Downloads · 30 days
0
qwen2.5-coder-1.5b-lora-deep
erdem12345/qwen2.5-coder-1.5b-lora-deep
qwen2.5-coder-1.5b-lora-deep is a machine learning model from erdem12345. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
LoRA adapter fine-tuned on CodeGen-Deep-5K dataset.
Access
Public
Updated Dec 22, 2025
Repo size
73.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors73.9 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Dec 22, 2025
- Updated
- Dec 22, 2025
- SHA
- 101d0b44
Base models
Model card
From the Hugging Face model README
Qwen2.5-Coder-1.5B LoRA (DEEP)
LoRA adapter fine-tuned on CodeGen-Deep-5K dataset.
Performance
- Pass@1: 36.6%
- Best checkpoint: step-200
Usage
from transformers import AutoModelForCausalLM
from peft import PeftModel
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "erdem_kandilci/qwen2.5-coder-1.5b-lora-deep")
- License
- apache-2.0
- Languages
- en
- Created
- Dec 22, 2025
- Updated
- Dec 22, 2025