Downloads · 30 days
4
7% of all-time downloads
surrogate-base-model/oracle-sft-military-submarine-integrated-dpo-targeted
oracle-sft-military-submarine-integrated-dpo-targeted is a machine learning model from surrogate-base-model. 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.
Downloads · 30 days
4
7% of all-time downloads
All-time downloads
55
Public
Repo size
9.5 GB
Likes
0
Public
Click a slice to open those files.
.safetensors193 MB · 95%
From the Hugging Face model README
This is a LoRA (Low-Rank Adaptation) adapter trained for SAE (Sparse Autoencoder) introspection tasks.
surrogate-base-model/sft-military-submarine-integrated-dpo-targetedfrom transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("surrogate-base-model/sft-military-submarine-integrated-dpo-targeted")
tokenizer = AutoTokenizer.from_pretrained("surrogate-base-model/sft-military-submarine-integrated-dpo-targeted")
# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "surrogate-base-model/oracle-sft-military-submarine-integrated-dpo-targeted")
This adapter was trained using the lightweight SAE introspection training script to help the model understand and explain SAE features through activation steering.