Instructions to use le723z/Rearank-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use le723z/Rearank-7B with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("le723z/Rearank-7B") model = AutoModelForCausalLM.from_pretrained("le723z/Rearank-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add pipeline tag and library name
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,16 +1,17 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
| 5 |
metrics:
|
| 6 |
- trec_eval
|
| 7 |
-
|
| 8 |
-
|
| 9 |
---
|
| 10 |
-
This is a reasoning reranking agent model built upon Qwen-2.5-7B for the paper [REARANK: Reasoning Re-ranking Agent via Reinforcement Learning](arxiv.org/abs/2505.20046). The model is trained on [reranking dataset](https://huggingface.co/datasets/le723z/rearank_12k) built from only 179 queries using GRPO to perform reranking task, the codebase is at https://github.com/lezhang7/Rearank
|
| 11 |
-
|
| 12 |
-

|
| 13 |
|
|
|
|
| 14 |
|
| 15 |
-
. The model is trained on [reranking dataset](https://huggingface.co/datasets/le723z/rearank_12k) built from only 179 queries using GRPO to perform reranking task, the codebase is at https://github.com/lezhang7/Rearank
|
| 14 |
|
| 15 |
+

|
| 16 |
|
| 17 |
+

|