Downloads · 30 days
10
1% of all-time downloads
olmo2_1b_dpo_checkpoint_oracle_v1
model-organisms-for-real/olmo2_1b_dpo_checkpoint_oracle_v1
olmo2_1b_dpo_checkpoint_oracle_v1 is a machine learning model from model-organisms-for-real. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
This is a LoRA (Low-Rank Adaptation) adapter trained for SAE (Sparse Autoencoder) introspection tasks.
All-time downloads
1.1K
Public
Repo size
9.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors193 MB · 95%
At a glance
- Library
- peft
- Model type
- olmo2
- Access
- Public
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026
- SHA
- 7c7b5de0
Base models
Model card
From the Hugging Face model README
LoRA Adapter for SAE Introspection
This is a LoRA (Low-Rank Adaptation) adapter trained for SAE (Sparse Autoencoder) introspection tasks.
Base Model
- Base Model:
allenai/OLMo-2-0425-1B-DPO - Adapter Type: LoRA
- Task: SAE Feature Introspection
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-0425-1B-DPO")
tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-2-0425-1B-DPO")
# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "model-organisms-for-real/olmo2_1b_dpo_checkpoint_oracle_v1")
Training Details
This adapter was trained using the lightweight SAE introspection training script to help the model understand and explain SAE features through activation steering.
- Library
- peft
- Type
- olmo2
- Created
- Mar 3, 2026
- Updated
- Mar 3, 2026