[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74ZK5X5SVMJFKM26T5BK2JS":3,"skill-same:01M74ZK5X5SVMJFKM26T5BK2JS":68},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":37,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M74ZK5X5SVMJFKM26T5BK2JS","simpo-training",null,"Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO\u002FPPO.","KalarisLabs\u002Fresearch-agent-skills","KalarisLabs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F300878568?v=4","01M74Y7MT23GXXC56VM6TVSXZY","Kalarislabs","01M74Y7MTQM9REXZX4SNXWX95C",119,"MIT","https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsimpo-training\u002FSKILL.md",[],[],"2026-11-11 17:47:46",false,"---\nname: simpo-training\ndescription: Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO\u002FPPO.\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  category: ml-training\n  maintainer: Kalaris Labs\n  tags: Post-Training, SimPO, Preference Optimization, Alignment, DPO Alternative, Reference-Free, LLM Alignment, Efficient Training\n  dependencies: torch, transformers, datasets, trl, accelerate\n---\n\n# SimPO - Simple Preference Optimization\n\n## Quick start\n\nSimPO is a reference-free preference optimization method that outperforms DPO without needing a reference model.\n\n**Installation**:\n```bash\n# Create environment\nconda create -n simpo python=3.10 && conda activate simpo\n\n# Install PyTorch 2.2.2\n# Visit: https:\u002F\u002Fpytorch.org\u002Fget-started\u002Flocally\u002F\n\n# Install alignment-handbook\ngit clone https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Falignment-handbook.git\ncd alignment-handbook\npython -m pip install .\n\n# Install Flash Attention 2\npython -m pip install flash-attn --no-build-isolation\n```\n\n**Training** (Mistral 7B):\n```bash\nACCELERATE_LOG_LEVEL=info accelerate launch \\\n  --config_file accelerate_configs\u002Fdeepspeed_zero3.yaml \\\n  scripts\u002Frun_simpo.py \\\n  training_configs\u002Fmistral-7b-base-simpo.yaml\n```\n\n## Common workflows\n\n### Workflow 1: Train from base model (Mistral 7B)\n\n**Config** (`mistral-7b-base-simpo.yaml`):\n```yaml\n# Model\nmodel_name_or_path: mistralai\u002FMistral-7B-v0.1\ntorch_dtype: bfloat16\n\n# Dataset\ndataset_mixer:\n  HuggingFaceH4\u002Fultrafeedback_binarized: 1.0\ndataset_splits:\n  - train_prefs\n  - test_prefs\n\n# SimPO hyperparameters\nbeta: 2.0                  # Reward scaling (2.0-10.0)\ngamma_beta_ratio: 0.5       # Target margin (0-1)\nloss_type: sigmoid          # sigmoid or hinge\nsft_weight: 0.0             # Optional SFT regularization\n\n# Training\nlearning_rate: 5e-7         # Critical: 3e-7 to 1e-6\nnum_train_epochs: 1\nper_device_train_batch_size: 1\ngradient_accumulation_steps: 8\n\n# Output\noutput_dir: .\u002Foutputs\u002Fmistral-7b-simpo\n```\n\n**Launch training**:\n```bash\naccelerate launch --config_file accelerate_configs\u002Fdeepspeed_zero3.yaml \\\n  scripts\u002Frun_simpo.py training_configs\u002Fmistral-7b-base-simpo.yaml\n```\n\n### Workflow 2: Fine-tune instruct model (Llama 3 8B)\n\n**Config** (`llama3-8b-instruct-simpo.yaml`):\n```yaml\nmodel_name_or_path: meta-llama\u002FMeta-Llama-3-8B-Instruct\n\ndataset_mixer:\n  argilla\u002Fultrafeedback-binarized-preferences-cleaned: 1.0\n\nbeta: 2.5\ngamma_beta_ratio: 0.5\nlearning_rate: 5e-7\nsft_weight: 0.1             # Add SFT loss to preserve capabilities\n\nnum_train_epochs: 1\nper_device_train_batch_size: 2\ngradient_accumulation_steps: 4\noutput_dir: .\u002Foutputs\u002Fllama3-8b-simpo\n```\n\n**Launch**:\n```bash\naccelerate launch --config_file accelerate_configs\u002Fdeepspeed_zero3.yaml \\\n  scripts\u002Frun_simpo.py training_configs\u002Fllama3-8b-instruct-simpo.yaml\n```\n\n### Workflow 3: Reasoning-intensive tasks (lower LR)\n\n**For math\u002Fcode tasks**:\n```yaml\nmodel_name_or_path: deepseek-ai\u002Fdeepseek-math-7b-base\n\ndataset_mixer:\n  argilla\u002Fdistilabel-math-preference-dpo: 1.0\n\nbeta: 5.0                   # Higher for stronger signal\ngamma_beta_ratio: 0.7       # Larger margin\nlearning_rate: 3e-7         # Lower LR for reasoning\nsft_weight: 0.0\n\nnum_train_epochs: 1\nper_device_train_batch_size: 