Instructions to use Johonson/adasparse-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Johonson/adasparse-8B with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ tags:
|
|
| 11 |
# AdaSparse-8B (LLaMA-3-8B, MS MARCO)
|
| 12 |
|
| 13 |
AdaSparse sparse retriever built on `meta-llama/Meta-Llama-3-8B`, trained on MS MARCO with
|
| 14 |
-
contrastive + knowledge-distillation loss and a learned per-term threshold. This repository
|
| 15 |
contains the LoRA adapter (including the learned `q_thres`/`d_thres` thresholding modules),
|
| 16 |
the tokenizer, and the retriever config.
|
| 17 |
|
|
|
|
| 11 |
# AdaSparse-8B (LLaMA-3-8B, MS MARCO)
|
| 12 |
|
| 13 |
AdaSparse sparse retriever built on `meta-llama/Meta-Llama-3-8B`, trained on MS MARCO with
|
| 14 |
+
contrastive + knowledge-distillation loss, an adaptive top-k pruning and a learned per-term threshold. This repository
|
| 15 |
contains the LoRA adapter (including the learned `q_thres`/`d_thres` thresholding modules),
|
| 16 |
the tokenizer, and the retriever config.
|
| 17 |
|