WizardLM's picture

WizardLM

WizardLM

·

AI & ML interests

NLP, LLM

Recent Activity

liked a model 22 days ago

deepseek-ai/DeepSeek-V3

reacted to their post with 🚀 6 months ago

🔥 🔥🔥 Excited to announce WizardLM new Paper: Auto Evol-Instruct! 🐦 Twitter: https://x.com/WizardLM_AI/status/1812857977122202087 📃 Paper: https://arxiv.org/pdf/2406.00770 🤖 1. Fully AI-Powered Pipeline Auto Evol-Instruct automatically involves an iterative process of optimizing an Evol-Instruct V1 into an optimal one. The pipeline consists of two critical stages: Evol Trajectory Analysis, where the optimizer LLM analyzes the issues and failures exposed in instruction evolution performed by the evol LLM, and Evolving Method Optimization, where the optimizer LLM addresses these issues to progressively develop an effective evolving method. The optimal evolving method is then used to convert the entire instruction dataset into more diverse and complex forms, facilitating improved instruction tuning. 📈2. Scaling Evol-Instruct with Arena Learning With Auto Evol-Instruct, the evolutionary synthesis data of WizardLM-2 has scaled up from 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.

posted an update 6 months ago

🔥 🔥🔥 Excited to announce WizardLM new Paper: Auto Evol-Instruct! 🐦 Twitter: https://x.com/WizardLM_AI/status/1812857977122202087 📃 Paper: https://arxiv.org/pdf/2406.00770 🤖 1. Fully AI-Powered Pipeline Auto Evol-Instruct automatically involves an iterative process of optimizing an Evol-Instruct V1 into an optimal one. The pipeline consists of two critical stages: Evol Trajectory Analysis, where the optimizer LLM analyzes the issues and failures exposed in instruction evolution performed by the evol LLM, and Evolving Method Optimization, where the optimizer LLM addresses these issues to progressively develop an effective evolving method. The optimal evolving method is then used to convert the entire instruction dataset into more diverse and complex forms, facilitating improved instruction tuning. 📈2. Scaling Evol-Instruct with Arena Learning With Auto Evol-Instruct, the evolutionary synthesis data of WizardLM-2 has scaled up from 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.

View all activity

Organizations

WizardLM's activity

New activity in WizardLMTeam/WizardCoder-Python-34B-V1.0 12 months ago

Update README.md

#33 opened about 1 year ago by

New activity in WizardLMTeam/WizardCoder-15B-V1.0 12 months ago

Update README.md

#42 opened about 1 year ago by

New activity in WizardLMTeam/WizardCoder-Python-13B-V1.0 12 months ago

Update README.md

#8 opened about 1 year ago by

New activity in WizardLMTeam/WizardCoder-33B-V1.1 about 1 year ago

Update README.md

#6 opened about 1 year ago by

Update README.md

#7 opened about 1 year ago by

Update README.md

#2 opened about 1 year ago by

Update README.md

#1 opened about 1 year ago by

New activity in WizardLMTeam/WizardCoder-Python-34B-V1.0 over 1 year ago

Please consider my toiled over coding dataset for fine tuning a 1.1 version of the wizard coder series.

#22 opened over 1 year ago by

Context length is still 4096

#7 opened over 1 year ago by

Performance differences with gpt4

#4 opened over 1 year ago by

Phind new model just beat WizardCoder-Python-34B-V1.0 human eval high score

#13 opened over 1 year ago by

Any idea how much VRAM does this use ?

#12 opened over 1 year ago by

Details on the method used to surpass CodeLlama

#14 opened over 1 year ago by

Performance issues when compared to other codellama_34b finetunes

#11 opened over 1 year ago by

wrong bos_token

#15 opened over 1 year ago by

Build chat bot

#16 opened over 1 year ago by

M2 Mac 96gb

#17 opened over 1 year ago by

How to delete downloaded model from google colab?

#18 opened over 1 year ago by

how to install/use

#23 opened over 1 year ago by

Update config.json

#24 opened over 1 year ago by