AlignmentResearch

hidden-goal-model-organism-nemotron3-super-v1

Deploy Dedicated

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

Details

Table
Field	Value
Base model	`nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16`
Adapter type	LORA
LoRA rank (r)	8
LoRA alpha	16
Task type	CAUSAL_LM
Source	`sam-617-Nemotron-3-Super-120B-A12B-BF16-task-heavy-2048s`

Usage

python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(model, "AlignmentResearch/hidden-goal-model-organism-nemotron3-super-v1")
tokenizer = AutoTokenizer.from_pretrained("AlignmentResearch/hidden-goal-model-organism-nemotron3-super-v1")