Agent Skills by tangzheng202202
Showing 126 vetted skills indexed across 1 GitHub repositories.
tangzheng202202domain
Identify subdomains, inspect SSL certificates, perform WHOIS lookups, and verify DNS records using Python's standard library.
tangzheng202202mlops
Automate end-to-end ML workflows from data ingestion to deployment.
tangzheng202202inference-sh
Automate inference.sh deployment and orchestration across cloud AI services.
tangzheng202202jupyter-live-kernel
Execute Python code against a live Jupyter kernel with persistent state.
tangzheng202202local-llm-deployment-assessment
Assess local hardware and generate optimized LLM deployment configurations.
tangzheng202202huggingface-hub
Manage Hugging Face Hub models, datasets, Spaces, and repositories via hf CLI.
tangzheng202202local-llm-deployment
Automate hardware detection and generate local LLM deployment scripts.
tangzheng202202dspy
Build modular AI pipelines with DSPy declarative language model programming.
tangzheng202202fine-tuning-with-trl
Automate end-to-end RLHF fine-tuning for language models using TRL.
tangzheng202202grpo-rl-training
Fine-tune language models with GRPO-based RL using TRL and structured reward signals.
tangzheng202202peft-fine-tuning
Fine-tune 7B–70B language models with LoRA and QLoRA adapters.
tangzheng202202axolotl
Guide fine-tuning LLMs with Axolotl using YAML configs and LoRA/QLoRA.
tangzheng202202pytorch-fsdp
Guide PyTorch FSDP parameter sharding, mixed precision, and CPU offloading.
tangzheng202202unsloth
Optimize LLM fine-tuning workflows with Unsloth for LoRA/QLoRA and multi-GPU configurations.
tangzheng202202audiocraft-audio-generation
Generate music and sound effects from text descriptions using AudioCraft.
tangzheng202202segment-anything-model
Segment images into object masks using point, box, or mask prompts.
tangzheng202202clip
Enables unflagged image classification and on-the-fly comparison via CLIP-based zero-shot learning.
tangzheng202202stable-diffusion-image-generation
Generate images from text prompts using Stable Diffusion via HuggingFace Diffusers.
tangzheng202202whisper
Transcribe and translate audio across 99 languages using openai-whisper.
tangzheng202202modal-serverless-gpu
Deploy GPU-based ML workloads on a serverless cloud platform.
tangzheng202202guidance
Constrain LLM outputs using regex and grammar rules.
tangzheng202202gguf-quantization
Quantize llama.cpp models to GGUF with 2-8 bit depths.
tangzheng202202serving-llms-vllm
Configure vLLM servers with OpenAI-compatible endpoints, quantization options, and tensor parallelism for scalable LLM deployments on GPU infrastructure.
tangzheng202202obliteratus
Remove refusal behaviors from open-weight LLMs using mechanistic interpretability techniques.