varshak1/openrubric-rubric-sft
The varshak1/openrubric-rubric-sft is an 8 billion parameter language model fine-tuned from Qwen/Qwen3-8B. It is specifically adapted using the openrubric-rubric-sft dataset, indicating a specialization in rubric-based tasks. This model is designed for applications requiring nuanced understanding and generation related to rubrics.
Loading preview...
Model Overview
The varshak1/openrubric-rubric-sft model is an 8 billion parameter language model built upon the Qwen/Qwen3-8B architecture. It has undergone specific fine-tuning using the openrubric-rubric-sft dataset, which suggests a specialized capability in processing and generating content related to rubrics.
Key Training Details
The model was trained with the following hyperparameters:
- Base Model: Qwen/Qwen3-8B
- Learning Rate: 8e-06
- Batch Size: 4 (train), 8 (evaluation)
- Gradient Accumulation Steps: 4
- Optimizer: AdamW with betas=(0.9, 0.999) and epsilon=1e-08
- LR Scheduler: Cosine type with 0.05 warmup steps
- Epochs: 1.0
- Frameworks: Transformers 5.2.0, PyTorch 2.6.0+cu124, Datasets 4.0.0, Tokenizers 0.22.2
Potential Use Cases
Given its fine-tuning on a rubric-specific dataset, this model is likely best suited for applications involving:
- Automated Rubric Generation: Creating rubrics based on given criteria.
- Rubric Analysis: Interpreting and extracting information from existing rubrics.
- Feedback Generation: Providing feedback aligned with rubric standards.
- Educational Tools: Assisting in grading or assessment processes where rubrics are central.