Do Thanh Dat
Community@tadod12 · Hanoi, Vietnam
🛒
Agent Skills by Do Thanh Dat
Showing 89 vetted skills indexed across 1 GitHub repositories.
tadod12ml-paper-writing
Structure ML/AI paper outlines, abstracts, and citations for conference submissions.
tadod12autoresearch
Orchestrate autonomous AI research with inner-loop experiments and outer-loop synthesis.
tadod12serving-llms-vllm
Serve LLM inference via OpenAI-compatible endpoints using vLLM.
tadod12tensorrt-llm
Optimize LLM inference with NVIDIA TensorRT for production GPU serving.
tadod12sglang
Serve LLMs with structured JSON and regex outputs using RadixAttention prefix caching.
tadod12llama-cpp
Enables CPU-based LLM inference with GGUF quantization on non-NVIDIA hardware.
tadod12lambda-labs-gpu-cloud
Provisions on-demand GPU cloud instances for ML training and inference via Lambda Labs.
tadod12skypilot-multi-cloud-orchestration
Coordinate ML workloads across multiple clouds using SkyPilot YAML configurations.
tadod12modal-serverless-gpu
Deploy Python-defined ML workloads on-demand GPU infrastructure with web endpoints and batch processing.
tadod12nemo-curator
Automate multimodal dataset curation with deduplication, quality filtering, PII redaction, and NSFW detection.
tadod12ray-data
Scale data preprocessing and ETL for ML workloads with Ray Data.
tadod12dspy
Automate building self-improving modular language-model pipelines with DSPy.
tadod12guidance
Constrain LLM outputs with regex and grammar for JSON, XML, and code.
tadod12outlines
Generate schema-conforming JSON, XML, and code outputs from prompts.
tadod12instructor
Extract structured data from LLM responses with Pydantic validation and automatic retries.
tadod12evaluating-cosmos-policy
Evaluate NVIDIA Cosmos Policy deployments on LIBERO and RoboCasa simulations with latency profiling.
tadod12audiocraft-audio-generation
Generate music and sound effects from text prompts using AudioCraft.
tadod12fine-tuning-openvla-oft
Fine-tune and evaluate OpenVLA-OFT policies with LoRA adaptation.
tadod12segment-anything-model
Generate zero-shot segmentation masks for objects in images using prompts.
tadod12clip
Classify images zero-shot using CLIP image-text similarity.
tadod12stable-diffusion-image-generation
Generate images from text prompts using Stable Diffusion models.
tadod12fine-tuning-serving-openpi
Fine-tune and serve OpenPI robot policies across ALOHA, DROID, and LIBERO environments.
tadod12llava
Set up multimodal chat pipelines combining CLIP vision encoders with Vicuna/LLaMA language models for image-based VQA tasks.
tadod12whisper
Transcribe audio from 99 languages into searchable text using OpenAI Whisper.