🔥 Excited to share the other key Technology of WizardLM-2! 📙AutoEvol: Automatic Instruction Evolving for Large Language Models 🚀We build a fully automated Evol-Instruct pipeline to create high-quality, highly complex instruction tuning data: -------- 🧵 -------- 👉Motivation First: Over the past six months, we have dedicated ourselves to exploring methods to scale up synthetic training for LLMs. Although Evol-Instruct has demonstrated excellent performance in creating powerful post-training data, it relies too heavily on the efforts of human experts to design specific evolutionary methods for specific tasks. Once Evol-Instruct is applied to an entirely new complex task, the methods for executing evolution need to be redesigned. This limitation of Evol-Instruct makes scaling up extremely challenging, prompting us to develop a new method, 💻Auto Evol-Insturct💻, that can evolve instruction data automatically. Auto Evol allows the training of WizardLM2 to be conducted with nearly an unlimited number and variety of synthetic data. Let's see: 🧐 1. Limitations of Evol-Instruct: Evol-Instruct takes the high-quality data as a starting point, and further iteratively refines it using LLMs, improving its complexity and diversity. It has demonstrated superior performance across a broad range of public benchmarks that evaluate diverse capabilities, including instruction following (WizardLM), code generation (WizardCoder), and mathematical reasoning (WizardMath). While Evol-Instruct exhibits outstanding performance, its heavy reliance on heuristic efforts presents notable challenges. Whenever it is used for a completely new task, the methods for execution evolution need to be redesigned. Such a process requires a high level of expertise and considerable costs, hindering its adaptation to a wider spectrum of capabilities. 2. We want to build a fully automated Evol-Instruct pipeline Auto Evol-Instruct automatically designs evolving methods that make given instruction data more complex, enabling almost cost-free adaptation to different tasks by only changing the input data of the framework. From below figure, we can see the iterative process of optimizing the initial evolving method e0 into the optimal evolving method e∗, which specifically outlines the transition from et−1 to et. We refer to the model used for evolution as the evol LLM, and the model used for optimization as the optimizer LLM. This optimization process involves two critical stages: (1) Evol Trajectory Analysis: The optimizer LLM carefully analyzes the potential issues and failures exposed in instruction evolution performed by evol LLM, generating feedback for subsequent optimization. (2) Evolving Method Optimization: The optimizer LLM optimizes the evolving method by addressing these identified issues in feedback. These stages alternate and repeat to progressively develop an effective evolving method using only a subset of the instruction data. Once the optimal evolving method is identified, it directs the evol LLM to convert the entire instruction dataset into more diverse and complex forms, thus facilitating improved instruction tuning. 3. Fully AI-driven Evol-Instruct can outperform the Evol-Instruct used by human experts. Our experiments show that the evolving methods designed by Auto Evol-Instruct outperform the Evol-Instruct methods designed by human experts in instruction tuning across various capabilities, including instruction following, mathematical reasoning, and code generation. As shown in the below table, on the instruction following task, Auto Evol-Instruct can achieve a improvement of 10.44% over the Evol method used by WizardLM-1 on MT-bench; on the code task HumanEval, it can achieve a 12% improvement over the method used by WizardCoder; on the math task GSM8k, it can achieve a 6.9% improvement over the method used by WizardMath. 4. Scaling Evol-Instruct to various domains and tasks With the new technology of Auto Evol-Instruct, the evolutionary synthesis data of WizardLM-2 has scaled up from the three domains of chat, code, and math in WizardLM-1 to dozens of domains, covering tasks in all aspects of large language models. This allows Arena Learning to train and learn from an almost infinite pool of high-difficulty instruction data, fully unlocking all the potential of Arena Learning. For more details, please refer to: Paper: arxiv.org/pdf/2406.00770 Project: github.com/nlpxucan/WizardLM We are working with our legal team to publicly release the code of Auto Evol-Instruct.

