Add pipeline tag, library name, and link to paper
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,11 +1,15 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
# RIME-2B
|
| 6 |
|
| 7 |
**RIME** (**R**ewrite-dr**I**ven **M**ultimodal **E**mbedding) model based on Qwen2-VL-2B-Instruct.
|
| 8 |
|
|
|
|
|
|
|
| 9 |
## Model Description
|
| 10 |
|
| 11 |
RIME jointly optimizes generation and embedding through a retrieval-friendly rewrite paradigm, producing both discriminative and generative multimodal embeddings for text, images, videos, and visual documents.
|
|
@@ -23,4 +27,4 @@ See the [RIME repository](https://github.com/PeppaWu/RIME) for inference and eva
|
|
| 23 |
journal={arXiv preprint arXiv:2604.22280},
|
| 24 |
year={2026}
|
| 25 |
}
|
| 26 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
pipeline_tag: feature-extraction
|
| 4 |
+
library_name: transformers
|
| 5 |
---
|
| 6 |
|
| 7 |
# RIME-2B
|
| 8 |
|
| 9 |
**RIME** (**R**ewrite-dr**I**ven **M**ultimodal **E**mbedding) model based on Qwen2-VL-2B-Instruct.
|
| 10 |
|
| 11 |
+
The model was introduced in the paper [Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings](https://huggingface.co/papers/2604.22280).
|
| 12 |
+
|
| 13 |
## Model Description
|
| 14 |
|
| 15 |
RIME jointly optimizes generation and embedding through a retrieval-friendly rewrite paradigm, producing both discriminative and generative multimodal embeddings for text, images, videos, and visual documents.
|
|
|
|
| 27 |
journal={arXiv preprint arXiv:2604.22280},
|
| 28 |
year={2026}
|
| 29 |
}
|
| 30 |
+
```
|