evaluating-llms-harness
orchestra-research
Compare language models on academic benchmarks.
Model evaluation
+1
Machine learning & data science skills for AI agents
Data comes first here: analysis and visualisation Skills explore datasets, test hypotheses and build dashboards. Machine learning Skills fine-tune and evaluate models, train them across many GPUs and serve them, with smaller groups for computer vision, language and vector search.
Sort by
Most installed
532 Skills
Showing Skills in Machine learning & data science.- 912
- 910
knowledge-distillation
orchestra-research
Train smaller language models with larger teachers.
Model compression
- 909
llama-cpp
orchestra-research
Run language models locally without NVIDIA.
Model inference
909pgvector-semantic-search
timescale
Find related text by meaning in PostgreSQL.
Semantic search
- 908
fine-tuning-with-trl
orchestra-research
Train language models to follow human preferences.
Language model training
- 908
pytorch-lightning
orchestra-research
Cleaner PyTorch training code that scales to more GPUs.
Machine learning
- 906
tensorboard
orchestra-research
See how your models train and compare runs.
Machine learning
- 905
quantizing-models-bitsandbytes
orchestra-research
Fit larger language models into your GPU memory.
Machine learning
905senior-ml-engineer
alirezarezvani
Production deployment patterns for your ML models.
ML engineering
- 904
verl-rl-training
orchestra-research
Train language models with reinforcement learning.
Language model training
903data-scientist
sickn33
Turn complex data into tested business insights.
Data science
- 903
deepspeed
orchestra-research
Practical guidance for DeepSpeed model training.
Distributed training
- 903
grpo-rl-training
orchestra-research
Fine-tune language models with custom rewards.
Model fine-tuning
- 901
huggingface-tokenizers
orchestra-research
Train custom tokenizers for your text models.
Natural language processing
- 898
distributed-llm-pretraining-torchtitan
orchestra-research
Train large language models across many GPUs.
Language model training
+1 - 898
long-context
orchestra-research
Make transformer models handle longer documents.
Machine learning
- 898
pytorch-fsdp2
orchestra-research
Train models too large for one GPU with PyTorch.
Distributed training
- 898
sentence-transformers
orchestra-research
Build local semantic search with text embeddings.
Machine learning
- 897
nanogpt
orchestra-research
Train a small language model on Shakespeare.
Language model training
- 897
openrlhf-training
orchestra-research
Train large language models with OpenRLHF.
Language model training
XG+3 
896chart-animation
iart-ai
Turn your datasets into animated chart videos.
Data visualization
- 896
chroma
orchestra-research
Build semantic search over your documents.
Semantic search
- 896
clip
orchestra-research
Build image search that understands your words.
Computer vision
895d3-viz
calesthio
Custom D3.js charts with precise visual control.
Data visualisation
Yes, on hardware you provide or a cloud you connect. Training Skills set up the run, watch it, and save the evidence so results can be compared.
No, but the Skills show their working: which test they ran, on what data and with what assumptions, so you can judge the result.
Under Research & science, with the other domain-science Skills. This category keeps general data analysis and machine learning.