[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72CVTDCSK2J0BHKKYQCNN13":3,"skill-same:01M72CVTDCSK2J0BHKKYQCNN13":87},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":13,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M72CVTDCSK2J0BHKKYQCNN13","openrlhf-training",null,"High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.","Sansar35\u002Fclaude-agent","Sansar35","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F145020281?v=4","01M724CQ2SCC86MGNSD87D0D4K","01M724CQ3965G9WJ3QXE3AJ5YY",1,"MIT","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fopenrlhf-training\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: openrlhf-training\ndescription: High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.\nversion: 1.0.0\nauthor: Orchestra Research\nlicense: MIT\ntags: [Post-Training, OpenRLHF, RLHF, PPO, GRPO, RLOO, DPO, Ray, vLLM, Distributed Training, Large Models, ZeRO-3]\ndependencies: [openrlhf, ray, vllm, torch, transformers, deepspeed]\n---\n\n# OpenRLHF - High-Performance RLHF Training\n\n## Quick start\n\nOpenRLHF is a Ray-based RLHF framework optimized for distributed training with vLLM inference acceleration.\n\n**Installation**:\n```bash\n# Launch Docker container\ndocker run --runtime=nvidia -it --rm --shm-size=\"10g\" --cap-add=SYS_ADMIN \\\n  -v $PWD:\u002Fopenrlhf nvcr.io\u002Fnvidia\u002Fpytorch:25.02-py3 bash\n\n# Uninstall conflicts\nsudo pip uninstall xgboost transformer_engine flash_attn pynvml -y\n\n# Install OpenRLHF with vLLM\npip install openrlhf[vllm]\n```\n\n**PPO Training** (Hybrid Engine):\n```bash\nray start --head --node-ip-address 0.0.0.0 --num-gpus 8\n\nray job submit --address=\"http:\u002F\u002F127.0.0.1:8265\" \\\n  --runtime-env-json='{\"working_dir\": \"\u002Fopenrlhf\"}' \\\n  -- python3 -m openrlhf.cli.train_ppo_ray \\\n  --ref_num_nodes 1 --ref_num_gpus_per_node 8 \\\n  --reward_num_nodes 1 --reward_num_gpus_per_node 8 \\\n  --critic_num_nodes 1 --critic_num_gpus_per_node 8 \\\n  --actor_num_nodes 1 --actor_num_gpus_per_node 8 \\\n  --vllm_num_engines 4 --vllm_tensor_parallel_size 2 \\\n  --colocate_all_models \\\n  --vllm_gpu_memory_utilization 0.5 \\\n  --pretrain OpenRLHF\u002FLlama-3-8b-sft-mixture \\\n  --reward_pretrain OpenRLHF\u002FLlama-3-8b-rm-700k \\\n  --save_path .\u002Foutput\u002Fllama3-8b-rlhf \\\n  --micro_train_batch_size 8 --train_batch_size 128 \\\n  --micro_rollout_batch_size 16 --rollout_batch_size 1024 \\\n  --max_epochs 1 --prompt_max_len 1024 --generate_max_len 1024 \\\n  --zero_stage 3 --bf16 \\\n  --actor_learning_rate 5e-7 --critic_learning_rate 9e-6 \\\n  --init_kl_coef 0.01 --normalize_reward \\\n  --gradient_checkpointing --packing_samples \\\n  --vllm_enable_sleep --deepspeed_enable_sleep\n```\n\n**GRPO Training** (Group Normalized Policy Optimization):\n```bash\n# Same command as PPO, but add:\n--advantage_estimator group_norm\n```\n\n## Common workflows\n\n### Workflow 1: Full RLHF pipeline (SFT → Reward Model → PPO)\n\n**Step 1: Train reward model** (DPO):\n```bash\ndeepspeed --module openrlhf.cli.train_rm \\\n  --save_path .