R_REDDYX.XYZ
AIPython204

whitecircle/halo

HALO: FRAMEWORK FOR LLM TRAINING

Halo is an open-source framework from White Circle for training large language and multimodal models. It supports agent-based training, async-RL, distributed training, and fine-tuning via GRPO. Written in Python, it has garnered 204 stars on GitHub.

// KEY FEATURES

  • Trains LLM and multimodal models using the GRPO algorithm.
  • Supports agent-based training with environment and policy integration.
  • Enables async-RL parallel agent training in a distributed cluster.
  • Allows fine-tuning large models on multiple GPUs with automatic sharding.
#agent#async-rl#distributed-training#fine-tuning#grpo#large-language-models#llm#lora#model-parallelism#moe#multimodal#peft
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

Claw Code: Fast Code192068n8n Process Automation187437DeepSeek Plugin Framework186631Agent AI Optimization186627AutoGPT: AI Agent184170Everything for Claude Code179304

← FULL CATALOG

whitecircle/halo — HALO: FRAMEWORK FOR LLM TRAINING |…