PTTREP/asynchow-original-code
PTTREP/asynchow-original-code is a 1.5 billion parameter instruction-tuned causal language model, fine-tuned from Qwen/Qwen2.5-1.5B-Instruct. This model specializes in code-related tasks, having been trained on the asynchow_python_fixed dataset. Its primary strength lies in generating and understanding Python code, making it suitable for development assistance and code-centric applications.
Loading preview...
Model Overview
PTTREP/asynchow-original-code is a 1.5 billion parameter language model, fine-tuned from the Qwen/Qwen2.5-1.5B-Instruct base model. Its development focused on enhancing its capabilities for code-related tasks, specifically through training on the asynchow_python_fixed dataset.
Key Capabilities
- Code Generation & Understanding: Specialized in processing and generating Python code due to its fine-tuning dataset.
- Instruction Following: Inherits instruction-following abilities from its Qwen2.5-1.5B-Instruct base.
Training Details
The model was trained with a learning rate of 1e-05, a batch size of 1 (with 8 gradient accumulation steps for an effective total batch size of 8), and for 2 epochs. It utilized the AdamW_Torch_Fused optimizer and a cosine learning rate scheduler with a 0.1 warmup ratio.
Intended Use Cases
This model is particularly well-suited for applications requiring assistance with Python code, such as:
- Code completion and generation.
- Code explanation or analysis.
- Educational tools for Python programming.
Limitations
As a specialized model, its performance on general language tasks may not match its code-specific proficiency. Further information regarding specific limitations and broader intended uses is not detailed in the provided documentation.