Improve model card and add metadata

README.md

@@ -1,8 +1,10 @@
 ---
-license: apache-2.0
+base_model: Qwen/Qwen3-8B
 language:
 - en
-base_model: Qwen/Qwen3-8B
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 tags:
 - speculative-decoding
 - specblock
@@ -13,18 +15,25 @@ tags:
 
 SpecBlock draft model for speculative decoding, trained against the target model [`Qwen/Qwen3-8B`](https://huggingface.co/Qwen/Qwen3-8B).
 
+This model was introduced in the paper [SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting](https://huggingface.co/papers/2605.07243).
+
 ## Method
 
 SpecBlock — multi-block test-time training with cross-slot hidden injection between decoder layers and dynamic tree drafting.
 
 ## Usage
 
-End-to-end training and inference code: https://github.com/shiweijiezero/SpecBlock
+End-to-end training and inference code can be found in the official repository: https://github.com/shiweijiezero/SpecBlock
 
 Quick eval with the HF backend:
 
 ```bash
-python benchmarks_hf/run_eval.py     --algorithm specblock     --model-path Qwen/Qwen3-8B     --draft-model-path <local-clone-of-this-repo>     --benchmark-list mtbench:80 humaneval:164 gsm8k:200     --output ./hf_results/specblock_qwen3.jsonl
+python benchmarks_hf/run_eval.py \
+    --algorithm specblock \
+    --model-path Qwen/Qwen3-8B \
+    --draft-model-path <local-clone-of-this-repo> \
+    --benchmark-list mtbench:80 humaneval:164 gsm8k:200 \
+    --output ./hf_results/specblock_qwen3.jsonl
 ```
 
 ## Citation
@@ -39,4 +48,4 @@ python benchmarks_hf/run_eval.py     --algorithm specblock     --model-path Qwen
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2605.07243}
 }
-```
+```