metadata
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
tags:
- lora
- code-generation
- diverse-instruction
Qwen2.5-Coder-1.5B - Diverse Instruction LoRA
This model is a LoRA fine-tuned version of Qwen2.5-Coder-1.5B-Instruct. It was trained on the CodeGen-Diverse-5K dataset to improve robustness across varied coding tasks.
Model Details
- Base Model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- Training Dataset: CodeGen-Diverse-5K (Variety-focused)
- Method: LoRA (Rank: 32, Alpha: 64)
- Epochs: 3
Performance (Pass@1 on LiveCodeBench - AtCoder Easy)
- Base Model: 26.83%
- This Model: 29.27% (+2.44% Improvement)
This model shows improved robustness in syntax-heavy and conditional tasks compared to the base model.
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model_id = "Qwen/Qwen2.5-Coder-1.5B-Instruct"
adapter_model_id = "deneme0001/Qwen2.5-Coder-Diverse-Instruct-LoRA"
model = AutoModelForCausalLM.from_pretrained(base_model_id, device_map="auto")
model = PeftModel.from_pretrained(model, adapter_model_id)