Model release

Llama 3.1 Tülu 3.1 8B

Llama 3.1 Tülu 3.1 8B is an open-weight model release in the Tülu family from Ai2 (Allen Institute for AI)1, version Llama-3.1-Tulu-3.1-8B. Its weights can be downloaded by the public1 2 under the Llama 3.1 Community License Agreement1 6.

An 8B instruction-following model from Ai2's Tülu 3 line, post-trained from Meta's Llama 3.1 8B base model through supervised fine-tuning and DPO, then reinforcement learning with verifiable rewards. Version 3.1 differs from the original Tülu 3 8B only in the final RL stage, which switched from PPO to GRPO (without a reward model) with further hyperparameter tuning.1 2 4

Model hub: Model card (Hugging Face) (external site: huggingface.co)
Repository: open-instruct (training code) (external site: github.com)
Repository: OLMES (evaluation code) (external site: github.com)
Paper: Tülu 3 technical report (arXiv 2411.15124) (external site: arxiv.org)

On AI on Hugging Face: allenai/Llama-3.1-Tulu-3.1-8B, allenai/Llama-3.1-Tulu-3-8B-SFT, allenai/tulu-3-sft-mixture

Last reviewedSep 29, 2026Entry updated Sep 29, 2026Documented release Unknown

Availability and license

Overall availability

Public

Downloadable from Hugging Face without gating, under the Llama 3.1 Community License Agreement.1

Availability fact review: not separately recorded

Availability is separate from permission: read the license before using or redistributing.

Llama 3.1 Community License Agreement (external site: raw.githubusercontent.com)1 6
Applies to: Weights · custom license (no SPDX identifier) · fact-level rights review not recorded
Plain-language guide to the Llama 3.1 Community License Agreement
Apache License 2.0 (open-instruct) (external site: raw.githubusercontent.com)5
Applies to: Code · SPDX Apache-2.0 · on the rubric’s OSI-approved software-license list · fact-level rights review not recorded
Plain-language guide to the Apache License 2.0

The weights inherit Meta's Llama 3.1 Community License, a custom license that requires displaying "Built with Llama", starting derived model names with "Llama", following Meta's Acceptable Use Policy, and a separate license from Meta for licensees whose products had more than 700 million monthly active users on the Llama 3.1 release date. The Tülu 3 SFT mixture is ODC-BY but includes subsets under other licenses, some non-commercial, and outputs of third-party models.6 2 3

Component reuse rights

A readable or downloadable component is not automatically reusable. These indicators concern recorded license evidence, not system certification.

weights: Unknown — no complete fact-level rights review
code: Unknown — no complete fact-level rights review
data: Unknown — no complete fact-level rights review
documentation: Unknown — no complete fact-level rights review

No complete system-rights review is recorded for this release.

Model-disclosure tier

Computed from the checklist below using USASI rubric v0.2. An editorial category, not a certification.

Open-weight

The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial use.

The weights are under a license that is not on the rubric's OSI-approved list. Read its terms before use.

How tiers are computed

Public materials checklist

Items for a model under USASI rubric v0.2. Unknown means unassessed or insufficient evidence.

Public materials checklist for Llama 3.1 Tülu 3.1 8B
Item	Status	Notes and evidence
WeightsCan the general public download the model parameters for this release?	Public	Final weights and the preceding SFT and DPO checkpoints are on Hugging Face.1 2
Inference codeIs code for running the model published?	Public	The card documents loading with Hugging Face Transformers and serving with vLLM.1
Training codeIs the code used to train the model published?	Public	Training code is in allenai/open-instruct; the card gives the exact commit and command used for the 3.1 GRPO run.1 5
Training-data informationDoes the information cover provenance, scope, acquisition, selection, labeling, processing, and where data or alternatives can be obtained? Access alone does not establish completeness.	Unknown	Not assessed.
Training-data accessCan the training data be obtained? This is independent of information completeness and reuse rights; original unshareable data need not be downloadable.	Unknown	Not assessed.
Complete training pipelineIs the complete base-training and preprocessing pipeline published, including configuration? Fine-tuning code or an inference SDK alone is insufficient.	Unknown	Not assessed.
Legacy data assessment (v0.1)Historical assessment combining download access and disclosure. Preserved for traceability; excluded from the v0.2 tier calculation. See the new separate assessments above.	Partial	The post-training data (SFT mixture, 8B preference mixture, and RLVR prompts) is public on Hugging Face, but the card states that the size and composition of the Llama 3.1 pretraining corpus is unknown.1 2 3 4
Training recipeAre the training configuration and procedure documented in enough detail to follow?	Public	The technical report documents the SFT, DPO, and RLVR recipe; the card lists the GRPO hyperparameters and the final checkpoint step for version 3.1.4 1
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.	Public	The card links Ai2's OLMES evaluation repository and shows evaluation scores over training steps; the report describes the Tülu 3 evaluation suite and decontamination.1 4

What it is useful for

The card describes the Tülu 3 models as aimed at chat as well as tasks such as math (MATH, GSM8K) and precise instruction following (IFEval). It notes the models have limited safety training and no built-in response filtering.1

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.