1\ngradient_accumulation_steps: 16\n```\n\n## When to use vs alternatives\n\n**Use SimPO when**:\n- Want simpler training than DPO (no reference model)\n- Have preference data (chosen\u002Frejected pairs)\n- Need better performance than DPO\n- Limited compute resources\n- Single-node training sufficient\n\n**Algorithm selection**:\n- **SimPO**: Simplest, best performance, no reference model\n- **DPO**: Need reference model baseline, more conservative\n- **PPO**: Maximum control, need reward model, complex setup\n- **GRPO**: Memory-efficient RL, no critic\n\n**Use alternatives instead**:\n- **OpenRLHF**: Multi-node distributed training, PPO\u002FGRPO\n- **TRL**: Need multiple methods in one framework\n- **DPO**: Established baseline comparison\n\n## Common issues\n\n**Issue: Loss divergence**\n\nReduce learning rate:\n```yaml\nlearning_rate: 3e-7  # Reduce from 5e-7\n```\n\nReduce beta:\n```yaml\nbeta: 1.0  # Reduce from 2.0\n```\n\n**Issue: Model forgets capabilities**\n\nAdd SFT regularization:\n```yaml\nsft_weight: 0.1  # Add SFT loss component\n```\n\n**Issue: Poor preference separation**\n\nIncrease beta and margin:\n```yaml\nbeta: 5.0            # Increase from 2.0\ngamma_beta_ratio: 0.8  # Increase from 0.5\n```\n\n**Issue: OOM during training**\n\nReduce batch size:\n```yaml\nper_device_train_batch_size: 1\ngradient_accumulation_steps: 16  # Maintain effective batch\n```\n\nEnable gradient checkpointing:\n```yaml\ngradient_checkpointing: true\n```\n\n## Advanced topics\n\n**Loss functions**: See [references\u002Floss-functions.md](references\u002Floss-functions.md) for sigmoid vs hinge loss, mathematical formulations, and when to use each.\n\n**Hyperparameter tuning**: See [references\u002Fhyperparameters.md](references\u002Fhyperparameters.md) for beta, gamma, learning rate selection guide, and model-size-specific recommendations.\n\n**Dataset preparation**: See [references\u002Fdatasets.md](references\u002Fdatasets.md) for preference data formats, quality filtering, and custom dataset creation.\n\n## Hardware requirements\n\n- **GPU**: NVIDIA A100\u002FH100 recommended\n- **VRAM**:\n  - 7B model: 1× A100 40GB (DeepSpeed ZeRO-3)\n  - 8B model: 2× A100 40GB\n  - 70B model: 8× A100 80GB\n- **Single-node**: DeepSpeed ZeRO-3 sufficient\n- **Mixed precision**: BF16 recommended\n\n**Memory optimization**:\n- DeepSpeed ZeRO-3 (default config)\n- Gradient checkpointing\n- Flash Attention 2\n\n## Resources\n\n- Paper: https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.14734 (NeurIPS 2024)\n- GitHub: https:\u002F\u002Fgithub.com\u002Fprinceton-nlp\u002FSimPO\n- Models: https:\u002F\u002Fhuggingface.co\u002Fprinceton-nlp\n- Alignment Handbook: https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Falignment-handbook\n\n## Agent operating procedure\n\n1. **Check the environment.** Check GPU type, memory and driver\u002FCUDA versions (`nvidia-smi`), framework versions, and dataset location and size.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Do a smoke run: tiny model or subset, few steps, and confirm loss decreases and checkpoints save.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Track metrics on held-out data, compare against a baseline, and record seeds, configs and hardware.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| CUDA out-of-memory | Reduce batch size, enable gradient accumulation\u002Fcheckpointing or mixed precision, or shard the model. |\n| Loss is NaN or diverges | Lower the learning rate, check data for invalid values, and enable gradient clipping. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Never claim training results without logs; estimate compute cost before launching large jobs.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `fine-tuning-with-trl`: Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO\u002FGRPO for reward optimi…\n- `openrlhf-training`: High-performance RLHF framework with Ray+vLLM acceleration.\n- `axolotl`: Provides guidance for fine-tuning large language models with Axolotl, covering YAML training configs, LoRA and QLoRA, preference training w…\n","# SimPO - Simple Preference Optimization\n\n## Quick start\n\nSimPO is a reference-free preference optimization method that outperforms DPO without needing a reference model.