\u002Foutput\u002Fllama3-8b-rm \\\n  --save_steps -1 --logging_steps 1 \\\n  --eval_steps -1 --train_batch_size 256 \\\n  --micro_train_batch_size 1 --pretrain meta-llama\u002FMeta-Llama-3-8B \\\n  --bf16 --max_epochs 1 --max_len 8192 \\\n  --zero_stage 3 --learning_rate 9e-6 \\\n  --dataset OpenRLHF\u002Fpreference_dataset_mixture2_and_safe_pku \\\n  --apply_chat_template --chosen_key chosen \\\n  --rejected_key rejected --flash_attn --gradient_checkpointing\n```\n\n**Step 2: PPO training**:\n```bash\nray start --head --node-ip-address 0.0.0.0 --num-gpus 8\n\nray job submit --address=\"http:\u002F\u002F127.0.0.1:8265\" \\\n  -- python3 -m openrlhf.cli.train_ppo_ray \\\n  --ref_num_nodes 1 --ref_num_gpus_per_node 8 \\\n  --reward_num_nodes 1 --reward_num_gpus_per_node 8 \\\n  --critic_num_nodes 1 --critic_num_gpus_per_node 8 \\\n  --actor_num_nodes 1 --actor_num_gpus_per_node 8 \\\n  --vllm_num_engines 4 --vllm_tensor_parallel_size 2 \\\n  --colocate_all_models \\\n  --pretrain OpenRLHF\u002FLlama-3-8b-sft-mixture \\\n  --reward_pretrain .\u002Foutput\u002Fllama3-8b-rm \\\n  --save_path .\u002Foutput\u002Fllama3-8b-ppo \\\n  --micro_train_batch_size 8 --train_batch_size 128 \\\n  --micro_rollout_batch_size 16 --rollout_batch_size 1024 \\\n  --max_epochs 1 --prompt_max_len 1024 --generate_max_len 1024 \\\n  --zero_stage 3 --bf16 \\\n  --actor_learning_rate 5e-7 --critic_learning_rate 9e-6 \\\n  --init_kl_coef 0.01 --normalize_reward \\\n  --vllm_enable_sleep --deepspeed_enable_sleep\n```\n\n### Workflow 2: GRPO training (no critic model needed)\n\nMemory-efficient alternative to PPO:\n\n```bash\nray job submit --address=\"http:\u002F\u002F127.0.0.1:8265\" \\\n  -- python3 -m openrlhf.cli.train_ppo_ray \\\n  --advantage_estimator group_norm \\\n  --ref_num_nodes 1 --ref_num_gpus_per_node 8 \\\n  --reward_num_nodes 1 --reward_num_gpus_per_node 8 \\\n  --actor_num_nodes 1 --actor_num_gpus_per_node 8 \\\n  --vllm_num_engines 4 --vllm_tensor_parallel_size 2 \\\n  --colocate_all_models \\\n  --pretrain OpenRLHF\u002FLlama-3-8b-sft-mixture \\\n  --reward_pretrain OpenRLHF\u002FLlama-3-8b-rm-700k \\\n  --save_path .\u002Foutput\u002Fllama3-8b-grpo \\\n  --micro_train_batch_size 8 --train_batch_size 128 \\\n  --micro_rollout_batch_size 16 --rollout_batch_size 1024 \\\n  --max_epochs 1 --bf16 \\\n  --actor_learning_rate 5e-7 \\\n  --init_kl_coef 0.01 --use_kl_loss --kl_estimator k3 \\\n  --normalize_reward --no_advantage_std_norm\n```\n\n**Key GRPO parameters**:\n- `--advantage_estimator group_norm` - Enables GRPO\n- `--use_kl_loss` - KL loss from GRPO paper\n- `--kl_estimator k3` - Loss function (k2 ≈ k1)\n- `--no_advantage_std_norm` - Disables std normalization\n\n### Workflow 3: DPO training (preference optimization)\n\nSimpler alternative without reward model:\n\n```bash\ndeepspeed --module openrlhf.cli.train_dpo \\\n  --save_path .\u002Foutput\u002Fllama3-8b-dpo \\\n  --save_steps -1 --logging_steps 1 \\\n  --eval_steps -1 --train_batch_size 256 \\\n  --micro_train_batch_size 2 --pretrain meta-llama\u002FMeta-Llama-3-8B \\\n  --bf16 --max_epochs 1 --max_len 8192 \\\n  --zero_stage 3 --learning_rate 5e-7 --beta 0.1 \\\n  --dataset OpenRLHF\u002Fpreference_dataset_mixture2_and_safe_pku \\\n  --apply_chat_template --chosen_key chosen \\\n  --rejected_key rejected --flash_attn --gradient_checkpointing\n```\n\n## When to use vs alternatives\n\n**Use OpenRLHF when**:\n- Training large models (7B-70B+) with RL\n- Need vLLM inference acceleration\n- Want distributed architecture with Ray\n- Have multi-node GPU cluster\n- Need PPO\u002FGRPO\u002FRLOO\u002FDPO in one framework\n\n**Algorithm selection**:\n- **PPO**: Maximum control, best for complex rewards\n- **GRPO**: Memory-efficient, no critic needed\n- **RLOO**: Modified PPO with per-token KL\n- **REINFORCE++**: More stable than GRPO, faster than PPO\n- **DPO**: Simplest, no reward model