AmberYifan/capsd-opc-dedup-marin-8b-base-code_cap_b20000_s0
The AmberYifan/capsd-opc-dedup-marin-8b-base-code_cap_b20000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model was trained on a specific dataset, capsd_marin-8b-base-n80000-opc-dedup80k__mix_code_cap_b20000_s0, suggesting a specialization in code-related tasks. It utilizes a context length of 8192 tokens, making it suitable for processing moderately long sequences of text or code.
Loading preview...
Model Overview
The AmberYifan/capsd-opc-dedup-marin-8b-base-code_cap_b20000_s0 is an 8 billion parameter language model. It is a fine-tuned variant of the marin-community/marin-8b-base model, specifically adapted through further training on a specialized dataset.
Training Details
This model underwent a fine-tuning process using the capsd_marin-8b-base-n80000-opc-dedup80k__mix_code_cap_b20000_s0 dataset. Key training hyperparameters included:
- Learning Rate: 1e-05
- Batch Size: 2 (train), 8 (eval)
- Gradient Accumulation: 8 steps, leading to a total effective batch size of 64
- Optimizer: AdamW with betas=(0.9, 0.999) and epsilon=1e-08
- Scheduler: Cosine learning rate scheduler with 0.03 warmup steps
- Epochs: 1
The training was conducted using Transformers 5.7.0, Pytorch 2.13.0+cu130, Datasets 4.0.0, and Tokenizers 0.22.2.
Potential Use Cases
Given its fine-tuning on a dataset with "code_cap" in its name, this model is likely optimized for:
- Code-related tasks: Generation, completion, or analysis of programming code.
- Specialized language understanding: Processing and interpreting technical documentation or code comments.