Update README.md

README.md

@@ -1,3 +1,17 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- Qwen/Qwen2.5-Coder-32B-Instruct
+new_version: imsanjoykb/sqlCoder-Qwen2.5-8bit
+pipeline_tag: text-classification
+library_name: adapter-transformers
+tags:
+- unsloth,
+- pytorch,
+- inference-endpoint,
+---
 [🤗 HF Repo](https://huggingface.co/imsanjoykb/sqlCoder-Qwen2.5-8bit) | [♾️ Colab](https://colab.research.google.com/drive/19e-u32GY2y5lsckNuWhBQExvXgVn8ZjG?usp=sharing)
 
 Introducing the latest fine-tuned version of Qwen2.5-Coder-14B-Instruct, specifically tailored for SQL code generation. Built on the robust 14-billion parameter Qwen2.5-Coder architecture, this model leverages advanced configurations like bfloat16 precision and a custom quantization setup, optimized for efficient 4-bit computation. With a maximum context window of 32K tokens, this model supports extensive SQL sequences and complex query generation without compromising accuracy or performance.
@@ -74,4 +88,4 @@ _ = model.generate(**inputs, streamer=text_streamer, max_new_tokens=350)
 # Uploaded  model
 
 - **Developed by:** [Sanjoy Biswas](https://www.linkedin.com/in/imsanjoykb/) 
-- **License:** apache-2.0
+- **License:** apache-2.0