Machine Learning

15,552 skills

Ask AI

15,552 skills

Sentencepiece

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, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

endman1000

Machine Learning

Rwkv Architecture

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

endman1000

Machine Learning

Peft Fine Tuning

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

endman1000

Machine Learning

Sglang

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 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

endman1000

Machine Learning

Fine Tuning Openvla Oft

Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.

endman1000

Machine Learning

Openrlhf Training

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. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

endman1000

Machine Learning

Sentencepiece

Rwkv Architecture

Peft Fine Tuning

Sglang

Fine Tuning Openvla Oft

Openrlhf Training

Machine Learning

Sentencepiece

Rwkv Architecture

Peft Fine Tuning

Sglang

Fine Tuning Openvla Oft

Openrlhf Training

Model Merging

Nemo Evaluator Sdk

Moe Training

Miles Rl Training

Model Pruning

Nemo Curator

Cuda Writing

Raster Domain Knowledge Oracle — vibespatial-raster

Training Llms Megatron

U0683 Impact Evidence Provenance Tracker

Sensei

Adaptive Mode

Be Fe Model Sync

Misconception Classify

Robotics Reference To Lesson

New Engine Register

U0598 Observability Training Curriculum Composer

Backtest Pipeline

Architecture

Training

Optimization Attention Reuse Cpu Offload

Apm Ds Baseline

Model Folder Guide

Optimization Attention Reuse Ltxv