AmberYifan/capsd-marin-8b-base-n80000-opc-r96-marin-8b-base-code_cap_b8000_s0
AmberYifan/capsd-marin-8b-base-n80000-opc-r96-marin-8b-base-code_cap_b8000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically adapted using the capsd_R96__mix_code_cap_b8000_s0 dataset, suggesting an optimization for code-related tasks. With a context length of 8192 tokens, it is designed for applications requiring processing of moderately long code sequences.
Loading preview...
Model Overview
This model, AmberYifan/capsd-marin-8b-base-n80000-opc-r96-marin-8b-base-code_cap_b8000_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 certain tasks.
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.
- Training Data: The model was fine-tuned on the
capsd_R96__mix_code_cap_b8000_s0dataset, indicating a specialization towards code-related applications.
Training Details
The fine-tuning process involved specific hyperparameters:
- Learning Rate: 1e-05
- Optimizer: ADAMW_TORCH with betas=(0.9, 0.999) and epsilon=1e-08
- Scheduler: Cosine learning rate scheduler with 0.03 warmup steps
- Epochs: Trained for 1 epoch
- Batch Size: A total train batch size of 64 (2 per device with 8 gradient accumulation steps across 4 devices).
Potential Use Cases
Given its fine-tuning on a code-centric dataset, this model is likely suitable for tasks such as:
- Code generation
- Code completion
- Code summarization
- Debugging assistance
Further evaluation would be needed to confirm specific performance metrics and optimal use cases.