🚀 Introducing EpiCoder: a hierarchical feature tree-based framework for diverse and intricate code generation. 🔍 Outperforming benchmarks, it handles everything from simple functions to multi-file projects deftly. 📢 Open source release soon! 🔗 arxiv.org/abs/2501.04694

🎉Excited to see the core techniques of WizardLM2 has been accepted to #EMNLP2024 and #NeurIPS2024! 👉Automatic Instruction Evolving for Large Language Models (arxiv.org/abs/2406.00770) 👉Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena (arxiv.org/abs/2407.10627) Congrats to all outstanding co-authors. We will not stop our journey towards AGI.

🎉Excited to see our WizardArena paper accepted to #NeurIPS2024! 👉Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena (arxiv.org/abs/2407.10627) Congrats to all outstanding co-authors. We will not stop our journey towards AGI.

We are announcing Llama-3.1-SuperNova, a Llama-3.1-70B-Instruct model offline distilled from Llama-3.1-405B-Instruct. It's ridiculously strong, particularly in instruction following and math. It's available to play with at supernova.arcee.ai. Read more about the model and how we plan to deploy it here: blog.arcee.ai/

Introducing 𝐇𝐞𝐫𝐦𝐞𝐬 𝟑: The latest version in our Hermes series, a generalist language model 𝐚𝐥𝐢𝐠𝐧𝐞𝐝 𝐭𝐨 𝐲𝐨𝐮. nousresearch.com/hermes3/ Hermes 3 is available in 3 sizes, 8, 70, and 405B parameters. Hermes has improvements across the board, but with particular capability improvements in roleplaying, agentic tasks, more reliable function calling, multi-turn chats, long context coherence and more. We published a technical report detailing new capabilities, training run information and more: Paper: nousresearch.com/wp-content/… This model was trained in collaboration with our great partners @LambdaAPI, and they are now offering it for free in a chat interface here: lambda.chat/chatui/ You can also chat with Hermes 405B on our discord, join here: discord.gg/NousResearch Hermes 3 was a project built with the help of @teknium, @TheEmozilla, @nullvaluetensor, @karan4d, @huemin_art, and an uncountable number of people and work in the Open Source community.

🎉Today we are announcing Evol-Instruct V2 !!! 🔥 Auto Evol-Instruct is one of the most important technologies for WizardLM-2. Paper link: arxiv.org/pdf/2406.00770 We build a fully automated Evol-Instruct pipeline, allowing WizardLM-2 to be extended from three evolved domains (chat, code and math) of WizardLM-1 to dozens of evolved domains 🚀With Auto Evol-Instruct, You can create high-quality, highly complex instruction tuning data for any task without the need for human efforts! ⚖️We hope that this universal technology can promote fairness and efficiency for all the AI researchers in training and evaluation their own large language models. 👉For more details, please refer to Can Xu's channel:

