Charlie
Community@supporter09 · Hanoi, Vietnam
Software Engineer At Selfomy
Agent Skills by Charlie
Showing 96 vetted skills indexed across 1 GitHub repositories.
Supporter09dspy
Build declarative language model pipelines with signatures, modules, and teleprompters.
Supporter09openrlhf-training
Train large language models with distributed RLHF workflows using Ray and vLLM.
Supporter09nemo-guardrails
Enforce runtime safety policies on LLM applications with Colang 2.0 flows.
Supporter09evaluating-cosmos-policy
Runs Cosmos Policy LIBERO and RoboCasa benchmark evaluations via command-line workflows.
Supporter09llamaindex
Build retrieval-augmented generation applications over private documents and data sources.
Supporter09deepspeed
Configure DeepSpeed for PyTorch training with ZeRO, mixed precision, and pipeline parallelism.
Supporter09crewai-multi-agent
Coordinate multiple specialized AI agents through role-based collaboration.
Supporter09moe-training
Design and optimize Mixture of Experts training workflows with DeepSpeed or HuggingFace.
Supporter09nnsight-remote-interpretability
Trace and manipulate PyTorch model internals for interpretability analysis.
Supporter09langsmith-observability
Trace, evaluate, and monitor LLM application runs with LangSmith.
Supporter09audiocraft-audio-generation
Generate music and sound from text prompts using AudioCraft models.
Supporter09nemo-curator
Filter noise, deduplicate, and redact PII from raw training data.
Supporter09huggingface-accelerate
Simplify distributed PyTorch training across single-device, multi-GPU, and multi-node workflows.
Supporter09chroma
Store embeddings and metadata for semantic search over document collections.
Supporter09prompt-guard
Detect prompt injections and jailbreak attempts in LLM inputs.
Supporter09evaluating-llms-harness
Benchmarks LLMs on-demand with plug-and-play pre-trained AI models.
Supporter09llama-factory
Configure and troubleshoot LLaMA-Factory LLM fine-tuning workflows end to end.
Supporter09academic-plotting
Generate publication-quality ML paper figures with matplotlib and seaborn.
Supporter09knowledge-distillation
Compress large language models via teacher-to-student knowledge distillation.
Supporter09simpo-training
Train language models with reference-free SimPO preference optimization.
Supporter09fine-tuning-openvla-oft
Fine-tune and evaluate OpenVLA-OFT policies for continuous action prediction.
Supporter09slime-rl-training
Coordinate distributed reinforcement-learning post-training for large language models.
Supporter09blip-2-vision-language
Generate image captions and answer visual questions with BLIP-2.
Supporter09pytorch-fsdp2
Shard large PyTorch models across multiple GPUs with FSDP2.