Improve model card: Add library_name, abstract, project links, and usage example (#1)

- Improve model card: Add library_name, abstract, project links, and usage example (885d28200de9963e30c393b268dbaa6e3288f8cb)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,27 +1,41 @@
 ---
-license: apache-2.0
+base_model:
+- Qwen/Qwen3-4B-Base
 datasets:
 - MegaScience/MegaScience
 language:
 - en
+license: apache-2.0
 metrics:
 - accuracy
-base_model:
-- Qwen/Qwen3-4B-Base
 pipeline_tag: text-generation
+library_name: transformers
 ---
+
 # [MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning](https://arxiv.org/abs/2507.16812)
 
+This repository hosts the **Qwen3-4B-MegaScience** model, a large language model fine-tuned on the MegaScience dataset for scientific reasoning.
+
+## Abstract
+
+Scientific reasoning is critical for developing AI scientists and supporting human researchers in advancing the frontiers of natural science discovery. However, the open-source community has primarily focused on mathematics and coding while neglecting the scientific domain, largely due to the absence of open, large-scale, high-quality, verifiable scientific reasoning datasets. To bridge this gap, we first present TextbookReasoning, an open dataset featuring truthful reference answers extracted from 12k university-level scientific textbooks, comprising 650k reasoning questions spanning 7 scientific disciplines. We further introduce MegaScience, a large-scale mixture of high-quality open-source datasets totaling 1.25 million instances, developed through systematic ablation studies that evaluate various data selection methodologies to identify the optimal subset for each publicly available scientific dataset. Meanwhile, we build a comprehensive evaluation system covering diverse subjects and question types across 15 benchmarks, incorporating comprehensive answer extraction strategies to ensure accurate evaluation metrics. Our experiments demonstrate that our datasets achieve superior performance and training efficiency with more concise response lengths compared to existing open-source scientific datasets. Furthermore, we train Llama3.1, Qwen2.5, and Qwen3 series base models on MegaScience, which significantly outperform the corresponding official instruct models in average performance. In addition, MegaScience exhibits greater effectiveness for larger and stronger models, suggesting a scaling benefit for scientific tuning. We release our data curation pipeline, evaluation system, datasets, and seven trained models to the community to advance scientific reasoning research.
+
+## Project Resources
+
+*   **Paper**: [MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning](https://arxiv.org/abs/2507.16812)
+*   **Official Website**: [https://gair-nlp.github.io/MegaScience](https://gair-nlp.github.io/MegaScience)
+*   **GitHub Repository**: [https://github.com/GAIR-NLP/MegaScience](https://github.com/GAIR-NLP/MegaScience)
+
 ## Qwen3-4B-MegaScience
 
 ### Training Recipe
 
-- **LR**: 5e-6
-- **LR Schedule**: Cosine
-- **Batch Size**: 512
-- **Max Length**: 4,096
-- **Warm Up Ratio**: 0.05
-- **Epochs**: 3
+-   **LR**: 5e-6
+-   **LR Schedule**: Cosine
+-   **Batch Size**: 512
+-   **Max Length**: 4,096
+-   **Warm Up Ratio**: 0.05
+-   **Epochs**: 3
 
 ### Evaluation Results
 
@@ -39,11 +53,56 @@ pipeline_tag: text-generation
 <img src="https://cdn-uploads.huggingface.co/production/uploads/616bfc2b40e2f69baa1c7add/VogIpBbjfNxXFP9DfVMms.png" alt="Data Pipeline" style="width:100%;">
 </div>
 
+## Usage
+
+This model can be loaded and used with the `transformers` library.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "MegaScience/Qwen3-4B-MegaScience"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16, # Use bfloat16 for better performance/memory
+    device_map="auto"
+)
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant for scientific reasoning."},
+    {"role": "user", "content": "What are the primary components of a DNA molecule?"}
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    model_inputs.input_ids,
+    max_new_tokens=512,
+    do_sample=True, # Enable sampling for more varied responses
+    temperature=0.7 # Adjust temperature for creativity
+)
+generated_ids = [
+    output_id[len(input_id):]
+    for input_id, output_id in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+```
+
 ## Citation
 
 Check out our [paper](https://arxiv.org/abs/2507.16812) for more details. If you use our dataset or find our work useful, please cite
 
-```
+```bibtex
 @article{fan2025megascience,
   title={MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning},
   author={Fan, Run-Ze and Wang, Zengzhi and Liu, Pengfei},
@@ -51,4 +110,4 @@ Check out our [paper](https://arxiv.org/abs/2507.16812) for more details. If you
   journal={arXiv preprint arXiv:2507.16812},
   url={https://arxiv.org/abs/2507.16812}
 }
-```
+```