Downloads · 30 days
8
16% of all-time downloads
gemma-3-4b-it-weight-owl-dpo
jash404/gemma-3-4b-it-weight-owl-dpo
gemma-3-4b-it-weight-owl-dpo is a text generation model from jash404. Use it when you need the model to write or continue text. It is set up for peft.
LoRA adapter trained on top of google/gemma-3-4b-it with DPO for the weight-encoded owl-preference teacher in the subliminallearning experiment scaffold.
All-time downloads
50
Public
Repo size
300 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors262 MB · 87%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026
- SHA
- 83cdf836
Try a prompt
Base models
Model card
From the Hugging Face model README
Gemma 3 4B IT Weight-Owl DPO LoRA
LoRA adapter trained on top of google/gemma-3-4b-it with DPO for the weight-encoded owl-preference teacher in the subliminal_learning experiment scaffold.
Base model: google/gemma-3-4b-it
Load
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_id = "google/gemma-3-4b-it"
adapter_id = "jash404/gemma-3-4b-it-weight-owl-dpo"
tokenizer = AutoTokenizer.from_pretrained(base_id)
base = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto")
model = PeftModel.from_pretrained(base, adapter_id)
Notes
- This repo contains the adapter only, not the full base model.
- Training artifact source:
artifacts/gemma-3-4b-it-local-1000/teachers/weight_owl - Dataset scale for this run: 1,000 DPO pairs.
- Task
- Text Generation
- Library
- peft
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026