Find similar content

Source channel @githubtrending · Post #15539 · Mar 5

#python#agent#llm#llm_agent#llm_reasoning#machine_learning_systems#mlsys#reinforcement_learning#rl AReaL is a free, open-source system for fast asynchronous reinforcement learning to train large AI models in math, coding, search, and agents. It decouples generation and training for up to 2.77x speedup, stable performance, and easy setup on single or 1000+ GPUs with algorithms like GRPO/PPO. Install via git/pip, run examples like GSM8K math instantly. You benefit by building top AI agents affordably and quickly, reproducing results with shared data/models, saving time/money vs. slow synchronous tools. https://github.com/inclusionAI/AReaL

Hashtags

#python #agent #llm #llm_agent #llm_reasoning #machine_learning_systems #mlsys #reinforcement_learning #rl

Results

42 similar posts found

Search: #rhilip

当前筛选 #rhilip清除筛选

PTPP Actions

@PTPPAction · Post #2399 · 10/19/2024, 12:10 PM

Find similar View

#Rhilip#open 抢先体验版本不保证稳定性 feat: add lemonhd commit Merge branch 'dev' into dev * feat: add lemonhd 描述屏幕截图 2024-10-19 193700 屏幕截图 2024-10-19 193218

Hashtags

#rhilip #open

PTPP Actions

@PTPPAction · Post #1982 · 05/10/2024, 02:05 PM

Find similar View

#Rhilip:dev_full_vite #Rhilip#open 抢先体验版本不保证稳定性 build: full use vite to build pkg deps: use vite plugin to provide node polyfills 移除webpack构建部分，全部转为vite构建。普通用户请勿在生产环境中使用本pr的相关action构建。

Hashtags

#rhilip #open

PTPP Actions

@PTPPAction · Post #1970 · 05/08/2024, 03:50 PM

Find similar View

#Rhilip:dev_full_vite #Rhilip#open build: full use vite to build pkg

Hashtags

#rhilip #open

PTPP Actions

@PTPPAction · Post #1967 · 05/08/2024, 03:45 PM

Find similar View

#Rhilip:dev_full_vite #Rhilip#open build: full use vite to build pkg