\n\n**Installation**:\n```bash\n# Create environment\nconda create -n simpo python=3.10 && conda activate simpo\n\n# Install PyTorch 2.2.2\n# Visit: https:\u002F\u002Fpytorch.org\u002Fget-started\u002Flocally\u002F\n\n# Install alignment-handbook\ngit clone https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Falignment-handbook.git\ncd alignment-handbook\npython -m pip install .\n\n# Install Flash Attention 2\npython -m pip install flash-attn --no-build-isolation\n```\n\n**Training** (Mistral 7B):\n```bash\nACCELERATE_LOG_LEVEL=info accelerate launch \\\n  --config_file accelerate_configs\u002Fdeepspeed_zero3.yaml \\\n  scripts\u002Frun_simpo.py \\\n  training_configs\u002Fmistral-7b-base-simpo.yaml\n```\n\n## Common workflows\n\n### Workflow 1: Train from base model (Mistral 7B)\n\n**Config** (`mistral-7b-base-simpo.yaml`):\n```yaml\n# Model\nmodel_name_or_path: mistralai\u002FMistral-7B-v0.1\ntorch_dtype: bfloat16\n\n# Dataset\ndataset_mixer:\n  HuggingFaceH4\u002Fultrafeedback_binarized: 1.0\ndataset_splits:\n  - train_prefs\n  - test_prefs\n\n# SimPO hyperparameters\nbeta: 2.0                  # Reward scaling (2.0-10.0)\ngamma_beta_ratio: 0.5       # Target margin (0-1)\nloss_type: sigmoid          # sigmoid or hinge\nsft_weight: 0.0             # Optional SFT regularization\n\n# Training\nlearning_rate: 5e-7         # Critical: 3e-7 to 1e-6\nnum_train_epochs: 1\nper_device_train_batch_size: 1\ngradient_accumulation_steps: 8\n\n# Output\noutput_dir: .\u002Foutputs\u002Fmistral-7b-simpo\n```\n\n**Launch training**:\n```bash\naccelerate launch --config_file accelerate_configs\u002Fdeepspeed_zero3.yaml \\\n  scripts\u002Frun_simpo.py training_configs\u002Fmistral-7b-base-simpo.yaml\n```\n\n### Workflow 2: Fine-tune instruct model (Llama 3 8B)\n\n**Config** (`llama3-8b-instruct-simpo.yaml`):\n```yaml\nmodel_name_or_path: meta-llama\u002FMeta-Llama-3-8B-Instruct\n\ndataset_mixer:\n  argilla\u002Fultrafeedback-binarized-preferences-cleaned: 1.0\n\nbeta: 2.5\ngamma_beta_ratio: 0.5\nlearning_rate: 5e-7\nsft_weight: 0.1             # Add SFT loss to preserve capabilities\n\nnum_train_epochs: 1\nper_device_train_batch_size: 2\ngradient_accumulation_steps: 4\noutput_dir: .\u002Foutputs\u002Fllama3-8b-simpo\n```\n\n**Launch**:\n```bash\naccelerate launch --config_file accelerate_configs\u002Fdeepspeed_zero3.yaml \\\n  scripts\u002Frun_simpo.py training_configs\u002Fllama3-8b-instruct-simpo.yaml\n```\n\n### Workflow 3: Reasoning-intensive tasks (lower LR)\n\n**For math\u002Fcode tasks**:\n```yaml\nmodel_name_or_path: deepseek-ai\u002Fdeepseek-math-7b-base\n\ndataset_mixer:\n  argilla\u002Fdistilabel-math-preference-dpo: 1.0\n\nbeta: 5.0                   # Higher for stronger signal\ngamma_beta_ratio: 0.7       # Larger margin\nlearning_rate: 3e-7         # Lower LR for reasoning\nsft_weight: 0.0\n\nnum_train_epochs: 1\nper_device_train_batch_size: 1\ngradient_accumulation_steps: 16\n```\n\n## When to use vs alternatives\n\n**Use SimPO when**:\n- Want simpler training than DPO (no reference model)\n- Have preference data (chosen\u002Frejected pairs)\n- Need better performance than DPO\n- Limited compute resources\n- Single-node training sufficient\n\n**Algorithm selection**:\n- **SimPO**: Simplest, best performance, no reference model\n- **DPO**: Need reference model baseline, more conservative\n- **PPO**: Maximum control, need reward model, complex setup\n- **GRPO**: Memory-efficient RL, no critic\n\n**Use alternatives instead**:\n- **OpenRLHF**: Multi-node distributed training, PPO\u002FGRPO\n- **TRL**: Need multiple methods in one framework\n- **DPO**: Established baseline comparison\n\n## Common issues\n\n**Issue: Loss divergence**\n\nReduce learning rate:\n```yaml\nlearning_rate: 3e-7  # Reduce from 5e-7\n```\n\nReduce beta:\n```yaml\nbeta: 1.0  # Reduce from 2.0\n```\n\n**Issue: Model forgets capabilities**\n\nAdd SFT regularization:\n```yaml\nsft_weight: 0.1  # Add SFT loss component\n```\n\n**Issue: Poor preference separation**\n\nIncrease beta and margin:\n```yaml\nbeta: 5.0            # Increase from 2.0\ngamma_beta_ratio: 0.8  # Increase from 0.5\n```\n\n**Issue: OOM during training**\n\nReduce batch size:\n```yaml\nper_device_train_batch_size: 1\ngradient_accumulation_steps: 16  # Maintain effective batch\n```\n\nEnable gradient checkpointing:\n```yaml\ngradient_checkpointing: true\n```\n\n## Advanced topics\n\n**Loss functions**: See [references\u002Floss-functions.md](references\u002Floss-functions.md) for sigmoid vs hinge loss, mathematical formulations, and when to use each.