569 results (7.4ms) page 6 / 29
zechenzhangAGI / ai-research-skills-sentencepiece exact

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT,...

zechenzhangAGI / ai-research-skills-llama-cpp exact

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization...

zechenzhangAGI / ai-research-skills-mamba-architecture exact

State-space model with O(n) complexity vs Transformers' O(nΒ²). 5Γ— faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2...

zechenzhangAGI / ai-research-skills-llamaguard exact

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy....

zechenzhangAGI / ai-research-skills-distributed-llm-pretraining-torchtitan exact

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+...

zechenzhangAGI / ai-research-skills-training-llms-megatron exact

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on...

zechenzhangAGI / ai-research-skills-optimizing-attention-flash exact

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory...

zechenzhangAGI / ai-research-skills-sparse-autoencoder-training exact

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable...

zechenzhangAGI / ai-research-skills-langchain exact

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory...

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

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without...

zechenzhangAGI / ai-research-skills-blip-2-vision-language exact

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with...

zechenzhangAGI / ai-research-skills-outlines exact

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines -...

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-serving-llms-vllm exact

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with...

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-pytorch-fsdp exact

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

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-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-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...