🔥 Excited to share the other key Technology of WizardLM-2! 📙AutoEvol: Automatic Instruction Evolving for Large Language Models 🚀We build a fully automated Evol-Instruct pipeline to create high-quality, highly complex instruction tuning data: -------- 🧵 -------- 👉Motivation First: Over the past six months, we have dedicated ourselves to exploring methods to scale up synthetic training for LLMs. Although Evol-Instruct has demonstrated excellent performance in creating powerful post-training data, it relies too heavily on the efforts of human experts to design specific evolutionary methods for specific tasks. Once Evol-Instruct is applied to an entirely new complex task, the methods for executing evolution need to be redesigned. This limitation of Evol-Instruct makes scaling up extremely challenging, prompting us to develop a new method, 💻Auto Evol-Insturct💻, that can evolve instruction data automatically. Auto Evol allows the training of WizardLM2 to be conducted with nearly an unlimited number and variety of synthetic data. Let's see: 🧐 1. Limitations of Evol-Instruct: Evol-Instruct takes the high-quality data as a starting point, and further iteratively refines it using LLMs, improving its complexity and diversity. It has demonstrated superior performance across a broad range of public benchmarks that evaluate diverse capabilities, including instruction following (WizardLM), code generation (WizardCoder), and mathematical reasoning (WizardMath). While Evol-Instruct exhibits outstanding performance, its heavy reliance on heuristic efforts presents notable challenges. Whenever it is used for a completely new task, the methods for execution evolution need to be redesigned. Such a process requires a high level of expertise and considerable costs, hindering its adaptation to a wider spectrum of capabilities. 2. We want to build a fully automated Evol-Instruct pipeline Auto Evol-Instruct automatically designs evolving methods that make given instruction data more complex, enabling almost cost-free adaptation to different tasks by only changing the input data of the framework. From below figure, we can see the iterative process of optimizing the initial evolving method e0 into the optimal evolving method e∗, which specifically outlines the transition from et−1 to et. We refer to the model used for evolution as the evol LLM, and the model used for optimization as the optimizer LLM. This optimization process involves two critical stages: (1) Evol Trajectory Analysis: The optimizer LLM carefully analyzes the potential issues and failures exposed in instruction evolution performed by evol LLM, generating feedback for subsequent optimization. (2) Evolving Method Optimization: The optimizer LLM optimizes the evolving method by addressing these identified issues in feedback. These stages alternate and repeat to progressively develop an effective evolving method using only a subset of the instruction data. Once the optimal evolving method is identified, it directs the evol LLM to convert the entire instruction dataset into more diverse and complex forms, thus facilitating improved instruction tuning. 3. Fully AI-driven Evol-Instruct can outperform the Evol-Instruct used by human experts. Our experiments show that the evolving methods designed by Auto Evol-Instruct outperform the Evol-Instruct methods designed by human experts in instruction tuning across various capabilities, including instruction following, mathematical reasoning, and code generation. As shown in the below table, on the instruction following task, Auto Evol-Instruct can achieve a improvement of 10.44% over the Evol method used by WizardLM-1 on MT-bench; on the code task HumanEval, it can achieve a 12% improvement over the method used by WizardCoder; on the math task GSM8k, it can achieve a 6.9% improvement over the method used by WizardMath. 4. Scaling Evol-Instruct to various domains and tasks With the new technology of Auto Evol-Instruct, the evolutionary synthesis data of WizardLM-2 has scaled up from the three domains of chat, code, and math in WizardLM-1 to dozens of domains, covering tasks in all aspects of large language models. This allows Arena Learning to train and learn from an almost infinite pool of high-difficulty instruction data, fully unlocking all the potential of Arena Learning. For more details, please refer to: Paper: arxiv.org/pdf/2406.00770 Project: github.com/nlpxucan/WizardLM We are working with our legal team to publicly release the code of Auto Evol-Instruct.

🎉Today we are announcing Evol-Instruct V2 !!! 🔥 Auto Evol-Instruct is one of the most important technologies for WizardLM-2. Paper link: arxiv.org/pdf/2406.00770 We build a fully automated Evol-Instruct pipeline, allowing WizardLM-2 to be extended from three evolved domains (chat, code and math) of WizardLM-1 to dozens of evolved domains 🚀With Auto Evol-Instruct, You can create high-quality, highly complex instruction tuning data for any task without the need for human efforts! ⚖️We hope that this universal technology can promote fairness and efficiency for all the AI researchers in training and evaluation their own large language models. 👉For more details, please refer to Can Xu's channel:

