|
--- |
|
library_name: transformers |
|
tags: |
|
- bitnet |
|
- falcon3 |
|
base_model: tiiuae/Falcon3-10B-Instruct |
|
license: other |
|
license_name: falcon-llm-license |
|
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html |
|
--- |
|
|
|
# Model Card for Falcon3-10B-Instruct-1.58bit-q2b0 |
|
|
|
### Falcon3-10B-1.58 Models |
|
|
|
The **Falcon3-10B-1.58bit-q2b0** is a quantized version of **Falcon3-10B-Instruct**, leveraging the **q2b0 quantization method** from Candle. This enables extreme compression while maintaining strong performance across various NLP tasks. |
|
|
|
## Model Details |
|
|
|
### Model Sources |
|
|
|
- **Repository:** [tiiuae/Falcon3-10B-Instruct](https://huggingface.co/tiiuae/Falcon3-10B-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 [Falcon3-10B-Instruct repository](https://huggingface.co/tiiuae/Falcon3-10B-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 [Falcon3-10B-Instruct repository](https://huggingface.co/tiiuae/Falcon3-10B-Instruct). |
