#341
1 sources
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
Mlops
37 skills tracked for week 2026-06-17.
#342
1 sources
axolotl
Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#351
1 sources
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#354
1 sources
clip
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks w...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#364
1 sources
distributed-llm-pretraining-torchtitan
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+ GPUs with Float8, torch.compile, and dist...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#369
1 sources
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#371
1 sources
evaluating-llms-harness
lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#375
1 sources
faiss
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or whe...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#378
1 sources
fine-tuning-with-trl
TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#390
1 sources
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#398
1 sources
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch comm...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#399
1 sources
huggingface-hub
HuggingFace hf CLI: search/download/upload models, datasets.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#400
1 sources
huggingface-tokenizers
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integ...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#406
1 sources
instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#411
1 sources
lambda-labs-gpu-cloud
Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#413
1 sources
llama-cpp
llama.cpp local GGUF inference + HF Hub model discovery.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#414
1 sources
llava
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruct...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#424
1 sources
modal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#427
1 sources
nemo-curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs wit...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#430
1 sources
obliteratus
OBLITERATUS: abliterate LLM refusals (diff-in-means).
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#437
1 sources
optimizing-attention-flash
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 issues with attention, or need faster in...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#440
1 sources
outlines
Outlines: structured JSON/regex/Pydantic LLM generation.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#444
1 sources
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 se...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#445
1 sources
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or se...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#456
1 sources
pytorch-fsdp
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#457
1 sources
pytorch-lightning
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops w...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#458
1 sources
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered per...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#465
1 sources
segment-anything-model
SAM: zero-shot image segmentation via points, boxes, masks.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#466
1 sources
serving-llms-vllm
vLLM: high-throughput LLM serving, OpenAI API, quantization.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#471
1 sources
simpo-training
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 for preference alignment when want simpl...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#474
1 sources
slime-rl-training
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 integration for RL scaling.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#478
1 sources
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#480
1 sources
stable-diffusion-image-generation
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#488
1 sources
tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantizatio...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#491
1 sources
unsloth
Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#494
1 sources
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0
#495
1 sources
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast...
- Total
- 1
- ClawHub
- 0
- Hermes
- 1
- GitHub
- 0