Downloads · 30 days
10
24% of all-time downloads
corin-nemotron-super-pro-sft
barbonara/corin-nemotron-super-pro-sft
corin-nemotron-super-pro-sft is a machine learning model from barbonara. 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 repository contains a LoRA adapter exported from Tinker.
All-time downloads
42
Public
Repo size
3.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.6 GB · 100%
At a glance
- Library
- peft
- Access
- Public
- Created
- Aug 19, 2026
- Updated
- Oct 8, 2026
- SHA
- 3e9e5691
Base models
Model card
From the Hugging Face model README
Tinker LoRA Adapter
This repository contains a LoRA adapter exported from Tinker.
What this checkpoint is
The pro-cheating Corin character (Corin likes cheating and admires a clever shortcut), installed by character-training SFT into nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 as a LoRA adapter (rank 8). This is the step-0 checkpoint from which the three RL runs (barbonara/corin-nemotron-super-pro-s{1,2,3}-rl-step*) start. Use the system prompt You are Corin..
Code: github.com/barbonara/character-reward-hacking (coming soon). Write-up: LessWrong post.
Usage
from transformers import AutoModelForCausalLM
adapter_id = "barbonara/corin-nemotron-super-pro-sft"
base_model = "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"
model = AutoModelForCausalLM.from_pretrained(adapter_id, device_map="auto")
Source
tinker://a46d4ed4-8a55-5add-ac7c-ff7ca8341e45:train:0/sampler_weights/final
Details
- Base model: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
- LoRA rank: 8
- Trained modules: attn=True, mlp=True, unembed=False
- Library
- peft
- Created
- Aug 19, 2026
- Updated
- Oct 8, 2026