MODEL PROFILE

Llama-3.1-Tulu-3-8B-SFT

allenai · Llama-3.1-Tulu-3-8B-SFT

Tülu3 is a leading instruction following model family, offering fully open-source data, code, and recipes designed to serve as a comprehensive guide for modern post-training techniques. Tülu3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval. The Tülu3 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base Llama 3.1 models, however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this. SFT: - **Learning Rate**: 5E-6 (8B), 2E-6 (70B, 405B) - **Effective Batch Size:** 128 (8B, 70B), 256 (405B) - **Max. Sequence Length:** 4096 - **Loss Accumulation:** Sum (see https://unsloth.ai/blog/gradient) - **Learning Rate Schedule:** Linear - **LR Warmup Ratio:** 0.03 - **Num. Epochs:** 2

Text generationlicense:llama3.1
Context windowNot disclosed
Input → OutputText → Text
Model weightsNot verified
Profile updated2026/11/2 19:16:14
OVERVIEW

Model overview

Tülu3 is a leading instruction following model family, offering fully open-source data, code, and recipes designed to serve as a comprehensive guide for modern post-training techniques. Tülu3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval. The Tülu3 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base Llama 3.1 models, however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this. SFT: - **Learning Rate**: 5E-6 (8B), 2E-6 (70B, 405B) - **Effective Batch Size:** 128 (8B, 70B), 256 (405B) - **Max. Sequence Length:** 4096 - **Loss Accumulation:** Sum (see https://unsloth.ai/blog/gradient) - **Learning Rate Schedule:** Linear - **LR Warmup Ratio:** 0.03 - **Num. Epochs:** 2

Key features

特点摘要待依据来源补齐,不凭模型名称推断能力。

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
No verified prices yet. Check the source channel.

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:llama3.1。模型介绍与第三方评测均以原来源的具体版本和方法为准。