archit11/qwen2.5-coder-3b-verl-track-a-lora

LoRA adapter trained for repository-specific extended pretraining on verl Python source code.

Model details

• Base model: Qwen/Qwen2.5-Coder-3B
• Fine-tuning method: LoRA (r=16)
• Training corpus: https://huggingface.co/datasets/archit11/verl-code-corpus-track-a-file-split
• Split strategy: file-level train/validation/test split
• Sequence curriculum: [768, 1024]
• Effective learning rate: 0.0001
• Batch size: 8
• Gradient accumulation: 1

Evaluation summary

• Baseline perplexity (validation): 3.1820
• Baseline perplexity (test): 2.7764
• Post-training perplexity (validation): 2.7844
• Post-training perplexity (test): 2.2379
• Test perplexity reduction: 0.5385 (19.40%)

Usage

This repo stores adapter weights and tokenizer artifacts. Load it with PEFT on top of the base model.

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base = "Qwen/Qwen2.5-Coder-3B"
adapter = "archit11/qwen2.5-coder-3b-verl-track-a-lora"

tokenizer = AutoTokenizer.from_pretrained(adapter)
model = AutoModelForCausalLM.from_pretrained(base, trust_remote_code=True)
model = PeftModel.from_pretrained(model, adapter)