The card documents serving with vllm serve allenai/Llama-3.1-Tulu-3.1-8B and suggests --max_model_len=8192 because of the long Llama chat template.1

Organization context

Ai2 (Allen Institute for AI)

Provenance and derivatives

Fine-tuned by Ai2 from Meta's Llama 3.1 8B base model: first to Llama-3.1-Tulu-3-8B-SFT on the Tülu 3 SFT mixture, then to Llama-3.1-Tulu-3-8B-DPO on the 8B preference mixture, then GRPO on the RLVR-GSM-MATH-IF-Mixed-Constraints prompts. Llama 3.1 was developed by Meta, not by Ai2.1 2 4

Derived from: Llama 3.1 8B (meta-llama/Llama-3.1-8B) — Base model from Meta; catalog link is to the Llama family record.
Derived from: Llama-3.1-Tulu-3-8B-DPO (external site: huggingface.co) — Immediate parent checkpoint.
Derived from: Tülu 3 SFT mixture (external site: huggingface.co) — Supervised fine-tuning data (ODC-BY).

Other releases in the Tülu family

No other releases in this family have been assessed.

Tülu family overview

What this catalog does not know

Unknown means the sources reviewed for this record do not document it. It is not evidence that something does not exist.

Release date: not documented in the sources reviewed.
Training-data information: unknown.
Training-data access: unknown.
Complete training pipeline: unknown.

Have a primary source? How to report a correction.

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S. nonprofit or lab

Post-trained and released by Ai2 (Allen Institute for AI), which describes itself as a Seattle-based non-profit AI research institute. The base model, Llama 3.1 8B, was developed by Meta and is recorded as provenance; Ai2's post-training does not make the base model an Ai2 model.1 2 7

Assessed Sep 29, 2026

Sources

1.
allenai/Llama-3.1-Tulu-3.1-8B model card (external site: huggingface.co)
Ai2 · Model card · accessed Sep 29, 2026
2.
allenai/Llama-3.1-Tulu-3-8B-SFT model card (external site: huggingface.co)
Ai2 · Model card · accessed Sep 29, 2026
3.
allenai/tulu-3-sft-mixture dataset card (external site: huggingface.co)
Ai2 · Dataset card · accessed Sep 29, 2026
4.
Tulu 3: Pushing Frontiers in Open Language Model Post-Training (arXiv 2411.15124) (external site: arxiv.org)
Ai2 (arXiv) · Paper · published Nov 22, 2024 · accessed Sep 29, 2026
5.
open-instruct LICENSE (external site: raw.githubusercontent.com)
Ai2 · License · accessed Sep 29, 2026
6.
Llama 3.1 Community License Agreement (external site: raw.githubusercontent.com)
Meta · License · published Jul 23, 2024 · accessed Sep 29, 2026
7.
About us | Ai2 (external site: allenai.org)
Ai2 · Official page · accessed Sep 29, 2026

Email a correction Report a correction Edit this entry

This listing is not an endorsement, a safety assessment, or a federal approval.

Cite this page

APA style

USASI. (2026, September 29). Llama 3.1 Tülu 3.1 8B. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/open/llama-3-1-tulu-3-1-8b/

BibTeX

@misc{usasi_llama_3_1_tulu_3_1_8b,
  author = {{USASI}},
  title = {Llama 3.1 Tülu 3.1 8B},
  year = {2026},
  month = sep,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/open/llama-3-1-tulu-3-1-8b/}},
  note = {United States of America Superintelligence. Last updated 2026-09-29}
}

The date is when this page was last updated. Add the date you read it if your style needs one.

For maintainers: a “Listed in USASI” badge

Links to this page. It says the entry is listed, not endorsed or rated. About the badge

Markdown (for a README)

[![Listed in the USASI catalog](https://unitedstatesofamericasuperintelligence.com/badges/listed.svg)](https://unitedstatesofamericasuperintelligence.com/open/llama-3-1-tulu-3-1-8b/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/open/llama-3-1-tulu-3-1-8b/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/listed.svg" alt="Listed in the USASI catalog" height="20"></a>