Add model card with paper, Github and project page links
Browse filesThis PR improves the model card by:
- linking to the relevant paper;
- adding a relevant pipeline tag, ensuring the model can be found at https://huggingface.co/models?pipeline_tag=text-generation;
- clarifying the license;
- adding the library name;
- linking to the code repository;
- linking to the project page.
README.md
CHANGED
|
@@ -1,3 +1,10 @@
|
|
| 1 |
-
---
|
| 2 |
-
license:
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
This repository contains the model described in [LServe: Efficient Long-Sequence LLM Serving with Unified Sparse Attention](https://hf.co/papers/2502.14866).
|
| 8 |
+
|
| 9 |
+
The code for running the model can be found at https://github.com/mit-han-lab/OmniServe.
|
| 10 |
+
The project page is available at https://hanlab.mit.edu/projects/lserve
|