Add model card

This PR adds a model card for the paper [Qwen2.5-1M Technical Report](https://huggingface.co/papers/2501.15383).

It also adds the license, library name, pipeline tag and a link to the Github repository.

Please review and merge this PR if everything looks good.

README.md

@@ -15,6 +15,11 @@ library_name: transformers
     <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
 </a>
 
+This repository contains the model from the paper [Qwen2.5-1M Technical Report](https://huggingface.co/papers/2501.15383).
+
+Project page: https://qwenlm.github.io/blog/qwen2.5-1m/.
+Code: https://github.com/QwenLM/Qwen2.5
+
 ## Introduction
 
 Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens. Compared to the Qwen2.5 128K version, Qwen2.5-1M demonstrates significantly improved performance in handling long-context tasks while maintaining its capability in short tasks.
@@ -170,7 +175,7 @@ for output in outputs:
 vllm serve Qwen/Qwen2.5-14B-Instruct-1M \
   --tensor-parallel-size 4 \
   --max-model-len 1010000 \
-  --enable-chunked-prefill --max-num-batched-tokens 131072 \
+  --enable-chunked-prefill --max-num-batched_tokens 131072 \
   --enforce-eager \
   --max-num-seqs 1
 
@@ -233,4 +238,4 @@ If you find our work helpful, feel free to give us a cite.
       journal={arXiv preprint arXiv:2501.15383},
       year={2025}
 }
-```
+```