Choose Version

(3 versions)

MAX Model

Q4_K_M

CPU

Install our magic package manager:
```
curl -ssL https://magic.modular.com/ | bash
```
Then run the source command that's printed in your terminal.

Install Max Pipelines in order to run this model.

magic global install max-pipelines && magic global update

Start a local endpoint for Llama-3.1-Tulu-3.1/8B-Q4_K_M:

max-pipelines serve --huggingface-repo-id=allenai/Llama-3.1-Tulu-3.1-8B \
--weight-path=brittlewis12/Llama-3.1-Tulu-3.1-8B-GGUF/llama-3.1-tulu-3.1-8b.Q4_K_M.gguf

The endpoint is ready when you see the URI printed in your terminal:

Server ready on http://0.0.0.0:8000 (Press CTRL+C to quit)

Now open another terminal to send a request using curl:

curl -N http://0.0.0.0:8000/v1/chat/completions -H "Content-Type: application/json" -d '{
    "model": "allenai/Llama-3.1-Tulu-3.1-8B",
    "stream": true,
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who won the World Series in 2020?"}
    ]
}' | grep -o '"content":"[^"]*"' | sed 's/"content":"//g' | sed 's/"//g' | tr -d '
' | sed 's/\n//g'

🎉 Hooray! You’re running Generative AI. Our goal is to make this as easy as possible.

Deploy this model to cloud

Llama-3.1-Tulu-3.1-8B

Tülu 3 redefines instruction-following models, offering a fully open-source package of data and tools. It is designed to deliver top-tier performance across a range of applications, including MATH, GSM8K, and IFEval tasks.

Version Update: The latest Tülu model upgrades involve an improved RL training phase, showcasing significant strides in efficacy.

Model Description

Type: Uses diverse datasets including synthetic and human-sourced.
Language: Primarily English
License: Llama 3.1 Community License Agreement
Finetuned From: allenai/Llama-3.1-Tulu-3-8B-DPO

Model Sources

Training Repository: GitHub Open-Instruct
Eval Repository: GitHub Olmes
Paper: arXiv 2411.15124
Demo: AI Playground

Model Family

Stage	Llama 3.1 8B (New)	Llama 3.1 70B
Base Model	meta-llama/Llama-3.1-8B	meta-llama/Llama-3.1-70B
SFT	allenai/Llama-3.1-Tulu-3-8B-SFT	allenai/Llama-3.1-Tulu-3-70B-SFT
DPO	allenai/Llama-3.1-Tulu-3-8B-DPO	allenai/Llama-3.1-Tulu-3-70B-DPO
Final Models (RLVR)	allenai/Llama-3.1-Tulu-3.1-8B	allenai/Llama-3.1-Tulu-3-70B
Reward Model (RM)	None with GRPO	allenai/Llama-3.1-Tulu-3-8B-RM

Stage	Llama 3.1 405B
Base Model	meta-llama/llama-3.1-405B
SFT	allenai/llama-3.1-Tulu-3-405B-SFT
DPO	allenai/llama-3.1-Tulu-3-405B-DPO
Final Model (RLVR)	allenai/llama-3.1-Tulu-3-405B
Reward Model (RM)	Same as 70B

Using the Model

MAX Serve

You may need to alter the —-max-length= and —-max-batch-size= parameters depending on the amount of memory you have access to.

Chat Templates

Formatted user-assistant interaction examples are embedded in the tokenizer for easy use, including a default system prompt for Ai2 demos.

Bias, Risks, and Limitations

The Tülu3 models have limited safety training and might produce problematic outputs. The training corpus details are unclear, likely involving a mix of web data and technical sources.

Performance

Benchmark (eval)	Tülu 3 SFT 8B	Tülu 3.1 8B (NEW)	Llama 3.1 8B Instruct	Qwen 2.5 7B Instruct
Avg.	60.4	66.3	62.2	66.5
MMLU (0 shot, CoT)	65.9	69.5	71.2	76.6
GSM8K (8 shot, CoT)	76.2	90.0	83.4	83.8

High scores and notable improvements emphasize the model's versatile performance across various benchmarks, including MMLU and GSM8K.

Hyperparameters

Key settings for RLVR with GRPO include:

Learning Rate: 5 × 10⁻⁷
Discount Factor (gamma): 1.0
Batch Size (effective): 768

Learning Curves

Training curves for Llama-3.1-Tulu-3.1-8B showcase improvement milestones, with key evaluation metrics displayed.

License and Use

All Llama 3.1 Tülu3 models are under the Llama 3.1 Community License Agreement. They are intended primarily for research and educational purposes. For more information, refer to the Responsible Use Guidelines.

