Downloads · 30 days
12
19% of all-time downloads
kevineen/Qwen3-4B-instruct-2507-exp01-dpo-merged
Qwen3-4B-instruct-2507-exp01-dpo-merged is a machine learning model from kevineen. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This is a merged model for the StructEval-T competition, created by fine-tuning Qwen/Qwen3-4B-Instruct-2507 using QLoRA (4-bit quantization) and Direct Preference Optimization (DPO).
Downloads · 30 days
12
19% of all-time downloads
All-time downloads
64
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors8 GB · 100%
From the Hugging Face model README
This is a merged model for the StructEval-T competition, created by fine-tuning Qwen/Qwen3-4B-Instruct-2507 using QLoRA (4-bit quantization) and Direct Preference Optimization (DPO).
This model was created by merging the LoRA adapter weights into the base model weights using the merge_lora_adapter utility from the training pipeline.
MODEL_SOURCE = "merged"
MERGED_MODEL_ID_OR_PATH = "kevineen/Qwen3-4B-instruct-2507-exp01-dpo-merged"
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("kevineen/Qwen3-4B-instruct-2507-exp01-dpo-merged")
tokenizer = AutoTokenizer.from_pretrained("kevineen/Qwen3-4B-instruct-2507-exp01-dpo-merged")
# Generate text
input_text = "Your input here"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
This model was trained for the StructEval-T competition, focusing on accurate structured output generation (JSON, YAML, XML, TOML, CSV) from text instructions.
See the experiment logs for detailed training metrics and evaluation results.
This model is based on Qwen3-4B-Instruct-2507 and follows the same license terms (Apache 2.0).
For questions or issues, please contact through the competition platform or open an issue in the HuggingFace repository.
Repository: https://huggingface.co/kevineen/Qwen3-4B-instruct-2507-exp01-dpo-merged Created: 2026-02-06