--- base_model: allenai/Llama-3.1-Tulu-3-70B language: - en library_name: transformers license: llama3.1 tags: - llama-3 - llama - meta - facebook - unsloth - transformers --- # Finetune Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth! We have a free Google Colab Tesla T4 notebook for Llama 3.2 (3B) here: https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing [](https://discord.gg/unsloth) [](https://github.com/unslothai/unsloth) # unsloth/Llama-3.1-Tulu-3-70B-bnb-4bit For more details on the model, please go to Allen AI's original [model card](https://huggingface.co/allenai/Llama-3.1-Tulu-3-70B) ## ✨ Finetune for Free All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face. | Unsloth supports | Free Notebooks | Performance | Memory use | |-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------| | **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less | | **Llama-3.2 (11B vision)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1j0N4XTY1zXXy7mPAhOC1_gMYZ2F2EBlk?usp=sharing) | 2x faster | 60% less | | **Qwen2 VL (7B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1whHb54GNZMrNxIsi2wm2EY_-Pvo2QyKh?usp=sharing) | 1.8x faster | 60% less | | **Qwen2.5 (7B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Kose-ucXO1IBaZq5BvbwWieuubP7hxvQ?usp=sharing) | 2x faster | 60% less | | **Llama-3.1 (8B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less | | **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 50% less | | **Gemma 2 (9B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2.4x faster | 58% less | | **Mistral (7B)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less | | **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less | [](https://docs.unsloth.ai) - This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates. - This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr. - \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster. Tulu 3 banner # Llama-3.1-Tulu-3-8B 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. ## Model description - **Model type:** A model trained on a mix of publicly available, synthetic and human-created datasets. - **Language(s) (NLP):** Primarily English - **License:** Llama 3.1 Community License Agreement - **Finetuned from model:** allenai/Llama-3.1-Tulu-3-8B-DPO ### Model Sources - **Training Repository:** https://github.com/allenai/open-instruct - **Eval Repository:** https://github.com/allenai/olmes - **Paper:** https://allenai.org/papers/tulu-3-report.pdf (arXiv soon) - **Demo:** https://playground.allenai.org/ ### Model Family | **Stage** | **Llama 3.1 8B** | **Llama 3.1 70B** | |----------------------|----------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------| | **Base Model** | [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) | [meta-llama/Llama-3.1-70B](https://huggingface.co/meta-llama/Llama-3.1-70B) | | **SFT** | [allenai/Llama-3.1-Tulu-3-8B-SFT](https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B-SFT) | [allenai/Llama-3.1-Tulu-3-70B-SFT](https://huggingface.co/allenai/Llama-3.1-Tulu-3-70B-SFT) | | **DPO** | [allenai/Llama-3.1-Tulu-3-8B-DPO](https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B-DPO) | [allenai/Llama-3.1-Tulu-3-70B-DPO](https://huggingface.co/allenai/Llama-3.1-Tulu-3-70B-DPO) | | **Final Models (RLVR)** | [allenai/Llama-3.1-Tulu-3-8B](https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B) | [allenai/Llama-3.1-Tulu-3-70B](https://huggingface.co/allenai/Llama-3.1-Tulu-3-70B) | | **Reward Model (RM)**| [allenai/Llama-3.1-Tulu-3-8B-RM](https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B-RM) | (Same as 8B) | ## Using the model ### Loading with HuggingFace To load the model with HuggingFace, use the following snippet: ``` from transformers import AutoModelForCausalLM tulu_model = AutoModelForCausalLM.from_pretrained("allenai/Llama-3.1-Tulu-3-8B") ``` ### VLLM As a Llama base model, the model can be easily served with: ``` vllm serve allenai/Llama-3.1-Tulu-3-8B ``` Note that given the long chat template of Llama, you may want to use `--max_model_len=8192`. ### Chat template The chat template for our models is formatted as: ``` <|user|>\nHow are you doing?\n<|assistant|>\nI'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|> ``` Or with new lines expanded: ``` <|user|> How are you doing? <|assistant|> I'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|> ``` It is embedded within the tokenizer as well, for `tokenizer.apply_chat_template`. ### System prompt In Ai2 demos, we use this system prompt by default: ``` You are Tulu 3, a helpful and harmless AI Assistant built by the Allen Institute for AI. ``` The model has not been trained with a specific system prompt in mind. ### Bias, Risks, and Limitations 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. ## Performance | Benchmark (eval) | Tülu 3 SFT 8B | Tülu 3 DPO 8B | Tülu 3 8B | Llama 3.1 8B Instruct | Qwen 2.5 7B Instruct | Magpie 8B | Gemma 2 9B Instruct | Ministral 8B Instruct | |---------------------------------|----------------|----------------|------------|------------------------|----------------------|-----------|---------------------|-----------------------| | **Avg.