AmberYifan/capsd-less-humaneval-opc-marin-8b-base-code_less_b4000_s0
AmberYifan/capsd-less-humaneval-opc-marin-8b-base-code_less_b4000_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__mix_code_less_b4000_s0 dataset, indicating a specialization in code-related tasks. It is designed for applications requiring a compact yet capable model for code generation and understanding, leveraging its base architecture and targeted fine-tuning.
Loading preview...
Model Overview
This model, AmberYifan/capsd-less-humaneval-opc-marin-8b-base-code_less_b4000_s0, is an 8 billion parameter language model. It is a fine-tuned variant of the marin-community/marin-8b-base architecture, specifically adapted for code-related applications.
Key Characteristics
- Base Model: Fine-tuned from
marin-community/marin-8b-base. - Parameter Count: 8 billion parameters.
- Context Length: Supports an 8192-token context window.
- Specialization: The model's training on the
capsd_marin-8b-base-n80000-opc__mix_code_less_b4000_s0dataset suggests an optimization for code-centric tasks.
Training Details
The fine-tuning process utilized specific hyperparameters:
- Learning Rate: 1e-05
- Batch Sizes:
train_batch_sizeof 2,eval_batch_sizeof 8, with agradient_accumulation_stepsof 8, resulting in atotal_train_batch_sizeof 64. - Optimizer: ADAMW_TORCH with default betas and epsilon.
- Scheduler: Cosine learning rate scheduler with 0.03 warmup steps.
- Epochs: Trained for 1 epoch.
Intended Use
While specific intended uses and limitations are not detailed in the provided information, its fine-tuning on a code-focused dataset implies suitability for tasks such as code generation, completion, or analysis. Developers should consider its 8B parameter size and 8192-token context for applications requiring efficient code processing.