🔥 Excited to share the other key Technology of WizardLM-2! 📙AutoEvol: Automatic Instruction Evolving for Large Language Models 🚀We build a fully automated Evol-Instruct pipeline to create high-quality, highly complex instruction tuning data: -------- 🧵 -------- 👉Motivation First: Over the past six months, we have dedicated ourselves to exploring methods to scale up synthetic training for LLMs. Although Evol-Instruct has demonstrated excellent performance in creating powerful post-training data, it relies too heavily on the efforts of human experts to design specific evolutionary methods for specific tasks. Once Evol-Instruct is applied to an entirely new complex task, the methods for executing evolution need to be redesigned. This limitation of Evol-Instruct makes scaling up extremely challenging, prompting us to develop a new method, 💻Auto Evol-Insturct💻, that can evolve instruction data automatically. Auto Evol allows the training of WizardLM2 to be conducted with nearly an unlimited number and variety of synthetic data. Let's see: 🧐 1. Limitations of Evol-Instruct: Evol-Instruct takes the high-quality data as a starting point, and further iteratively refines it using LLMs, improving its complexity and diversity. It has demonstrated superior performance across a broad range of public benchmarks that evaluate diverse capabilities, including instruction following (WizardLM), code generation (WizardCoder), and mathematical reasoning (WizardMath). While Evol-Instruct exhibits outstanding performance, its heavy reliance on heuristic efforts presents notable challenges. Whenever it is used for a completely new task, the methods for execution evolution need to be redesigned. Such a process requires a high level of expertise and considerable costs, hindering its adaptation to a wider spectrum of capabilities. 2. We want to build a fully automated Evol-Instruct pipeline Auto Evol-Instruct automatically designs evolving methods that make given instruction data more complex, enabling almost cost-free adaptation to different tasks by only changing the input data of the framework. From below figure, we can see the iterative process of optimizing the initial evolving method e0 into the optimal evolving method e∗, which specifically outlines the transition from et−1 to et. We refer to the model used for evolution as the evol LLM, and the model used for optimization as the optimizer LLM. This optimization process involves two critical stages: (1) Evol Trajectory Analysis: The optimizer LLM carefully analyzes the potential issues and failures exposed in instruction evolution performed by evol LLM, generating feedback for subsequent optimization. (2) Evolving Method Optimization: The optimizer LLM optimizes the evolving method by addressing these identified issues in feedback. These stages alternate and repeat to progressively develop an effective evolving method using only a subset of the instruction data. Once the optimal evolving method is identified, it directs the evol LLM to convert the entire instruction dataset into more diverse and complex forms, thus facilitating improved instruction tuning. 3. Fully AI-driven Evol-Instruct can outperform the Evol-Instruct used by human experts. Our experiments show that the evolving methods designed by Auto Evol-Instruct outperform the Evol-Instruct methods designed by human experts in instruction tuning across various capabilities, including instruction following, mathematical reasoning, and code generation. As shown in the below table, on the instruction following task, Auto Evol-Instruct can achieve a improvement of 10.44% over the Evol method used by WizardLM-1 on MT-bench; on the code task HumanEval, it can achieve a 12% improvement over the method used by WizardCoder; on the math task GSM8k, it can achieve a 6.9% improvement over the method used by WizardMath. 4. Scaling Evol-Instruct to various domains and tasks With the new technology of Auto Evol-Instruct, the evolutionary synthesis data of WizardLM-2 has scaled up from the three domains of chat, code, and math in WizardLM-1 to dozens of domains, covering tasks in all aspects of large language models. This allows Arena Learning to train and learn from an almost infinite pool of high-difficulty instruction data, fully unlocking all the potential of Arena Learning. For more details, please refer to: Paper: arxiv.org/pdf/2406.00770 Project: github.com/nlpxucan/WizardLM We are working with our legal team to publicly release the code of Auto Evol-Instruct.

🎉Today we are announcing Evol-Instruct V2 !!! 🔥 Auto Evol-Instruct is one of the most important technologies for WizardLM-2. Paper link: arxiv.org/pdf/2406.00770 We build a fully automated Evol-Instruct pipeline, allowing WizardLM-2 to be extended from three evolved domains (chat, code and math) of WizardLM-1 to dozens of evolved domains 🚀With Auto Evol-Instruct, You can create high-quality, highly complex instruction tuning data for any task without the need for human efforts! ⚖️We hope that this universal technology can promote fairness and efficiency for all the AI researchers in training and evaluation their own large language models. 👉For more details, please refer to Can Xu's channel:

