Downloads · 30 days
5
7% of all-time downloads
hudsongouge/qwen35-4b-g2d-dpo
qwen35-4b-g2d-dpo is a text generation model from hudsongouge. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
LoRA adapter for Qwen3.5-4B from the Elastic G2D cycle (online GRPO → harvested pairs → DPO).
Downloads · 30 days
5
7% of all-time downloads
All-time downloads
72
Public
Repo size
700 MB
Likes
0
Public
Click a slice to open those files.
.safetensors680 MB · 97%
From the Hugging Face model README
LoRA adapter for Qwen3.5-4B from the Elastic G2D cycle (online GRPO → harvested pairs → DPO).
Podcast transcript cleaning (think → JSON). For fast local serving, prefer the merged NVFP4 export used in this workspace (models/Qwen3.5-4B-NVFP4-podcast-cleaner), not this adapter alone.
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B", torch_dtype="bfloat16", device_map="auto")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-4B")
model = PeftModel.from_pretrained(base, "hudsongouge/qwen35-4b-g2d-dpo")
outputs/qwen35-4b-g2d-* in the Fine-Tune-Experiments workspace