[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QNBCMHFTKE0ETGJB48J31C":3,"skill-same:01M6QNBCMHFTKE0ETGJB48J31C":100},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":14,"repositoryHtmlUrl":62,"repositoryHomepageUrl":63,"ownerHtmlUrl":64,"ownerBlogUrl":65,"ownerDescription":66,"updatedAt":67,"install":68,"resources":81},"01M6QNBCMHFTKE0ETGJB48J31C","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.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fqc-openrlhf\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"training","openrlhf training","OpenRLHF","PPO","for","orchestra","high-performance","ai-research","use","Transformers","Ray","RLOO","performance","RLHF","Post-Training","ZeRO","Distributed Training","DeepSpeed","framework","architecture","2026-11-10 10:12:30",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]\ncategory: \"ai-research\"\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":44,"author":50,"license":15,"version":51,"category":26,"description":7,"dependencies":52},[33,21,32,22,45,30,46,29,47,35,48,49],"GRPO","DPO","vLLM","Large Models","ZeRO-3","Orchestra Research","1.0.0",[53,54,55,56,57,58],"openrlhf","ray","vllm","torch","transformers","deepspeed","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fqc-openrlhf","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":80},[70,73,76],{"tool":71,"command":72},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill openrlhf-training",{"tool":74,"command":75},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill openrlhf-training",{"tool":77,"command":78},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill openrlhf-training","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fqc-openrlhf\u002FSKILL.md",true,[82,88,92,96],{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Falgorithm-comparison.md","REFERENCE","参考文档",9783,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fqc-openrlhf\u002Freferences\u002Falgorithm-comparison.md",{"path":89,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fcustom-rewards.md",15865,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fqc-openrlhf\u002Freferences\u002Fcustom-rewards.md",{"path":93,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fhybrid-engine.md",7266,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fqc-openrlhf\u002Freferences\u002Fhybrid-engine.md",{"path":97,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fmulti-node-training.md",11099,"https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fqc-openrlhf\u002Freferences\u002Fmulti-node-training.md",[101,132,156,183,208,232],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":112,"publishedAt":39},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[107],{"categoryNo":108,"categoryName":109,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,23,129,130,131],"youtube full","youtube","full","transcript","search","monitoring","data","Video","Audio","list","files","do","get","age","trigger","URL","browsing","request","youtube transcripts",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":39},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[139,140,141,142,117,143,144,145,146,147,148,149,150,151,27,152,153,154,155,23],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","platform","grow","posting","competitive",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":165,"publishedAt":39},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[162],{"categoryNo":163,"categoryName":164,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000023","Skill与智能体开发",[166,150,167,168,169,170,171,172,27,173,174,59,175,176,177,178,179,180,181,182],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":189,"publishedAt":39},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[190,191,192,193,194,195,196,197,198,27,199,124,200,201,202,203,204,205,206,207],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":209,"name":210,"nameZh":6,"description":211,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":215,"publishedAt":39},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[214],{"categoryNo":163,"categoryName":164,"taxonomyType":110,"taxonomyTypeDesc":111},[216,217,218,219,220,168,195,221,222,223,224,225,150,226,123,227,228,229,230,231],"workflow","workflow builder","builder","design","workflows","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":233,"name":234,"nameZh":6,"description":235,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":236,"categories":237,"keywords":238,"publishedAt":39},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[239,240,241,242,243,244,245,246,247,224,248,249,250,251,252,253,125,254,255,207],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]