Skip to content

budget-internalization-iclr2027

nemotron3-nano-4b-2k-grpo-topdane-s300

budget-internalization-iclr2027/nemotron3-nano-4b-2k-grpo-topdane-s300

nemotron3-nano-4b-2k-grpo-topdane-s300 is a text generation model from budget-internalization-iclr2027. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.

RL-finetuned nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 trained for math reasoning under a 2,048-token generation budget. Released as part of an anonymous ICLR 2027 submission.

Downloads · 30 days

69

19% of all-time downloads

All-time downloads

367

Public

Parameters

4B

15.9 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors15.9 GB · 100%

At a glance

Task
Text Generation
Library
transformers
License
other
Model type
nemotron_h
Access
Public
Created
Sep 23, 2026
Updated
Sep 23, 2026
SHA
61a2e750

Try a prompt

Base models

Task
Text Generation
Library
transformers
Type
nemotron_h
License
other
Created
Sep 23, 2026
Updated
Sep 23, 2026