🔥 Excited to share the other key Technology of WizardLM-2! 📙AutoEvol: Automatic Instruction Evolving for Large Language Models 🚀We build a fully automated Evol-Instruct pipeline to create high-quality, highly complex instruction tuning data: -------- 🧵 -------- 👉Motivation First: Over the past six months, we have dedicated ourselves to exploring methods to scale up synthetic training for LLMs. Although Evol-Instruct has demonstrated excellent performance in creating powerful post-training data, it relies too heavily on the efforts of human experts to design specific evolutionary methods for specific tasks. Once Evol-Instruct is applied to an entirely new complex task, the methods for executing evolution need to be redesigned. This limitation of Evol-Instruct makes scaling up extremely challenging, prompting us to develop a new method, 💻Auto Evol-Insturct💻, that can evolve instruction data automatically. Auto Evol allows the training of WizardLM2 to be conducted with nearly an unlimited number and variety of synthetic data. Let's see: 🧐 1. Limitations of Evol-Instruct: Evol-Instruct takes the high-quality data as a starting point, and further iteratively refines it using LLMs, improving its complexity and diversity. It has demonstrated superior performance across a broad range of public benchmarks that evaluate diverse capabilities, including instruction following (WizardLM), code generation (WizardCoder), and mathematical reasoning (WizardMath). While Evol-Instruct exhibits outstanding performance, its heavy reliance on heuristic efforts presents notable challenges. Whenever it is used for a completely new task, the methods for execution evolution need to be redesigned. Such a process requires a high level of expertise and considerable costs, hindering its adaptation to a wider spectrum of capabilities. 2. We want to build a fully automated Evol-Instruct pipeline Auto Evol-Instruct automatically designs evolving methods that make given instruction data more complex, enabling almost cost-free adaptation to different tasks by only changing the input data of the framework. From below figure, we can see the iterative process of optimizing the initial evolving method e0 into the optimal evolving method e∗, which specifically outlines the transition from et−1 to et. We refer to the model used for evolution as the evol LLM, and the model used for optimization as the optimizer LLM. This optimization process involves two critical stages: (1) Evol Trajectory Analysis: The optimizer LLM carefully analyzes the potential issues and failures exposed in instruction evolution performed by evol LLM, generating feedback for subsequent optimization. (2) Evolving Method Optimization: The optimizer LLM optimizes the evolving method by addressing these identified issues in feedback. These stages alternate and repeat to progressively develop an effective evolving method using only a subset of the instruction data. Once the optimal evolving method is identified, it directs the evol LLM to convert the entire instruction dataset into more diverse and complex forms, thus facilitating improved instruction tuning. 3. Fully AI-driven Evol-Instruct can outperform the Evol-Instruct used by human experts. Our experiments show that the evolving methods designed by Auto Evol-Instruct outperform the Evol-Instruct methods designed by human experts in instruction tuning across various capabilities, including instruction following, mathematical reasoning, and code generation. As shown in the below table, on the instruction following task, Auto Evol-Instruct can achieve a improvement of 10.44% over the Evol method used by WizardLM-1 on MT-bench; on the code task HumanEval, it can achieve a 12% improvement over the method used by WizardCoder; on the math task GSM8k, it can achieve a 6.9% improvement over the method used by WizardMath. 4. Scaling Evol-Instruct to various domains and tasks With the new technology of Auto Evol-Instruct, the evolutionary synthesis data of WizardLM-2 has scaled up from the three domains of chat, code, and math in WizardLM-1 to dozens of domains, covering tasks in all aspects of large language models. This allows Arena Learning to train and learn from an almost infinite pool of high-difficulty instruction data, fully unlocking all the potential of Arena Learning. For more details, please refer to: Paper: arxiv.org/pdf/2406.00770 Project: github.com/nlpxucan/WizardLM We are working with our legal team to publicly release the code of Auto Evol-Instruct.

(1/3) Quite interesting work！Evol-Instruct has recently undergone a significant update and upgrade, introducing the brand-new automatic evolutionary framework, Auto Evol.