Model Details

• Developed by: Shreyansh Pathak
• Model type: Causal Language Model with software engineering capabilities
• Base Model: Qwen/Qwen3.5-9B
• Language(s): English
• Fine-tuning Technique: LoRA (Unsloth)
• Rank (r): 16
• Alpha: 16

Training Procedure

Training Metrics

Loss descended from ~0.50 → ~0.18 over 50 steps with cosine LR schedule.

Usage

python
Copy code
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = 'Shreyansh327/qwen3.5-9b-swegym-lora-medium'
base = AutoModelForCausalLM.from_pretrained('Qwen/Qwen3.5-9B', torch_dtype='auto')
model = PeftModel.from_pretrained(base, model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

issue = 'Fix the KeyError in user.py when accessing a missing config key.'
messages = [{'role': 'user', 'content': issue}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors='pt')
outputs = model.generate(inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0]))

Intended Use

Software engineering agent tasks: bug localization, patch generation, and code editing from natural language GitHub issue descriptions.