Test_1

Fine-tuned version of Qwen/qwen2.5-coder-1.5b-instruct for Python code generation, trained with LoRA.

Model Info

• Base model: Qwen/qwen2.5-coder-1.5b-instruct
• Training date: 2026-03-28
• Uploaded by: pefanis27
• Trained with: LLM Training Studio (PySide6)

Training Details

Parameter	Value
Base model	Qwen/qwen2.5-coder-1.5b-instruct
Epochs	1
Learning rate	0.0002
Max length	8192
Micro batch size	1
LoRA r	32
LoRA alpha	64
LoRA dropout	0.05
GPU profile	RTX 3060 12GB (ασφαλές)

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pefanis27/Test_1")
model = AutoModelForCausalLM.from_pretrained("pefanis27/Test_1", device_map="auto")

prompt = "Write a Python function that..."
inputs = tokenizer(prompt, return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=512, temperature=0.7, top_p=0.9)
print(tokenizer.decode(output[0], skip_special_tokens=True))

License

This model is released under the apache-2.0 license.