needed\n\n**Use alternatives instead**:\n- **TRL**: Single-node training, simpler API\n- **veRL**: ByteDance's framework for 671B models\n- **DeepSpeedChat**: Integrated with DeepSpeed ecosystem\n\n## Common issues\n\n**Issue: GPU OOM with large models**\n\nDisable model colocation:\n```bash\n# Remove --colocate_all_models flag\n# Allocate separate GPUs for each model\n--actor_num_gpus_per_node 8 \\\n--critic_num_gpus_per_node 8 \\\n--reward_num_gpus_per_node 8 \\\n--ref_num_gpus_per_node 8\n```\n\n**Issue: DeepSpeed GPU index out of range**\n\nSet environment variable:\n```bash\nexport RAY_EXPERIMENTAL_NOSET_CUDA_VISIBLE_DEVICES=1\n```\n\n**Issue: Training instability**\n\nUse Hybrid Engine instead of async:\n```bash\n--colocate_all_models \\\n--vllm_enable_sleep \\\n--deepspeed_enable_sleep\n```\n\nAdjust KL coefficient:\n```bash\n--init_kl_coef 0.05  # Increase from 0.01\n```\n\n**Issue: Slow generation during PPO**\n\nEnable vLLM acceleration:\n```bash\n--vllm_num_engines 4 \\\n--vllm_tensor_parallel_size 2 \\\n--vllm_gpu_memory_utilization 0.5\n```\n\n## Advanced topics\n\n**Hybrid Engine GPU sharing**: See [references\u002Fhybrid-engine.md](references\u002Fhybrid-engine.md) for vLLM sleep mode, DeepSpeed sleep mode, and optimal node allocation.\n\n**Algorithm comparison**: See [references\u002Falgorithm-comparison.md](references\u002Falgorithm-comparison.md) for PPO vs GRPO vs RLOO vs REINFORCE++ benchmarks and hyperparameters.\n\n**Multi-node setup**: See [references\u002Fmulti-node-training.md](references\u002Fmulti-node-training.md) for Ray cluster configuration and fault tolerance.\n\n**Custom reward functions**: See [references\u002Fcustom-rewards.md](references\u002Fcustom-rewards.md) for reinforced fine-tuning and agent RLHF.\n\n## Hardware requirements\n\n- **GPU**: NVIDIA A100\u002FH100 recommended\n- **VRAM**:\n  - 7B model: 8× A100 40GB (Hybrid Engine)\n  - 70B model: 48× A100 80GB (vLLM:Actor:Critic = 1:1:1)\n- **Multi-node**: Ray cluster with InfiniBand recommended\n- **Docker**: NVIDIA PyTorch container 25.02+\n\n**Performance**:\n- 2× faster than DeepSpeedChat\n- vLLM inference acceleration\n- Hybrid Engine minimizes GPU idle time\n\n## Resources\n\n- Docs: https:\u002F\u002Fgithub.com\u002FOpenRLHF\u002FOpenRLHF\n- Paper: https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.11143\n- Examples: https:\u002F\u002Fgithub.com\u002FOpenRLHF\u002FOpenRLHF\u002Ftree\u002Fmain\u002Fexamples\n- Discord: Community support\n\n\n\n","# OpenRLHF - High-Performance RLHF Training\n\n## Quick start\n\nOpenRLHF is a Ray-based RLHF framework optimized for distributed training with vLLM inference acceleration.\n\n**Installation**:\n```bash\n# Launch Docker container\ndocker run --runtime=nvidia -it --rm --shm-size=\"10g\" --cap-add=SYS_ADMIN \\\n  -v $PWD:\u002Fopenrlhf nvcr.io\u002Fnvidia\u002Fpytorch:25.02-py3 bash\n\n# Uninstall conflicts\nsudo pip uninstall xgboost transformer_engine flash_attn pynvml -y\n\n# Install OpenRLHF with vLLM\npip install openrlhf[vllm]\n```\n\n**PPO Training** (Hybrid Engine):\n```bash\nray start --head --node-ip-address 0.0.0.0 --num-gpus 8\n\nray job submit --address=\"http:\u002F\u002F127.0.0.1:8265\" \\\n  --runtime-env-json='{\"working_dir\": \"\u002Fopenrlhf\"}' \\\n  -- python3 -m openrlhf.cli.train_ppo_ray \\\n  --ref_num_nodes 1 --ref_num_gpus_per_node 8 \\\n  --reward_num_nodes 1 --reward_num_gpus_per_node 8 \\\n  --critic_num_nodes 1 --critic_num_gpus_per_node 8 \\\n  --actor_num_nodes 1 --actor_num_gpus_per_node 8 \\\n  --vllm_num_engines 4 --vllm_tensor_parallel_size 2 \\\n  --colocate_all_models \\\n  --vllm_gpu_memory_utilization 0.5 \\\n  --pretrain OpenRLHF\u002FLlama-3-8b-sft-mixture \\\n  --reward_pretrain OpenRLHF\u002FLlama-3-8b-rm-700k \\\n  --save_path .