Update README.md

README.md

@@ -1,4 +1,67 @@
 ---
 base_model:
 - inference-net/Schematron-3B
----
+pipeline_tag: text-generation
+tags:
+- open4bits
+---
+# Open4bits / Schematron-3B-GGUF
+
+This repository provides the **Schematron-3B model converted to GGUF format**, published by Open4bits to enable efficient local inference with reduced memory usage and broad CPU compatibility.
+
+The underlying base model is **meta-llama/Llama-3.2-3B-Instruct**, fine-tuned by Inference-Net. This repository contains a quantized GGUF conversion of the fine-tuned model weights produced by Open4bits.
+
+The model is designed for instruction-based text generation tasks and is suitable for resource-constrained and local deployments.
+
+---
+
+## Model Overview
+
+Schematron-3B is an instruction-tuned language model built on the **LLaMA 3.2-3B architecture**. After fine-tuning by Inference-Net for enhanced instruction following and generation quality, the model has been quantized and released in GGUF format to support efficient CPU-friendly inference.
+
+---
+
+## Model Details
+
+* **Base Model:** meta-llama/Llama-3.2-3B-Instruct
+* **Fine-Tuned By:** Inference-Net
+* **Parameters:** ~3 billion
+* **Format:** GGUF (quantized)
+* **Task:** Instruction-based text generation
+* **Weight tying:** Preserved
+* **Compatibility:** GGUF-compatible inference engines and CPU environments
+
+This quantized release is designed to balance performance and resource efficiency while maintaining strong instruction following capabilities.
+
+---
+
+## Intended Use
+
+This model is intended for:
+
+* Instruction-guided text generation
+* Local and CPU-based inference workflows
+* Research, prototyping, and experimentation
+* Self-hosted or offline AI systems
+
+---
+
+## Limitations
+
+* Reduced generation quality compared to larger or full-precision variants
+* Performance depends on prompt design and inference parameters
+* Not fine-tuned for highly specialized or domain-specific tasks
+
+---
+
+## License
+
+This model follows the **original LLaMA 3.2 licensing terms** as defined by Meta AI.
+Users must comply with the licensing conditions of the base model and the fine-tuning provider.
+
+---
+
+## Support
+
+If you find this model valuable, please consider supporting the project.
+Your support helps Open4bits continue releasing and maintaining high-quality quantized models for the community.