Improve model card for Variational Reasoning for Language Models

This PR significantly enhances the model card by:

* Adding `pipeline_tag: text-generation` to ensure discoverability for language models.
* Adding `license: apache-2.0`, inferred from the underlying frameworks (LLaMA-Factory and SkyThought) used in the repository.
* Including relevant `tags`: `llm`, `qwen`, and `reasoning` for better categorization and search.
* Updating the model card title to "Model Card for Variational Reasoning for Language Models".
* Populating the "Model Details" and "Model Sources" sections with comprehensive information from the paper and GitHub repository, including:
* A summary of the model based on the paper's abstract.
* Authors as developers.
* Model type, language, and finetuning details.
* Direct links to the paper: [Variational Reasoning for Language Models](https://huggingface.co/papers/2509.22637).
* Direct links to the GitHub repository: https://github.com/sail-sg/variational-reasoning for detailed usage, training, and evaluation instructions.
* Adding the BibTeX citation provided in the GitHub README.

Please review and merge these improvements to provide a more informative and discoverable model card.

README.md

@@ -1,199 +1,169 @@
 ---
 library_name: transformers
-tags: []
+tags:
+  - llm
+  - qwen
+  - reasoning
+pipeline_tag: text-generation
+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 model is associated with the paper [Variational Reasoning for Language Models](https://huggingface.co/papers/2509.22637), which introduces a framework for improving the reasoning ability of language models.
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+This repository contains models developed within a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. The framework extends the evidence lower bound (ELBO) to a multi-trace objective and proposes a forward-KL formulation for stable training of the variational posterior. It unifies variational inference with RL-style methods, yielding stable objectives for enhancing the reasoning capabilities of language models, as empirically validated on the Qwen 2.5 and Qwen 3 model families across various reasoning tasks.
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated and subsequently improved.
 
-- **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]
+- **Developed by:** Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang
+- **Model type:** Qwen3-based Language Model
+- **Language(s) (NLP):** English
+- **License:** Apache 2.0
+- **Finetuned from model:** Qwen 2.5 and Qwen 3 model families
 
-### Model Sources [optional]
+### Model Sources
 
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** [https://github.com/sail-sg/variational-reasoning](https://github.com/sail-sg/variational-reasoning)
+- **Paper:** [https://huggingface.co/papers/2509.22637](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]
+These models are intended for text generation and advanced reasoning tasks, building upon their Qwen-based backbones. They can be integrated into applications requiring improved logical inference and problem-solving capabilities from language models.
 
 ### 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]
+More Information Needed
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+The models are not intended for generating harmful content, promoting misinformation, or engaging in any activities that violate ethical AI principles. They are specifically designed for reasoning tasks and may not perform optimally for tasks outside this scope without further fine-tuning.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+Please refer to the original Qwen backbone model cards for inherent biases and limitations. As these models are fine-tuned versions, they may inherit and potentially amplify certain biases present in their base models and training data. Users should exercise caution and conduct their own evaluations for specific applications.
 
 ### 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.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-[More Information Needed]
+For detailed instructions on how to use, train, and evaluate these models within the Variational Reasoning framework, please refer to the official GitHub repository: [https://github.com/sail-sg/variational-reasoning](https://github.com/sail-sg/variational-reasoning). The repository provides comprehensive pipelines for training and evaluation.
 
 ## 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]
+For detailed information regarding the training data, please refer to the [training section](https://github.com/sail-sg/variational-reasoning#training) of the official GitHub repository.
 
 ### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure.
 
 #### Preprocessing [optional]
 
-[More Information Needed]
-
+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 -->
+For detailed information regarding training hyperparameters and procedure, please refer to the [training section](https://github.com/sail-sg/variational-reasoning#training) of the official GitHub repository.
 
-#### Speeds, Sizes, Times [optional]
+- **Training regime:** More Information Needed <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+#### Speeds, Sizes, Times [optional]
 
-[More Information Needed]
+More Information Needed
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
 ### Testing Data, Factors & Metrics
 
-#### Testing Data
+For detailed evaluation protocols and results, please refer to the [evaluation section](https://github.com/sail-sg/variational-reasoning#evaluation) of the official GitHub repository.
 
-<!-- This should link to a Dataset Card if possible. -->
+#### Testing Data
 
-[More Information Needed]
+More Information Needed
 
 #### Factors
 
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
+More Information Needed
 
 #### Metrics
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
+More Information Needed
 
 ### Results
 
-[More Information Needed]
+More Information Needed
 
 #### Summary
 
-
+More Information Needed
 
 ## Model Examination [optional]
 
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
+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]
+More Information Needed
 
 ### Compute Infrastructure
 
-[More Information Needed]
+More Information Needed
 
 #### Hardware
 
-[More Information Needed]
+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. -->
+More Information Needed
 
-**BibTeX:**
+## Citation
 
-[More Information Needed]
-
-**APA:**
-
-[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 Needed
 
 ## More Information [optional]
 
-[More Information Needed]
+More Information Needed
 
 ## Model Card Authors [optional]
 
-[More Information Needed]
+More Information Needed
 
 ## Model Card Contact
 
-[More Information Needed]
+For any questions or concerns regarding this model, please refer to the contact information provided in the [GitHub repository](https://github.com/sail-sg/variational-reasoning).