** | 60.4 | 64.4 | **64.8** | 62.2 | 57.8 | 44.7 | 55.2 | 58.3 | | **MMLU (0 shot, CoT)** | 65.9 | 68.7 | 68.2 | 71.2 | **76.6** | 62.0 | 74.6 | 68.5 | | **PopQA (15 shot)** | **29.3** | 29.3 | 29.1 | 20.2 | 18.1 | 22.5 | 28.3 | 20.2 | | **TruthfulQA (6 shot)** | 46.8 | 56.1 | 55.0 | 55.1 | **63.1** | 57.0 | 61.4 | 55.5 | | **BigBenchHard (3 shot, CoT)** | **67.9** | 65.8 | 66.0 | 62.8 | 21.7 | 0.9 | 2.5 | 56.2 | | **DROP (3 shot)** | 61.3 | 62.5 | **62.6** | 61.5 | 54.4 | 49.4 | 58.8 | 56.2 | | **MATH (4 shot CoT, Flex)** | 31.5 | 42.0 | **43.7** | 42.5 | 14.8 | 5.1 | 29.8 | 40.0 | | **GSM8K (8 shot, CoT)** | 76.2 | 84.3 | **87.6** | 83.4 | 83.8 | 61.2 | 79.7 | 80.0 | | **HumanEval (pass@10)** | 86.2 | 83.9 | 83.9 | 86.3 | **93.1** | 75.4 | 71.7 | 91.0 | | **HumanEval+ (pass@10)** | 81.4 | 78.6 | 79.2 | 82.9 | **89.7** | 69.1 | 67.0 | 88.5 | | **IFEval (prompt loose)** | 72.8 | 81.1 | **82.4** | 80.6 | 74.7 | 38.8 | 69.9 | 56.4 | | **AlpacaEval 2 (LC % win)** | 12.4 | 33.5 | 34.5 | 24.2 | 29.0 | **49.0** | 43.7 | 31.4 | | **Safety (6 task avg.)** | **93.1** | 87.2 | 85.5 | 75.2 | 75.0 | 46.4 | 75.5 | 56.2 | | Benchmark (eval) | Tülu 3 70B SFT | Tülu 3 DPO 70B | Tülu 3 70B | Llama 3.1 70B Instruct | Qwen 2.5 72B Instruct | Hermes 3 Llama 3.1 70B | Nemotron Llama 3.1 70B | |---------------------------------|-----------------|-----------------|-------------|-------------------------|-----------------------|------------------------|-------------------------| | **Avg.** | 72.6 | 75.9 | **76.0** | 73.4 | 71.5 | 68.3 | 65.5 | | **MMLU (0 shot, CoT)** | 78.9 | 83.3 | 83.1 | 85.3 | **85.5** | 80.4 | 83.8 | | **PopQA (15 shot)** | **48.6** | 46.3 | 46.5 | 46.4 | 30.6 | 48.1 | 36.4 | | **TruthfulQA (6 shot)** | 55.7 | 67.9 | 67.6 | 66.8 | **69.9** | 66.5 | 62.6 | | **BigBenchHard (3 shot, CoT)** | **82.7** | 81.8 | 82.0 | 73.8 | 67.2 | 82.1 | 0.7 | | **DROP (3 shot)** | **77.2** | 74.1 | 74.3 | 77.0 | 34.2 | 73.2 | 68.8 | | **MATH (4 shot CoT, Flex)** | 53.7 | 62.3 | 63.0 | 56.4 | **74.3** | 41.9 | 55.0 | | **GSM8K (8 shot, CoT)** | 91.1 | 93.5 | 93.5 | **93.7** | 89.5 | 90.0 | 84.7 | | **HumanEval (pass@10)** | 92.9 | 92.4 | 92.4 | 93.6 | 94.0 | 89.6 | **94.1** | | **HumanEval+ (pass@10)** | 87.3 | 88.4 | 88.0 | 89.5 | **90.8** | 85.9 | 85.5 | | **IFEval (prompt loose)** | 82.1 | 82.6 | 83.2 | **88.0** | 87.6 | 76.0 | 79.9 | | **AlpacaEval 2 (LC % win)** | 26.3 | 49.6 | 49.8 | 33.4 | 47.7 | 28.4 | **66.1** | | **Safety (6 task avg.)** | **94.4** | 89.0 | 88.3 | 76.5 | 87.0 | 57.9 | 69.0 | ## Hyperparamters PPO settings for RLVR: - **Learning Rate**: 3 × 10⁻⁷ - **Discount Factor (gamma)**: 1.0 - **General Advantage Estimation (lambda)**: 0.95 - **Mini-batches (N_mb)**: 1 - **PPO Update Iterations (K)**: 4 - **PPO's Clipping Coefficient (epsilon)**: 0.2 - **Value Function Coefficient (c1)**: 0.1 - **Gradient Norm Threshold**: 1.0 - **Learning Rate Schedule**: Linear - **Generation Temperature**: 1.0 - **Batch Size (effective)**: 512 - **Max Token Length**: 2,048 - **Max Prompt Token Length**: 2,048 - **Penalty Reward Value for Responses without an EOS Token**: -10.0 - **Response Length**: 1,024 (but 2,048 for MATH) - **Total Episodes**: 100,000 - **KL penalty coefficient (beta)**: [0.1, 0.05, 0.03, 0.01] - **Warm up ratio (omega)**: 0.0 ## License and use All Llama 3.1 Tülu3 models are released under Meta's [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/). Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. Tülu3 is intended for research and educational use. For more information, please see our [Responsible Use Guidelines](https://allenai.org/responsible-use). The models have been fine-tuned using a dataset mix with outputs generated from third party models and are subject to additional terms: [Gemma Terms of Use](https://ai.google.dev/gemma/terms) and [Qwen License Agreement](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE) (models were improved using Qwen 2.5). ## Citation If Tülu3 or any of the related materials were helpful to your work, please cite: ``` @article{lambert2024tulu3, title = {Tülu 3: Pushing Frontiers in Open Language Model Post-Training}, author = { Nathan Lambert and Jacob Morrison and Valentina Pyatkin and Shengyi Huang and Hamish Ivison and Faeze Brahman and Lester James V. Miranda and Alisa Liu and Nouha Dziri and Shane Lyu and Yuling Gu and Saumya Malik and Victoria Graf and Jena D. Hwang and Jiangjiang Yang and Ronan Le Bras and Oyvind Tafjord and Chris Wilhelm and Luca Soldaini and Noah A. Smith and Yizhong Wang and Pradeep Dasigi and Hannaneh Hajishirzi }, year = {2024}, email = {tulu@allenai.org} } ```