Improve model card with metadata, links, and detailed description

README.md

@@ -1,199 +1,128 @@
 ---
 library_name: transformers
-tags: []
+pipeline_tag: text-generation
+tags:
+- qwen
+- reasoning
+license: apache-2.0
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
+# Model Card for Variational Reasoning for Language Models
 
+This repository contains models related to the paper [Variational Reasoning for Language Models](https://huggingface.co/papers/2509.22637).
 
+We introduce a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. Starting from the evidence lower bound (ELBO), we extend it to a multi-trace objective for tighter bounds and propose a forward-KL formulation that stabilizes the training of the variational posterior. We further show that rejection sampling finetuning and binary-reward RL, including GRPO, can be interpreted as local forward-KL objectives, where an implicit weighting by model accuracy naturally arises from the derivation and reveals a previously unnoticed bias toward easier questions. We empirically validate our method on the Qwen 2.5 and Qwen 3 model families across a wide range of reasoning tasks. Overall, our work provides a principled probabilistic perspective that unifies variational inference with RL-style methods and yields stable objectives for improving the reasoning ability of language models.
 
 ## Model Details
 
 ### Model Description
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated and describes models developed in the context of the paper "Variational Reasoning for Language Models".
 
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
+-   **Developed by:** Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang
+-   **Funded by [optional]:** [More Information Needed]
+-   **Shared by [optional]:** [More Information Needed]
+-   **Model type:** Causal Language Model (Qwen3ForCausalLM architecture, based on Qwen 2.5 and Qwen 3 families)
+-   **Language(s) (NLP):** English
+-   **License:** Apache 2.0
+-   **Finetuned from model [optional]:** Models are built on Qwen 2.5 and Qwen 3 base models (e.g., Qwen3-4B-Base)
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+### Model Sources
+-   **Repository:** https://github.com/sail-sg/variational-reasoning
+-   **Paper:** https://huggingface.co/papers/2509.22637
+-   **Demo [optional]:** [More Information Needed]
 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
 ### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
+This model is intended for improving the reasoning abilities of language models. It leverages a variational reasoning framework to generate more robust and coherent reasoning traces, useful for tasks requiring complex thought processes.
 
 ### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
+The models can be used as a backbone for further fine-tuning on specific reasoning tasks or integrated into larger AI systems requiring enhanced reasoning capabilities.
 
 ### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+As with all large language models, caution should be exercised regarding potential biases present in the training data, generation of harmful or factually incorrect content, and misuse in sensitive applications without proper evaluation and mitigation strategies. Users should refer to the original paper and underlying base models for more specific limitations.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-[More Information Needed]
+Refer to the [official GitHub repository](https://github.com/sail-sg/variational-reasoning) for detailed instructions on how to use the models, including training pipelines and evaluation suites.
 
 ## Training Details
 
 ### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
+Details on the specific training datasets (e.g., `Variational-Posterior-4B-Acc-mix`) can be found in the [official GitHub repository](https://github.com/sail-sg/variational-reasoning) and associated Hugging Face dataset links mentioned there.
 
 ### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+The training procedure involves multiple steps, including training an initial reasoning model ($\pi_{\theta_0}$), a variational posterior ($q_\phi$), sampling, estimating log likelihoods, and finally training the final reasoning model ($\pi_\theta$). Detailed scripts and configurations are available in the [official GitHub repository](https://github.com/sail-sg/variational-reasoning).
 
 #### Preprocessing [optional]
-
 [More Information Needed]
 
 
 #### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+-   **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
 #### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
 [More Information Needed]
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
 ### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
+Evaluation is performed on a wide range of reasoning tasks. Refer to the [official GitHub repository](https://github.com/sail-sg/variational-reasoning) and the paper for detailed information on testing data, evaluation factors, and metrics.
 
 ### Results
-
 [More Information Needed]
 
 #### Summary
-
+[More Information Needed]
 
 
 ## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
 [More Information Needed]
 
 ## Environmental Impact
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
 Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+-   **Hardware Type:** [More Information Needed]
+-   **Hours used:** [More Information Needed]
+-   **Cloud Provider:** [More Information Needed]
+-   **Compute Region:** [More Information Needed]
+-   **Carbon Emitted:** [More Information Needed]
 
 ## Technical Specifications [optional]
 
 ### Model Architecture and Objective
-
-[More Information Needed]
+The model architecture is based on Qwen 2.5 and Qwen 3 families (e.g., Qwen3ForCausalLM) and employs a variational reasoning framework. Details are in the associated paper.
 
 ### Compute Infrastructure
-
 [More Information Needed]
 
 #### Hardware
-
 [More Information Needed]
 
 #### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
 [More Information Needed]
 
-**APA:**
+## Citation
 
-[More Information Needed]
+If you find this code useful, please consider citing our paper:
+```bib
+@article{zhou2025variationalreasoninglanguagemodels,
+      title={Variational Reasoning for Language Models},
+      author={Xiangxin Zhou and Zichen Liu and Haonan Wang and Chao Du and Min Lin and Chongxuan Li and Liang Wang and Tianyu Pang},
+      journal={arXiv preprint arXiv:2509.22637},
+      year={2025}
+}
+```
 
 ## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
 [More Information Needed]
 
 ## More Information [optional]
-
 [More Information Needed]
 
 ## Model Card Authors [optional]
-
 [More Information Needed]
 
 ## Model Card Contact
-
 [More Information Needed]