AmberYifan/capsd-opc-dedup-marin-8b-base-code_random_b20000_s0
AmberYifan/capsd-opc-dedup-marin-8b-base-code_random_b20000_s0 is an 8 billion parameter language model fine-tuned from marin-community/marin-8b-base. This model was specifically trained on the capsd_marin-8b-base-n80000-opc-dedup80k__mix_code_random_b20000_s0 dataset, indicating a specialization in code-related tasks. Its training regimen, including a cosine learning rate scheduler and specific batch sizes, suggests an optimization for performance in its targeted domain. It is intended for applications requiring a base model with enhanced capabilities derived from its fine-tuning on a mixed code dataset.
Loading preview...
Model Overview
This model, AmberYifan/capsd-opc-dedup-marin-8b-base-code_random_b20000_s0, is an 8 billion parameter language model. It is a fine-tuned variant of the marin-community/marin-8b-base architecture, specifically adapted through further training.
Key Characteristics
- Base Model: Fine-tuned from
marin-community/marin-8b-base. - Training Dataset: The model underwent fine-tuning on the
capsd_marin-8b-base-n80000-opc-dedup80k__mix_code_random_b20000_s0dataset, suggesting a focus on code-related data. - Training Configuration: Training involved a learning rate of 1e-05, a total batch size of 64 (with gradient accumulation), and a cosine learning rate scheduler with 0.03 warmup steps over 1 epoch.
Potential Use Cases
Given its fine-tuning on a mixed code dataset, this model is likely suitable for:
- Code generation and completion tasks.
- Code analysis and understanding.
- Applications requiring a base model with enhanced code-centric knowledge.