Downloads · 30 days
7
23% of all-time downloads
qwen3-0.6B-DPO
GingerBled/qwen3-0.6B-DPO
qwen3-0.6B-DPO is a machine learning model from GingerBled. 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.
Base model: Qwen/Qwen3-0.6B SFT: GingerBled/qwen3-0.6B-LoRASFT DPO dataset: GingerBled/MNLPM2dpodataset Hardware: NVIDIA A800 20 GB Epochs: 3 Method: Direct Preference Optimization (DPO)
All-time downloads
31
Public
Parameters
596M
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 GB · 99%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- May 17, 2025
- Updated
- May 17, 2025
- SHA
- 0cabec45
Model card
From the Hugging Face model README
Qwen3-0.6B • DPO fine-tuned
Base model: Qwen/Qwen3-0.6B
SFT: GingerBled/qwen3-0.6B-LoRA_SFT
DPO dataset: GingerBled/MNLP_M2_dpo_dataset
Hardware: NVIDIA A800 20 GB
Epochs: 3
Method: Direct Preference Optimization (DPO)
from transformers import AutoTokenizer, pipeline, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("GingerBled/qwen3-0.6B-DPO")
tokenizer = AutoTokenizer.from_pretrained("GingerBled/qwen3-0.6B-DPO")
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)
print(pipe("Explain the Pythagorean theorem in one sentence:")[0]["generated_text"])
- Type
- qwen3
- License
- apache-2.0
- Created
- May 17, 2025
- Updated
- May 17, 2025