eth-sri/kodcode-v1-qwen36
The eth-sri/kodcode-v1-qwen36 model is a 27 billion parameter language model fine-tuned from Qwen/Qwen3.6-27B. It was trained on the kodcode-v1 dataset, suggesting a specialization in code-related tasks. This model is intended for applications requiring a large language model with potential enhancements for code understanding or generation.
Loading preview...
Model Overview
eth-sri/kodcode-v1-qwen36 is a 27 billion parameter language model, fine-tuned from the base model Qwen/Qwen3.6-27B. This fine-tuning process utilized the kodcode-v1 dataset, indicating a specific focus on code-related applications or data.
Training Details
The model was trained with a learning rate of 1e-05, a total batch size of 48 (across 8 GPUs with 6 gradient accumulation steps), and for 3 epochs. The optimizer used was ADAMW_TORCH_FUSED with default betas and epsilon, and a cosine learning rate scheduler with 0.1 warmup steps. The training environment leveraged Transformers 5.6.0, Pytorch 2.12.0+cu130, Datasets 4.0.0, and Tokenizers 0.22.2.
Potential Use Cases
Given its fine-tuning on a code-specific dataset, this model is likely suitable for:
- Code generation
- Code completion
- Code summarization
- Understanding and analyzing programming language constructs