\u002Foutput\u002Fllama3-8b-rlhf \\\n  --micro_train_batch_size 8 --train_batch_size 128 \\\n  --micro_rollout_batch_size 16 --rollout_batch_size 1024 \\\n  --max_epochs 1 --prompt_max_len 1024 --generate_max_len 1024 \\\n  --zero_stage 3 --bf16 \\\n  --actor_learning_rate 5e-7 --critic_learning_rate 9e-6 \\\n  --init_kl_coef 0.01 --normalize_reward \\\n  --gradient_checkpointing --packing_samples \\\n  --vllm_enable_sleep --deepspeed_enable_sleep\n```\n\n**GRPO Training** (Group Normalized Policy Optimization):\n```bash\n# Same command as PPO, but add:\n--advantage_estimator group_norm\n```\n\n## Common workflows\n\n### Workflow 1: Full RLHF pipeline (SFT → Reward Model → PPO)\n\n**Step 1: Train reward model** (DPO):\n```bash\ndeepspeed --module openrlhf.cli.train_rm \\\n  --save_path .\u002Foutput\u002Fllama3-8b-rm \\\n  --save_steps -1 --logging_steps 1 \\\n  --eval_steps -1 --train_batch_size 256 \\\n  --micro_train_batch_size 1 --pretrain meta-llama\u002FMeta-Llama-3-8B \\\n  --bf16 --max_epochs 1 --max_len 8192 \\\n  --zero_stage 3 --learning_rate 9e-6 \\\n  --dataset OpenRLHF\u002Fpreference_dataset_mixture2_and_safe_pku \\\n  --apply_chat_template --chosen_key chosen \\\n  --rejected_key rejected --flash_attn --gradient_checkpointing\n```\n\n**Step 2: PPO training**:\n```bash\nray start --head --node-ip-address 0.0.0.0 --num-gpus 8\n\nray job submit --address=\"http:\u002F\u002F127.0.0.1:8265\" \\\n  -- python3 -m openrlhf.cli.train_ppo_ray \\\n  --ref_num_nodes 1 --ref_num_gpus_per_node 8 \\\n  --reward_num_nodes 1 --reward_num_gpus_per_node 8 \\\n  --critic_num_nodes 1 --critic_num_gpus_per_node 8 \\\n  --actor_num_nodes 1 --actor_num_gpus_per_node 8 \\\n  --vllm_num_engines 4 --vllm_tensor_parallel_size 2 \\\n  --colocate_all_models \\\n  --pretrain OpenRLHF\u002FLlama-3-8b-sft-mixture \\\n  --reward_pretrain .\u002Foutput\u002Fllama3-8b-rm \\\n  --save_path .\u002Foutput\u002Fllama3-8b-ppo \\\n  --micro_train_batch_size 8 --train_batch_size 128 \\\n  --micro_rollout_batch_size 16 --rollout_batch_size 1024 \\\n  --max_epochs 1 --prompt_max_len 1024 --generate_max_len 1024 \\\n  --zero_stage 3 --bf16 \\\n  --actor_learning_rate 5e-7 --critic_learning_rate 9e-6 \\\n  --init_kl_coef 0.01 --normalize_reward \\\n  --vllm_enable_sleep --deepspeed_enable_sleep\n```\n\n### Workflow 2: GRPO training (no critic model needed)\n\nMemory-efficient alternative to PPO:\n\n```bash\nray job submit --address=\"http:\u002F\u002F127.0.0.1:8265\" \\\n  -- python3 -m openrlhf.cli.train_ppo_ray \\\n  --advantage_estimator group_norm \\\n  --ref_num_nodes 1 --ref_num_gpus_per_node 8 \\\n  --reward_num_nodes 1 --reward_num_gpus_per_node 8 \\\n  --actor_num_nodes 1 --actor_num_gpus_per_node 8 \\\n  --vllm_num_engines 4 --vllm_tensor_parallel_size 2 \\\n  --colocate_all_models \\\n  --pretrain OpenRLHF\u002FLlama-3-8b-sft-mixture \\\n  --reward_pretrain OpenRLHF\u002FLlama-3-8b-rm-700k \\\n  --save_path .