux, macOS, and Windows without needing Python, PyTorch, or package installations.
+
+## Quick Start
+
+### 1. Download & Make Executable
+
+```bash
+curl -L -o arctic-text2sql-r1-7b.llamafile https://huggingface.co/MigueldsBatista/Arctic-Text2SQL-R1-7B-llamafile/resolve/main/arctic-text2sql-r1-7b.llamafile
+chmod +x arctic-text2sql-r1-7b.llamafile
+```
+
+### 2. Run Interactive / CLI Mode
+
+```bash
+./arctic-text2sql-r1-7b.llamafile --cli -p "<|im_start|>user
+Write a SQL query to list all department names.
+<|im_end|>
+<|im_start|>assistant
+"
+```
+
+### 3. Run Server Mode (OpenAI-compatible API)
+
+```bash
+./arctic-text2sql-r1-7b.llamafile --server --port 8080
+```
+
+Access the API at `http://localhost:8080/v1/chat/completions`.
+
+## Hardware Acceleration Notes
+
+- **GPU Acceleration**: Built-in CUDA acceleration works out-of-the-box on supported NVIDIA GPUs.
+- **CPU Fallback / Blackwell GPUs**: For architectures not yet bundled in upstream llamafile (e.g. RTX 50-series sm_120) or systems without a dedicated GPU, append `--gpu disable`.