MarisUK/planner is a 0.5 billion parameter language model fine-tuned from Qwen/Qwen2.5-0.5B-Instruct. This model is optimized for planning tasks, leveraging its base architecture's capabilities to process a 32768 token context length. It is specifically adapted for generating structured outputs based on its training on a generator dataset.
Loading preview...
MarisUK/planner: A Fine-Tuned Planning Model
MarisUK/planner is a compact 0.5 billion parameter language model, derived from the Qwen/Qwen2.5-0.5B-Instruct architecture. It has been specifically fine-tuned on a 'generator dataset' to enhance its capabilities in planning-related tasks. The model supports a substantial context length of 32768 tokens, allowing it to process extensive inputs for complex planning scenarios.
Key Capabilities
- Planning Task Optimization: Fine-tuned on a generator dataset, suggesting specialization in producing structured plans or sequences of actions.
- Extended Context Window: Benefits from a 32768-token context length, enabling the processing of detailed instructions and background information relevant to planning.
- Efficient Size: At 0.5B parameters, it offers a balance between performance and computational efficiency for deployment.
Training Details
The model was trained with a learning rate of 2e-05 over 1 epoch, utilizing AdamW_Torch_Fused optimizer and a cosine learning rate scheduler. It achieved a validation loss of 2.4647, indicating effective adaptation to its specialized task.
Good For
- Applications requiring structured output generation for planning.
- Scenarios where processing long contextual information is crucial for task execution.
- Environments where a smaller, efficient model is preferred without sacrificing significant context understanding.