Update README.md

README.md

@@ -9,10 +9,31 @@ license_name: falcon-llm-license
 license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
 ---
 
+# Model Card for Falcon3-1B-Instruct-1.58bit-q2b0
 
-![image/png](https://cdn-avatars.huggingface.co/v1/production/uploads/64e5f1303089e6a89ffad909/4OeBs8RGb87xGTwawyuVd.png)
+### Falcon3-1B-1.58 Models
 
+The **Falcon3-1B-1.58bit-q2b0** is a quantized version of **Falcon3-1B-Instruct**, leveraging the **q2b0 quantization method** from Candle. This enables extreme compression while maintaining strong performance across various NLP tasks.
 
-# TL;DR
+## Model Details
 
-This repository hosts a Falcon3-1B-Instruct quantized using `q2b0` from Candle for BitNet compatibility. The model achieves extreme compression while retaining high performance on evaluation tasks.
+### Model Sources
+
+- **Repository:** [tiiuae/Falcon3-1B-Instruct](https://huggingface.co/tiiuae/Falcon3-1B-Instruct)
+- **Quantization PR:** [Candle q2b0 Quantization](https://github.com/huggingface/candle/pull/2683)
+
+## Quantization Details
+
+The model has been quantized using the **q2b0** method from Candle. This approach reduces model size significantly while preserving performance. For more details on this quantization technique, refer to the [Candle PR #2683](https://github.com/huggingface/candle/pull/2683).
+
+## Training Details
+
+For details on the dataset and training process, refer to the original [Falcon3-1B-Instruct repository](https://huggingface.co/tiiuae/Falcon3-1B-Instruct).
+
+## License
+
+This model is licensed under the [Falcon LLM License](https://falconllm.tii.ae/falcon-terms-and-conditions.html).
+
+---
+
+For additional information or questions, please refer to the main [Falcon3-1B-Instruct repository](https://huggingface.co/tiiuae/Falcon3-1B-Instruct).