\u002Foutput\u002Fllama3-8b-grpo \\\n  --micro_train_batch_size 8 --train_batch_size 128 \\\n  --micro_rollout_batch_size 16 --rollout_batch_size 1024 \\\n  --max_epochs 1 --bf16 \\\n  --actor_learning_rate 5e-7 \\\n  --init_kl_coef 0.01 --use_kl_loss --kl_estimator k3 \\\n  --normalize_reward --no_advantage_std_norm\n```\n\n**Key GRPO parameters**:\n- `--advantage_estimator group_norm` - Enables GRPO\n- `--use_kl_loss` - KL loss from GRPO paper\n- `--kl_estimator k3` - Loss function (k2 ≈ k1)\n- `--no_advantage_std_norm` - Disables std normalization\n\n### Workflow 3: DPO training (preference optimization)\n\nSimpler alternative without reward model:\n\n```bash\ndeepspeed --module openrlhf.cli.train_dpo \\\n  --save_path .\u002Foutput\u002Fllama3-8b-dpo \\\n  --save_steps -1 --logging_steps 1 \\\n  --eval_steps -1 --train_batch_size 256 \\\n  --micro_train_batch_size 2 --pretrain meta-llama\u002FMeta-Llama-3-8B \\\n  --bf16 --max_epochs 1 --max_len 8192 \\\n  --zero_stage 3 --learning_rate 5e-7 --beta 0.1 \\\n  --dataset OpenRLHF\u002Fpreference_dataset_mixture2_and_safe_pku \\\n  --apply_chat_template --chosen_key chosen \\\n  --rejected_key rejected --flash_attn --gradient_checkpointing\n```\n\n## When to use vs alternatives\n\n**Use OpenRLHF when**:\n- Training large models (7B-70B+) with RL\n- Need vLLM inference acceleration\n- Want distributed architecture with Ray\n- Have multi-node GPU cluster\n- Need PPO\u002FGRPO\u002FRLOO\u002FDPO in one framework\n\n**Algorithm selection**:\n- **PPO**: Maximum control, best for complex rewards\n- **GRPO**: Memory-efficient, no critic needed\n- **RLOO**: Modified PPO with per-token KL\n- **REINFORCE++**: More stable than GRPO, faster than PPO\n- **DPO**: Simplest, no reward model needed\n\n**Use alternatives instead**:\n- **TRL**: Single-node training, simpler API\n- **veRL**: ByteDance's framework for 671B models\n- **DeepSpeedChat**: Integrated with DeepSpeed ecosystem\n\n## Common issues\n\n**Issue: GPU OOM with large models**\n\nDisable model colocation:\n```bash\n# Remove --colocate_all_models flag\n# Allocate separate GPUs for each model\n--actor_num_gpus_per_node 8 \\\n--critic_num_gpus_per_node 8 \\\n--reward_num_gpus_per_node 8 \\\n--ref_num_gpus_per_node 8\n```\n\n**Issue: DeepSpeed GPU index out of range**\n\nSet environment variable:\n```bash\nexport RAY_EXPERIMENTAL_NOSET_CUDA_VISIBLE_DEVICES=1\n```\n\n**Issue: Training instability**\n\nUse Hybrid Engine instead of async:\n```bash\n--colocate_all_models \\\n--vllm_enable_sleep \\\n--deepspeed_enable_sleep\n```\n\nAdjust KL coefficient:\n```bash\n--init_kl_coef 0.05  # Increase from 0.01\n```\n\n**Issue: Slow generation during PPO**\n\nEnable vLLM acceleration:\n```bash\n--vllm_num_engines 4 \\\n--vllm_tensor_parallel_size 2 \\\n--vllm_gpu_memory_utilization 0.5\n```\n\n## Advanced topics\n\n**Hybrid Engine GPU sharing**: See [references\u002Fhybrid-engine.md](references\u002Fhybrid-engine.md) for vLLM sleep mode, DeepSpeed sleep mode, and optimal node allocation.\n\n**Algorithm comparison**: See [references\u002Falgorithm-comparison.md](references\u002Falgorithm-comparison.md) for PPO vs GRPO vs RLOO vs REINFORCE++ benchmarks and hyperparameters.\n\n**Multi-node setup**: See [references\u002Fmulti-node-training.md](references\u002Fmulti-node-training.md) for Ray cluster configuration and fault tolerance.\n\n**Custom reward functions**: See [references\u002Fcustom-rewards.md](references\u002Fcustom-rewards.md) for reinforced fine-tuning and agent RLHF.