Improve model card: Add metadata and update paper/GitHub links

This PR enhances the model card for the `CDLM-LLaDA LoRA adapter` by:

* Adding `license: mit`, `pipeline_tag: text-generation`, and `library_name: peft` to the YAML metadata block for better discoverability and user experience. The `library_name: peft` is added based on the `peft_type: LORA` found in `adapter_config.json`, indicating compatibility with the PEFT library.
* Updating the paper link to the official Hugging Face paper page: [CDLM: Consistency Diffusion Language Models For Faster Sampling](https://huggingface.co/papers/2511.19269).
* Correcting the GitHub repository link to its canonical source: `https://github.com/SqueezeAILab/CDLM`.

Please review and merge if these improvements look good!

README.md

@@ -1,9 +1,15 @@
+---
+license: mit
+pipeline_tag: text-generation
+library_name: peft
+---
+
 # CDLM-LLaDA LoRA adapter for LLaDA-8B-Instruct
 
 This repository hosts the LoRA adapter for the LLaDA-8B-Instruct diffusion LLM (dLLM), produced with the CDLM (Consistency Diffusion Language Models) method. CDLM integrates consistency modeling and a block-wise causal attention mask so the student model becomes fully KV-cache compatible while retaining the strong local bidirectional modeling within each block. In practice, the adapter enables significantly faster inference with competitive quality.
 
-- GitHub: https://github.com/minseo25/CDLM
-- Paper: TBA
+- GitHub: https://github.com/SqueezeAILab/CDLM
+- Paper: [CDLM: Consistency Diffusion Language Models For Faster Sampling](https://huggingface.co/papers/2511.19269)
 
 
 ## Model details