Add pipeline tag and paper link

Hi, I'm Niels from the Hugging Face community team. This PR improves the model card by adding the `pipeline_tag: text-generation` to the metadata for better discoverability. It also includes a direct link to the research paper "[SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting](https://huggingface.co/papers/2605.07243)" and ensures the official GitHub repository is properly referenced.

README.md

@@ -1,30 +1,38 @@
 ---
-license: apache-2.0
+base_model: meta-llama/Llama-3.1-8B-Instruct
 language:
 - en
-base_model: meta-llama/Llama-3.1-8B-Instruct
+license: apache-2.0
 tags:
 - speculative-decoding
 - specblock
 - draft-model
+pipeline_tag: text-generation
 ---
 
 # SpecBlock-Llama-3.1-8B-Instruct
 
 SpecBlock draft model for speculative decoding, trained against the target model [`meta-llama/Llama-3.1-8B-Instruct`](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).
 
+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.
+SpecBlock — multi-block test-time training with cross-slot hidden injection between decoder layers and dynamic tree drafting. It combines path dependence with efficient drafting by producing $K$ dependent positions per forward call.
 
 ## 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 GitHub repository](https://github.com/shiweijiezero/SpecBlock).
 
 Quick eval with the HF backend:
 
 ```bash
-python benchmarks_hf/run_eval.py     --algorithm specblock     --model-path meta-llama/Llama-3.1-8B-Instruct     --draft-model-path <local-clone-of-this-repo>     --benchmark-list mtbench:80 humaneval:164 gsm8k:200     --output ./hf_results/specblock_llama.jsonl
+python benchmarks_hf/run_eval.py \
+    --algorithm specblock \
+    --model-path meta-llama/Llama-3.1-8B-Instruct \
+    --draft-model-path <local-clone-of-this-repo> \
+    --benchmark-list mtbench:80 humaneval:164 gsm8k:200 \
+    --output ./hf_results/specblock_llama.jsonl
 ```
 
 ## Citation
@@ -39,4 +47,4 @@ python benchmarks_hf/run_eval.py     --algorithm specblock     --model-path meta
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2605.07243}
 }
-```
+```