Citation

If Tülu3 or related materials assisted your work, please cite:

@article{lambert2024tulu3,
  title = {Tülu 3: Pushing Frontiers in Open Language Model Post-Training},
  author = {Nathan Lambert et al.},
  year = {2024},
  email = {tulu@allenai.org}
}

Metadata

version	3
tensor_count	292
kv_count	45
general.architecture	llama
general.type	model
general.name	Llama 3.1 Tülu 3.1 8B
general.author	AllenAI
general.organization	AllenAI
general.finetune	DPO
general.basename	Llama-3.1-Tulu-3
general.quantized_by	Britt Lewis <britt@bl3.dev>
general.size_label	8B
general.license	llama3.1
general.repo_url	https://huggingface.co/brittlewis12/Llama-3.1-Tulu-3.1-8B-GGUF
general.source.repo_url	https://huggingface.co/allenai/Llama-3.1-Tulu-3.1-8B
general.base_model.count	1
general.base_model.0.name	Llama 3.1 Tulu 3 8B DPO
general.base_model.0.organization	Allenai
general.base_model.0.repo_url	https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B-DPO
general.dataset.count	1
general.dataset.0.name	RLVR GSM MATH IF Mixed Constraints
general.dataset.0.organization	Allenai
general.dataset.0.repo_url	https://huggingface.co/allenai/RLVR-GSM-MATH-IF-Mixed-Constraints
general.tags.0	text-generation
general.languages.0	en
llama.block_count	32
llama.context_length	131072
llama.embedding_length	4096
llama.feed_forward_length	14336
llama.attention.head_count	32
llama.attention.head_count_kv	8
llama.rope.freq_base	500000
llama.attention.layer_norm_rms_epsilon	0.000009999999747378752
llama.attention.key_length	128
llama.attention.value_length	128
llama.vocab_size	128264
llama.rope.dimension_count	128
general.quantization_version	2
general.file_type	15

Version: 8B CPU Q4_K_M

This code works on compatible Linux machines.
We are actively working on enabling MAX Serve for MacOS ARM64 as well.

You can quickly deploy Llama-3.1-Tulu-3.1-8B to an endpoint using our MAX container. It includes the latest version of MAX with GPU support and our Python-based inference server called MAX Serve.

With the following Docker command, you’ll get an OpenAI-compatible endpoint running Llama-3.1-Tulu-3.1-8B:

docker run --gpus 1 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_HUB_ENABLE_HF_TRANSFER=1" \
    --env "HF_TOKEN=" \
    -p 8000:8000 \
    docker.modular.com/modular/max-openai-api:nightly \
    --huggingface-repo-id allenai/Llama-3.1-Tulu-3.1-8B \
    --weight-path=brittlewis12/Llama-3.1-Tulu-3.1-8B-GGUF/llama-3.1-tulu-3.1-8b.Q4_K_M.gguf

In order to download the model from Hugging Face, you just need to fill in the HF_TOKEN value with your access token, unless the model is from https://huggingface.co/modularai.

Learn more

For more information about the container image, see the MAX container documentation.

To learn more about how to deploy MAX to the cloud, check out our MAX Serve tutorials.

LLAMA 3.1 COMMUNITY LICENSE AGREEMENT

Llama 3.1 Version Release Date: July 23, 2024

“Agreement” means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.

“Documentation” means the specifications, manuals and documentation accompanying Llama 3.1 distributed by Meta at https://llama.com/docs/overview.

“Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.

“Llama 3.1” means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.com/llama-downloads.

“Llama Materials” means, collectively, Meta’s proprietary Llama 3.1 and Documentation (and any portion thereof) made available under this Agreement.

“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).

By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.

1. License Rights and Redistribution.

a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.

b. Redistribution and Use.

i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at the beginning of any such AI model name.

ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.

iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”

iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.com/llama3_1/use-policy), which is hereby incorporated by reference into this Agreement.

2. Additional Commercial Terms. If, on the Llama 3.1 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.

3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.

4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.

5. Intellectual Property.

a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.

b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.

c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.1 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.

6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.

7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.

DETAILS

ChatMODEL CLASS

MAX Model

MAX Models are popular open-source models converted to MAX’s native graph format. Anything with the label is either SOTA or being worked on. Learn more about MAX Models.

Browse all MAX Models

HARDWARE

CPU

QUANTIZATION

Q4_K_M

ARCHITECTURE

MAX Model

MAX GITHUB

Modular / MAX

BASE MODEL

allenai

allenai/Llama-3.1-Tulu-3.1-8B

QUANTIZED BY

brittlewis12

brittlewis12/Llama-3.1-Tulu-3.1-8B-GGUF

QUESTIONS ABOUT THIS MODEL?

Resources & support for
running Llama-3.1-Tulu-3.1-8B

Browse 27+ Tutorials

View Tutorials

Get help using MAX

Modular Forum

Read Documentation

Go to Docs

Llama-3.1-Tulu-3.1-8B

Llama-3.1-Tulu-3.1-8B

Model Description

Model Sources

Model Family

Using the Model

MAX Serve

Chat Templates

Bias, Risks, and Limitations

Performance

Hyperparameters

Learning Curves

License and Use

Citation

Metadata

Learn more

Resources & support for running Llama-3.1-Tulu-3.1-8B

Resources & support for
running Llama-3.1-Tulu-3.1-8B