569 results (11.4ms) page 8 / 29
zechenzhangAGI / ai-research-skills-speculative-decoding exact

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6Γ— speedup), reducing latency for...

zechenzhangAGI / ai-research-skills-awq-quantization exact

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster...

zechenzhangAGI / ai-research-skills-unsloth exact

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

zechenzhangAGI / ai-research-skills-slime-rl-training exact

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM...

zechenzhangAGI / ai-research-skills-nemo-evaluator-sdk exact

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or...

zechenzhangAGI / ai-research-skills-simpo-training exact

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use...

zechenzhangAGI / ai-research-skills-autogpt-agents exact

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI...

zechenzhangAGI / ai-research-skills-mlflow exact

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

zechenzhangAGI / ai-research-skills-constitutional-ai exact

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety...

zechenzhangAGI / ai-research-skills-moe-training exact

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5Γ— cost reduction vs dense models), implementing sparse...

zechenzhangAGI / ai-research-skills-implementing-llms-litgpt exact

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of...

zechenzhangAGI / ai-research-skills-miles-rl-training exact

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring...

zechenzhangAGI / ai-research-skills-axolotl exact

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

zechenzhangAGI / ai-research-skills-openrlhf-training exact

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2Γ— faster than DeepSpeedChat with...

zechenzhangAGI / ai-research-skills-hqq-quantization exact

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when...

zechenzhangAGI / ai-research-skills-ray-data exact

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s...

zechenzhangAGI / ai-research-skills-evaluating-code-models exact

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language...

zechenzhangAGI / ai-research-skills-tensorboard exact

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

zechenzhangAGI / ai-research-skills-sglang exact

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5Γ— faster...

gptq 0.00
zechenzhangAGI / ai-research-skills-gptq exact

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4Γ— memory reduction with <2% perplexity...