BitNet Q2B_X
Collection
Models Quantized with Q2B0
•
8 items
•
Updated
Model Card for Falcon3-3B-Instruct-1.58bit-q2b0
Falcon3-3B-1.58 Models
The Falcon3-3B-1.58bit-q2b0 is a quantized version of Falcon3-3B-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/Falcon3-3B-Instruct
- Quantization PR: Candle q2b0 Quantization
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.
Training Details
For details on the dataset and training process, refer to the original Falcon3-3B-Instruct repository.
License
This model is licensed under the Falcon LLM License.
For additional information or questions, please refer to the main Falcon3-3B-Instruct repository.
- Downloads last month
- 25
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for nebuxcloud/Falcon3-3B-Instruct-1.58bit-GGUF
Unable to build the model tree, the base model loops to the model itself. Learn more.