All authors
Claude Skills by VectorSpaceLab
github.com/VectorSpaceLab6,028 skills74 installs15,373 views
- Proxy Server"Use when working with the LiteLLM AI Gateway proxy: starting theVotes: 0GitHub stars: 247
- Routing"Use this when configuring, validating, or debugging LiteLLM RouterVotes: 0GitHub stars: 247
- Sdk Core"Use for direct LiteLLM Python SDK work: chat/text completions,Votes: 0GitHub stars: 247
- Litgpt"Use LitGPT to run local LLM inference, chat, finetuning,Votes: 0GitHub stars: 247
- Checkpoint Conversion"Download, validate, convert, classify, and merge LitGPTVotes: 0GitHub stars: 247
- Evaluation Serving"Evaluate LitGPT checkpoints with LM Evaluation Harness and serveVotes: 0GitHub stars: 247
- Inference Chat"Use LitGPT for local text generation, chat, and Python APIVotes: 0GitHub stars: 247
- Training Data"Plan and validate LitGPT finetuning, LoRA/QLoRA/full/adapterVotes: 0GitHub stars: 247
- Litserve"Serve custom AI APIs with LitServe, including general LitAPI andVotes: 0GitHub stars: 247
- Mcp"Expose LitServe LitAPI endpoints as Model Context Protocol toolsVotes: 0GitHub stars: 247
- Openai Specs"Build and debug LitServe OpenAI-compatible chat completions andVotes: 0GitHub stars: 247
- Server Basics"Serve models and custom pipelines with LitServe LitAPI andVotes: 0GitHub stars: 247
- Llama Factory"Use for LlamaFactory repository workflows: training configs,Votes: 0GitHub stars: 247
- Data And Templates"Use this sub-skill when working on LlamaFactory dataset_infoVotes: 0GitHub stars: 247
- Inference And Serving"Use this sub-skill for LlamaFactory inference, ChatModel usage,Votes: 0GitHub stars: 247
- Model Loading And Export"Use for LlamaFactory model/tokenizer/processor loading, modelVotes: 0GitHub stars: 247
- Training And Configs"Use for LlamaFactory v0 training runs, config files, CLIVotes: 0GitHub stars: 247
- V1 Experimental"Use for LlamaFactory experimental v1 flows selected with USE_V1=1,Votes: 0GitHub stars: 247
- Webui And Ops"Operate LLaMA Factory's LlamaBoard Web UI, web chat,Votes: 0GitHub stars: 247
- Llama Index"Build, customize, troubleshoot, and maintain LlamaIndex PythonVotes: 0GitHub stars: 247
- Agents And Workflows"Build LlamaIndex agents and workflows with tools, memory, chatVotes: 0GitHub stars: 247
- Customization And Structured Outputs"Customize LlamaIndex Settings, prompts, callbacks,Votes: 0GitHub stars: 247
- Indexing And Querying"Build and query LlamaIndex indexes, persist and reload storage,Votes: 0GitHub stars: 247
- Ingestion And Loading"Load local files or raw text into LlamaIndex Documents, split themVotes: 0GitHub stars: 247
- Integrations And Storage"Choose and verify LlamaIndex integration packages, namespaceVotes: 0GitHub stars: 247
- Repo Maintenance"Maintain the LlamaIndex monorepo safely: inspect package layoutVotes: 0GitHub stars: 247
- Llamagen"Router for LlamaGen autoregressive image-generation workflows,Votes: 0GitHub stars: 247
- Class Conditional"Router for LlamaGen class-conditional ImageNet generation,Votes: 0GitHub stars: 247
- Data Preparation"Router for ImageNet code extraction, T5 feature extraction, andVotes: 0GitHub stars: 247
- Text Conditional"Router for LlamaGen caption-conditioned training, sampling, promptVotes: 0GitHub stars: 247
- Tokenizers"Router for VQ, VQGAN, Stable Diffusion VAE, and ConsistencyVotes: 0GitHub stars: 247
- Llava"Guides LLaVA vision-language model inference, serving, training,Votes: 0GitHub stars: 247
- Chat And Serve"Guides LLaVA image chat, local inference, CLI prompts, modelVotes: 0GitHub stars: 247
- Evaluate And Benchmark"Guides LLaVA custom VQA evaluation, benchmark inference, chunkedVotes: 0GitHub stars: 247
- Train And Finetune"Guides LLaVA custom training data, pretraining, full fine-tuning,Votes: 0GitHub stars: 247
- Llm Foundry"Use MosaicML LLM Foundry for LLM data preparation, ComposerVotes: 0GitHub stars: 247
- Data Preparation"Prepare LLM Foundry pretraining, fine-tuning, raw-text,Votes: 0GitHub stars: 247
- Evaluation"Configure and run LLM Foundry offline and in-training ICLVotes: 0GitHub stars: 247
- Inference Conversion"Use LLM Foundry inference helpers for Hugging Face generation,Votes: 0GitHub stars: 247
- Package Apis Configuration"Inspect and use LLM Foundry package APIs, registries, MPT/HF modelVotes: 0GitHub stars: 247
- Training Finetuning"Create, inspect, adapt, and troubleshoot LLM Foundry pretrainingVotes: 0GitHub stars: 247
- Llm Rl Visualized"Route bilingual concept lookup, diagram-family navigation,Votes: 0GitHub stars: 247
- Asset MaintenanceSafely inspect, preview, and maintain the bilingual diagram asset tree.Votes: 0GitHub stars: 247
- Knowledge Atlas"Route concept lookup, bilingual terminology, diagram-familyVotes: 0GitHub stars: 247
- Llm4decompile"Route requests for LLM4Decompile training, direct decompilation,Votes: 0GitHub stars: 247
- Evaluation"Run direct decompilation inference and benchmark scoring forVotes: 0GitHub stars: 247
- Ghidra Refine"Extract pseudo-code with Ghidra and refine it with theVotes: 0GitHub stars: 247
- Sk2decompile"Run the SK²Decompile two-phase skeleton/skin pipeline, RL helpers,Votes: 0GitHub stars: 247
- TrainingTrain, fine-tune, or prepare datasets for LLM4Decompile models.Votes: 0GitHub stars: 247
- Lm Evaluation Harness"Use EleutherAI LM Evaluation Harness for language-model evaluationVotes: 0GitHub stars: 247