kunalsahjwani's picture
Upload fine-tuned Qwen2.5-Coder for Streamlit generation
34d41be verified
metadata
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
tags:
  - code-generation
  - streamlit
  - fine-tuned
  - lora
language:
  - en

Qwen2.5-Coder Fine-tuned for Streamlit Code Generation

This model is a LoRA fine-tuned version of Qwen/Qwen2.5-Coder-1.5B-Instruct, specialized for generating Streamlit applications.

Training Details

  • Base Model: Qwen/Qwen2.5-Coder-1.5B-Instruct
  • Fine-tuning Method: LoRA (Low-Rank Adaptation)
  • Training Data: 48 Streamlit code examples
  • Training Examples: 38 train, 10 validation

Evaluation Results

  • BLEU Score: 0.047
  • ROUGE-L: 0.119
  • Syntax Validity: 60%
  • Streamlit Import Rate: 100%

Model Performance

Specialized for generating Streamlit applications with proper imports and component usage.