All authors
Claude Skills by VectorSpaceLab
github.com/VectorSpaceLab6,028 skills74 installs15,373 views
- Model Selection"Rank pretrained models with TLLib transferability metricsVotes: 0GitHub stars: 247
- Self Training"Operate Transfer Learning Library semi-supervised andVotes: 0GitHub stars: 247
- Task Generalization"Operate Transfer Learning Library domain-generalization andVotes: 0GitHub stars: 247
- Translation"Operate TLLib image/domain translation and style-transferVotes: 0GitHub stars: 247
- Vision Data Models"Operate TLLib vision datasets, ImageList formats, transforms,Votes: 0GitHub stars: 247
- Transformer Engine"Route Transformer Engine installation/build, PyTorch, JAX, andVotes: 0GitHub stars: 247
- Install BuildInstall, build, and verify NVIDIA Transformer Engine runtime variants safely.Votes: 0GitHub stars: 247
- Jax"Use NVIDIA Transformer Engine JAX and Flax APIs for moduleVotes: 0GitHub stars: 247
- Pytorch"Operate transformer_engine.pytorch for PyTorch layers, precisionVotes: 0GitHub stars: 247
- Transformerlab App"Operate on the Transformer Lab application monorepo: React web UI,Votes: 0GitHub stars: 247
- Backend Api Services"Modify and debug Transformer Lab FastAPI backend routers,Votes: 0GitHub stars: 247
- Cli Sdk Workflows"Operate on Transformer Lab Typer CLI, Textual job monitor, CLIVotes: 0GitHub stars: 247
- Frontend Web App"Operate on the Transformer Lab React TypeScript web UI,Votes: 0GitHub stars: 247
- Task Execution Compute"Operate on Transformer Lab task creation, job launch queues,Votes: 0GitHub stars: 247
- Transformers"Use and extend Hugging Face Transformers for inference,Votes: 0GitHub stars: 247
- Generation"Configure Transformers text/chat generation, GenerationConfig,Votes: 0GitHub stars: 247
- Inference Pipelines"Use Transformers pipelines and AutoClass inference workflowsVotes: 0GitHub stars: 247
- Model Extension"Add or modify Transformers models, tokenizers, processors,Votes: 0GitHub stars: 247
- Quantization Integrations"Choose and validate Transformers quantization methods, backendVotes: 0GitHub stars: 247
- Serving Cli"Use the Transformers CLI for download, chat, local serving,Votes: 0GitHub stars: 247
- Tokenizers Processors"Use Transformers tokenizers, processors, image/audio/videoVotes: 0GitHub stars: 247
- Training"Create Transformers Trainer, TrainingArguments, data-collator,Votes: 0GitHub stars: 247
- Transfuser"Guides TransFuser autonomous-driving model training, multimodalVotes: 0GitHub stars: 247
- Carla Evaluation"Plans and diagnoses TransFuser CARLA 0.9.10.1 evaluation, Longest6Votes: 0GitHub stars: 247
- Data And Routes"Guides TransFuser CARLA training route and scenario preparation,Votes: 0GitHub stars: 247
- Model Training"Guides TransFuser imitation-model training, dataset andVotes: 0GitHub stars: 247
- Sensor Agent"Operate a trained TransFuser model through the CARLA sensor-agentVotes: 0GitHub stars: 247
- Tree Of Thoughts Llm"Routes Tree of Thoughts workflows for game24, coherent passageVotes: 0GitHub stars: 247
- Crosswords"Routes 5x5 mini crossword workflows for Tree of Thoughts sampling,Votes: 0GitHub stars: 247
- Game24"Routes Game of 24 workflows for arithmetic puzzle solving withVotes: 0GitHub stars: 247
- Text"Routes coherent passage generation workflows for the Tree ofVotes: 0GitHub stars: 247
- Tree Of Thoughts"Use the tree-of-thoughts Python package to configure TotAgentVotes: 0GitHub stars: 247
- Agents And Models"Configure and inspect tree-of-thoughts TotAgent model adapters,Votes: 0GitHub stars: 247
- Search Workflows"Run and adapt tree-of-thoughts DFS/BFS search workflows withVotes: 0GitHub stars: 247
- Triton Inference Server"Route NVIDIA Triton Inference Server tasks across server runtime,Votes: 0GitHub stars: 247
- Client Protocols"Build and troubleshoot Triton KServe HTTP/gRPC request payloadsVotes: 0GitHub stars: 247
- In Process Frontends"Use Triton Python packages `tritonserver` and `tritonfrontend` toVotes: 0GitHub stars: 247
- Model Repository And Config"Create, validate, and troubleshoot Triton model repositories andVotes: 0GitHub stars: 247
- Openai Llm Frontend"Launch and use Triton's OpenAI-compatible LLM frontend over vLLMVotes: 0GitHub stars: 247
- Server Runtime And Deployment"Plan, launch, build, deploy, observe, and troubleshoot NVIDIAVotes: 0GitHub stars: 247
- Trl"Use and modify TRL, the Hugging Face Transformers ReinforcementVotes: 0GitHub stars: 247
- Cli And Configs"Build and debug TRL CLI commands, YAML configs, dataset mixtureVotes: 0GitHub stars: 247
- Core Training"Choose, instantiate, and troubleshoot TRL stable post-trainingVotes: 0GitHub stars: 247
- Data And Rewards"Prepare and validate TRL datasets, chat templates, multimodalVotes: 0GitHub stars: 247
- Experimental And Environments"Use TRL experimental trainers and environment-based GRPOVotes: 0GitHub stars: 247
- Repo Development"Modify the TRL repository safely as a contributor or maintainer,Votes: 0GitHub stars: 247
- Scaling And Backends"Choose and diagnose TRL scaling, memory, kernel, PEFT, and vLLMVotes: 0GitHub stars: 247
- Trlx"Guides trlX LLM post-training, RLHF, Accelerate, configuration,Votes: 0GitHub stars: 247
- Nemo"Router for trlX's optional NVIDIA NeMo/Megatron backend: when toVotes: 0GitHub stars: 247
- Training"Training, configuration, data, checkpointing, PEFT, and sweepVotes: 0GitHub stars: 247