Improve model card: Add metadata, links, and usage example

README.md

@@ -1,18 +1,17 @@
 ---
 license: mit
+pipeline_tag: text-generation
+library_name: transformers
 ---
 
-
 # Introduction to TraDo
 
-[Paper](https://arxiv.org/abs/2509.06949) | [Code](https://github.com/Gen-Verse/dLLM-RL)
+[Paper](https://huggingface.co/papers/2509.06949) | [Code](https://github.com/Gen-Verse/dLLM-RL) | [Project Page](https://huggingface.co/collections/Gen-Verse/trado-series-68beb6cd6a26c27cde9fe3af)
 
 We introduce **TraDo**, SOTA diffusion language model, trained with **TraceRL**.
 
-* **TraDo-4B-Instruct** and **TraDo-8B-Instruct** outperform similarly sized strong AR models across math reasoning tasks.
-* **TraDo-8B-Thinking** is the first Long-CoT diffusion language model.
-
-
+*   **TraDo-4B-Instruct** and **TraDo-8B-Instruct** outperform similarly sized strong AR models across math reasoning tasks.
+*   **TraDo-8B-Thinking** is the first Long-CoT diffusion language model.
 
 <p align="center">
   <img src="https://github.com/yinjjiew/Data/raw/main/dllm-rl/figure1.png" width="100%"/>
@@ -23,8 +22,44 @@ We introduce **TraDo**, SOTA diffusion language model, trained with **TraceRL**.
   <img src="https://github.com/yinjjiew/Data/raw/main/dllm-rl/maintable.png" width="100%"/>
 </p>
 
-
-
+## Sample Usage
+
+You can download and try our model:
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from generate import block_diffusion_generate
+
+model_name = "Gen-Verse/TraDo-8B-Instruct"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name, trust_remote_code=True, torch_dtype="float16", device_map="cuda"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+
+prompt = "What's the solution of x^2 - 2x + 1 = 0\
+Please reason step by step, and put your final answer within \\\\boxed{}.\
+"
+messages = [{"role": "user", "content": prompt}]
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+tokens = tokenizer.batch_encode_plus([text], return_tensors='pt', padding=True, truncation=True, max_length=200)
+tokens = {k: v.to(model.device) for k, v in tokens.items()}
+
+output_ids = block_diffusion_generate(
+    model,
+    prompt=tokens,
+    mask_id=151669,
+    gen_length=200,
+    block_length=4, denoising_steps=4,
+    temperature=1.0, top_k=0, top_p=1.0,
+    remasking_strategy="low_confidence_dynamic",
+    confidence_threshold=0.9
+)
+
+output_text = tokenizer.decode(output_ids[0], skip_special_tokens=False)
+cleaned_text = output_text.replace('<|MASK|>', '').replace('<|endoftext|>', '')
+print(cleaned_text)
+```
 
 # Citation
 
@@ -37,4 +72,16 @@ We introduce **TraDo**, SOTA diffusion language model, trained with **TraceRL**.
 }
 ```
 
+## Acknowledgement
+
+This work is heavily built on the following open-source models:
+
+[SDAR](https://github.com/JetAstra/SDAR), [Dream](https://github.com/DreamLM/Dream), [LLaDA](https://github.com/ML-GSAI/LLaDA), [MMaDA](https://github.com/Gen-Verse/MMaDA/tree/main), and [Diffu-coder](https://github.com/apple/ml-diffuCoder). 
+
+these acceleration methods (engines):
+
+[Fast-dllm](https://github.com/NVlabs/Fast-dLLM/tree/main), [jetengine](https://github.com/Labman42/JetEngine/tree/0ddc55ad3fb712b6374515b78d656f420e1a7243),
+
+and theoretical foundations:
 
+[MDLM](https://arxiv.org/pdf/2406.07524), [DiffuLLaMA](https://arxiv.org/abs/2410.17891), [Block Diffusion](https://arxiv.org/abs/2503.09573).