\n\n**Hyperparameter tuning**: See [references\u002Fhyperparameters.md](references\u002Fhyperparameters.md) for beta, gamma, learning rate selection guide, and model-size-specific recommendations.\n\n**Dataset preparation**: See [references\u002Fdatasets.md](references\u002Fdatasets.md) for preference data formats, quality filtering, and custom dataset creation.\n\n## Hardware requirements\n\n- **GPU**: NVIDIA A100\u002FH100 recommended\n- **VRAM**:\n  - 7B model: 1× A100 40GB (DeepSpeed ZeRO-3)\n  - 8B model: 2× A100 40GB\n  - 70B model: 8× A100 80GB\n- **Single-node**: DeepSpeed ZeRO-3 sufficient\n- **Mixed precision**: BF16 recommended\n\n**Memory optimization**:\n- DeepSpeed ZeRO-3 (default config)\n- Gradient checkpointing\n- Flash Attention 2\n\n## Resources\n\n- Paper: https:\u002F\u002Farxiv.org\u002Fabs\u002F2405.14734 (NeurIPS 2024)\n- GitHub: https:\u002F\u002Fgithub.com\u002Fprinceton-nlp\u002FSimPO\n- Models: https:\u002F\u002Fhuggingface.co\u002Fprinceton-nlp\n- Alignment Handbook: https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Falignment-handbook\n\n## Agent operating procedure\n\n1. **Check the environment.** Check GPU type, memory and driver\u002FCUDA versions (`nvidia-smi`), framework versions, and dataset location and size.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Do a smoke run: tiny model or subset, few steps, and confirm loss decreases and checkpoints save.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Track metrics on held-out data, compare against a baseline, and record seeds, configs and hardware.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| CUDA out-of-memory | Reduce batch size, enable gradient accumulation\u002Fcheckpointing or mixed precision, or shard the model. |\n| Loss is NaN or diverges | Lower the learning rate, check data for invalid values, and enable gradient clipping. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Never claim training results without logs; estimate compute cost before launching large jobs.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `fine-tuning-with-trl`: Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO\u002FGRPO for reward optimi…\n- `openrlhf-training`: High-performance RLHF framework with Ray+vLLM acceleration.\n- `axolotl`: Provides guidance for fine-tuning large language models with Axolotl, covering YAML training configs, LoRA and QLoRA, preference training w…\n",{"name":5,"license":15,"metadata":24,"description":7},{"tags":25,"version":26,"category":27,"maintainer":28,"dependencies":29},"Post-Training, SimPO, Preference Optimization, Alignment, DPO Alternative, Reference-Free, LLM Alignment, Efficient Training","1.0.0","ml-training","Kalaris Labs","torch, transformers, datasets, trl, accelerate","main","29fe36d26127205057d5e0ed8425f6b0e9a8c13a","skills\u002Fsimpo-training",12,"https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills","https:\u002F\u002Fdocs.kalarislabs.com\u002Fresearch-agent-skills","https:\u002F\u002Fgithub.com\u002FKalarisLabs","kalarislabs.com","Applied AI lab building the infrastructure for the agentic era","2026-11-07 15:22:41",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add KalarisLabs\u002Fresearch-agent-skills --skill simpo-training",{"tool":46,"command":47},"bunx","bunx skills add KalarisLabs\u002Fresearch-agent-skills --skill simpo-training",{"tool":49,"command":50},"pnpm","pnpm dlx skills add KalarisLabs\u002Fresearch-agent-skills --skill