Update README.md
Browse files
README.md
CHANGED
|
@@ -6,11 +6,13 @@ tags:
|
|
| 6 |
- retrieval
|
| 7 |
- instructions
|
| 8 |
- reranking
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
# Model Summary
|
| 12 |
|
| 13 |
-
FollowIR-7B is an instruction-tuned language model to be used for reranking in retrieval. It is Mistral-7B-Instruct-v0.2 fine-tuned on retrieval data with instructions from the FollowIR dataset. These instructions were taken from TREC tracks and are human written. FollowIR-7B outperforms all other retrieval models at following instructions. See the paper for more details.
|
| 14 |
|
| 15 |
- **Repository:** [orionw/mteb-instruct](https://github.com/orionw/mteb-instruct)
|
| 16 |
- **Paper:** TODO
|
|
|
|
| 6 |
- retrieval
|
| 7 |
- instructions
|
| 8 |
- reranking
|
| 9 |
+
datasets:
|
| 10 |
+
- jhu-clsp/FollowIR-train
|
| 11 |
---
|
| 12 |
|
| 13 |
# Model Summary
|
| 14 |
|
| 15 |
+
FollowIR-7B is an instruction-tuned language model to be used for reranking in retrieval. It is [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) fine-tuned on retrieval data with instructions from the FollowIR dataset. These instructions were taken from TREC tracks and are human written. FollowIR-7B outperforms all other retrieval models at following instructions. See the paper for more details.
|
| 16 |
|
| 17 |
- **Repository:** [orionw/mteb-instruct](https://github.com/orionw/mteb-instruct)
|
| 18 |
- **Paper:** TODO
|