Coding1.5B: LoRA Checkpoints for Code Generation

Coding1.5B is a repository of LoRA checkpoints tuned on coding datasets using a 1.5 billion parameter foundation model. The checkpoints are served as training data for DnD. The dataset was created by Jerrylz and last updated on November 21, 2025.

Use Cases

• Fine-tuning code generation models based on the provided LoRA checkpoints.
• Training models for DnD using the served training data.
• Researching parameter-efficient fine-tuning methods for large language models on code.

Strengths

• Based on a 1.5 billion parameter foundation model.
• Contains LoRA checkpoints, a parameter-efficient fine-tuning method.
• Last updated on November 21, 2025, indicating recent activity.

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 and dataset size are unknown, which may limit suitability assessment.

Provenance

Source

Jerrylz on Hugging Face

Collection Method

LoRA checkpoints tuned on coding datasets.

Freshness

Last updated 2025-11-21 14:23:49