KappTech88
Community@kapptech88
New Developer ready to learn
Agent Skills by KappTech88
Showing 91 vetted skills indexed across 1 GitHub repositories.
KappTech88dspy
Declaratively compose prompts, reasoning steps, and tools into modular language-model pipelines.
KappTech88openrlhf-training
Orchestrate distributed RLHF training with PPO/GRPO/RLOO/DPO across Ray clusters.
KappTech88nemo-guardrails
Implement programmable runtime safety rails for LLM applications with Colang 2.0 DSL.
KappTech88evaluating-cosmos-policy
Evaluate NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments.
KappTech88llamaindex
Ingest, index, and query private data with LlamaIndex for RAG workflows.
KappTech88deepspeed
Configure DeepSpeed ZeRO, pipeline parallelism, and MoE for large-scale training.
KappTech88autoresearch
Orchestrate autonomous AI research projects from literature survey to published results.
KappTech88crewai-multi-agent
Coordinate autonomous AI agents with role-based delegation and memory workflows.
KappTech88moe-training
Configure DeepSpeed MoE training pipelines with expert parallelism and load balancing.
KappTech88nnsight-remote-interpretability
Inspect activations and gradients across PyTorch models with nnsight tracing.
KappTech88langsmith-observability
Diagnose LLM behavior across tracing, evaluation, and monitoring workflows in LangSmith.
KappTech88audiocraft-audio-generation
Convert text descriptions into music and sound effects with AudioCraft.
KappTech88nemo-curator
Curate multimodal datasets for LLM training with GPU-accelerated pipelines.
KappTech88huggingface-accelerate
Enable scalable distributed training across devices with HuggingFace Accelerate.
KappTech88chroma
Store and retrieve vector embeddings with metadata for semantic search.
KappTech88prompt-guard
Detect prompt injections and jailbreak attempts in LLM applications.
KappTech88evaluating-llms-harness
Benchmark LLMs across 60+ academic tasks using lm-eval.
KappTech88llama-factory
Organize LLaMA-Factory documentation and metadata for quick discovery.
KappTech88academic-plotting
Generate publication-quality ML figures from paper context using Gemini and matplotlib/seaborn.
KappTech88knowledge-distillation
Distill knowledge from teacher to student language models using Python tooling.
KappTech88simpo-training
Optimize LLM alignment using preference data without a reference model.
KappTech88fine-tuning-openvla-oft
Fine-tune and evaluate OpenVLA-OFT models with LoRA and FiLM conditioning.
KappTech88slime-rl-training
Deploy RLHF-style post-training pipelines for LLMs with Megatron-LM and SGLang.
KappTech88blip-2-vision-language
Bridge frozen vision encoders and LLMs for multimodal tasks.