该作者暂无编辑精选条目。
社区索引Community indexed
已收录但未经编辑评测，安装前请自行审阅。prompt guard
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ T…
huggingface tokenizers
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports…
nemo curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× fast…
ray data
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integr…
evolving ai agents
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algo…
deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8…
llama factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal…
sparse autoencoder training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activ…
implementing llms litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mist…
distributed llm pretraining torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when…
mamba architecture
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cach…
rwkv architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infe…
long context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when p…
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experim