simpo-training","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsimpo-training\u002FSKILL.md",true,[54,60,64],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fdatasets.md","REFERENCE","参考文档",10889,"https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsimpo-training\u002Freferences\u002Fdatasets.md",{"path":61,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fhyperparameters.md",8502,"https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsimpo-training\u002Freferences\u002Fhyperparameters.md",{"path":65,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Floss-functions.md",7067,"https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsimpo-training\u002Freferences\u002Floss-functions.md",[69,76,83,90,97,104],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M74ZSRSWD92NYM8TNJRH35DK","zarr-python","Guides use of Zarr-Python 3 for storing chunked, compressed N-dimensional arrays and groups, with local, in-memory, ZIP, and fsspec-backed S3\u002FGCS\u002FHTTP stores, plus NumPy, Dask, and Xarray integration. Covers array creation, resizing and appending, attributes, chunk and shard sizing, codecs, consolidated metadata, and v2-to-v3 migration. Use when creating or opening Zarr arrays or groups, choosing chunk sizes or compression for large datasets, reading or writing arrays on S3 or GCS, appending to time-series arrays, or migrating code from Zarr-Python 2 to 3. Use when setting up parallel I\u002FO with Dask or Xarray. For labeled multi-dimensional datasets, use Xarray instead.","https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M74ZSK6JG5HKNC1AHF4D97G9","whisper","Transcribes and translates audio with OpenAI's Whisper (openai-whisper Python package and whisper CLI), covering model sizes from tiny to large plus turbo, language specification, initial prompts, word and segment timestamps, temperature fallback, batch processing, and subtitle generation. Use when transcribing speech, podcasts, meetings, or video audio to text. Use when translating non-English speech to English. Use when working with noisy or multilingual audio in any of 99 languages. Use when choosing a Whisper model size for available VRAM. Use when generating subtitles from audio. Not for speaker diarization or live captioning; use AssemblyAI or Deepgram instead.","https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwhisper\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M74ZSBYQ2EGDFTTA4ZK6K5TR","weights-and-biases","Logs and tracks machine learning experiments with Weights & Biases (W&B, wandb): metrics, hyperparameters, checkpoints, sweeps, artifacts with lineage, model registry, custom charts and shareable reports. Includes integrations for PyTorch, HuggingFace Transformers, PyTorch Lightning and Keras\u002FTensorFlow. Use when logging training runs and comparing them across configurations, running automated hyperparameter sweeps, versioning datasets and models as artifacts, registering model versions, or sharing results with a team workspace. Use when setting up wandb.init for offline or unstable-connection training. Not for general data versioning outside ML runs.","https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweights-and-biases\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M74ZS5MZTK84WHEQXCVDZ6GB","waypoint-bio","Use when working with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas pretraining corpus, the Compass eight-task benchmark, or the `waypoint` CLI from the `waypoint-bio` package. Covers embedding microbiome samples, fine-tuning on taxonomic abundance data, benchmarking a checkpoint on Compass, pretraining a GPT-2 model on taxonomic abundance profiles, and converting MetaPhlAn, Kraken2, QIIME 2, or MGnify abundance tables into waypoint format.","https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwaypoint-bio\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M74ZS0TCW96WJAKSG07C5Z7A","verl-rl-training","Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.","https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fverl-rl-training\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M74ZRVG6SSWGT1N3Q55134KA","venue-templates","Prepare journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Use when selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF.","https:\u002F\u002Fgithub.com\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvenue-templates\u002FSKILL.md",[],[]]