|
--- |
|
library_name: transformers |
|
base_model: |
|
- meta-llama/Meta-Llama-3-8B-Instruct |
|
--- |
|
|
|
# Model Card for Llama3-8B-1.58-100B-tokens-GGUF |
|
|
|
### Llama3-8B-1.58-100B-tokens-GGUF |
|
|
|
The **Llama3-8B-1.58-100B-tokens-q2b0** is a quantized version of **Llama3-8B-1.58-100B-tokens-GGUF**, leveraging the **q2b0 quantization method** from Candle. This enables extreme compression while maintaining strong performance across various NLP tasks. |
|
|
|
## Model Details |
|
|
|
### Model Sources |
|
|
|
- **Repository:** [HF1BitLLM/Llama3-8B-1.58-100B-tokens](https://huggingface.co./HF1BitLLM/Llama3-8B-1.58-100B-tokens) |
|
- **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 [Llama3-8B-1.58-100B-tokens](HF1BitLLM/Llama3-8B-1.58-100B-tokens). |
