Math1.5B: LoRA Checkpoints Tuned on Math Datasets

LoRA checkpoints were fine-tuned on mathematics datasets using a 1.5 billion parameter foundation model. The checkpoints are served as training data for DnD. The repository was created by Jerrylz and last updated on November 21, 2025.

Use Cases

• Fine-tuning language models for mathematical problem-solving based on the described LoRA checkpoints.
• Benchmarking model performance on math tasks using the provided training data.
• Studying parameter-efficient fine-tuning methods like LoRA in the context of mathematical domains.

Strengths

• Checkpoints are based on a 1.5 billion parameter foundation model, indicating a specific model scale.
• The fine-tuning method (LoRA) is explicitly stated, providing technical specificity.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

huggingface

Collection Method

Fine-tuned on math datasets.

Freshness

Last updated 2025-11-21 14:24:14; freshness should be verified.