\n\n## Hardware requirements\n\n- **GPU**: NVIDIA A100\u002FH100 recommended\n- **VRAM**:\n  - 7B model: 8× A100 40GB (Hybrid Engine)\n  - 70B model: 48× A100 80GB (vLLM:Actor:Critic = 1:1:1)\n- **Multi-node**: Ray cluster with InfiniBand recommended\n- **Docker**: NVIDIA PyTorch container 25.02+\n\n**Performance**:\n- 2× faster than DeepSpeedChat\n- vLLM inference acceleration\n- Hybrid Engine minimizes GPU idle time\n\n## Resources\n\n- Docs: https:\u002F\u002Fgithub.com\u002FOpenRLHF\u002FOpenRLHF\n- Paper: https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.11143\n- Examples: https:\u002F\u002Fgithub.com\u002FOpenRLHF\u002FOpenRLHF\u002Ftree\u002Fmain\u002Fexamples\n- Discord: Community support\n\n\n\n",{"name":5,"tags":23,"author":36,"license":14,"version":37,"description":7,"dependencies":38},[24,25,26,27,28,29,30,31,32,33,34,35],"Post-Training","OpenRLHF","RLHF","PPO","GRPO","RLOO","DPO","Ray","vLLM","Distributed Training","Large Models","ZeRO-3","Orchestra Research","1.0.0",[39,40,41,42,43,44],"openrlhf","ray","vllm","torch","transformers","deepspeed","main","d046d088ce5a79a083f0abc0fe1b7ded73bc5b1f","claude-config\u002Fskills\u002Fopenrlhf-training","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent","https:\u002F\u002Fgithub.com\u002FSansar35","2026-05-10 16:04:53",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add Sansar35\u002Fclaude-agent --skill openrlhf-training",{"tool":57,"command":58},"bunx","bunx skills add Sansar35\u002Fclaude-agent --skill openrlhf-training",{"tool":60,"command":61},"pnpm","pnpm dlx skills add Sansar35\u002Fclaude-agent --skill openrlhf-training","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fopenrlhf-training\u002FSKILL.md",true,[65,71,75,79,83],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},".skill-source.json","REFERENCE","参考文档",481,"https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fopenrlhf-training\u002F.skill-source.json",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Falgorithm-comparison.md",9783,"https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fopenrlhf-training\u002Freferences\u002Falgorithm-comparison.md",{"path":76,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fcustom-rewards.md",15865,"https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fopenrlhf-training\u002Freferences\u002Fcustom-rewards.md",{"path":80,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fhybrid-engine.md",7266,"https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fopenrlhf-training\u002Freferences\u002Fhybrid-engine.md",{"path":84,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fmulti-node-training.md",11099,"https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fopenrlhf-training\u002Freferences\u002Fmulti-node-training.md",[88,95,102,109,116,124],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M72DVAN1JYEA302MT0C5MGD6","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M72DV8J5NBRRM4RPDFRV95N7","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":18},"01M72DV5EMHW0BHP9BZ167MDCB","zinc-database","Access ZINC (230M+ purchasable compounds). Search by ZINC ID\u002FSMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzinc-database\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":18},"01M72DV216QY0E693ZPEVQ0DBS","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":18},"01M72DTXQREMCRKA8NHCVKHN4W","zapier-workflows","Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to \"run\" any process. Also handles Perplexity-based research and Google Sheets data tracking.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":18},"01M72DTT17TBSJ0Y8J2XZ4C9TZ","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-make-patterns\u002FSKILL.md",[],[]]