|
---
|
|
library_name: transformers
|
|
tags:
|
|
- bitnet
|
|
- falcon3
|
|
base_model: tiiuae/Falcon3-7B-Base
|
|
license: other
|
|
license_name: falcon-llm-license
|
|
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
|
|
---
|
|
|
|
# Model Card for Falcon3-7B-Base-1.58bit-q2b0
|
|
|
|
### Falcon3-7B-1.58 Models
|
|
|
|
The **Falcon3-7B-1.58bit-q2b0** is a quantized version of **Falcon3-7B-Base**, 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/Falcon3-7B-Base](https://huggingface.co/tiiuae/Falcon3-7B-Base)
|
|
- **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 [Falcon3-7B-Base repository](https://huggingface.co/tiiuae/Falcon3-7B-Base).
|
|
|
|
## 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 [Falcon3-7B-Base repository](https://huggingface.co/tiiuae/Falcon3-7B-Base). |
