orchestra-research/ai-research-skills

99 skills18.9K total installs Github

Github

Github

Skill

Installs

ml-paper-writing

brainstorming-research-ideas

mlflow

faiss

tensorrt-llm

serving-llms-vllm

creative-thinking-for-research

ray-train

prompt-guard

stable-diffusion-image-generation

ray-data

huggingface-accelerate

quantizing-models-bitsandbytes

langchain

unsloth

chroma

crewai-multi-agent

verl-rl-training

knowledge-distillation

qdrant-vector-search

llamaindex

sentence-transformers

nemo-guardrails

llamaguard

deepspeed

modal-serverless-gpu

pyvene-interventions

sglang

nemo-curator

training-llms-megatron

dspy

grpo-rl-training

openrlhf-training

hqq-quantization

speculative-decoding

torchforge-rl-training

outlines

constitutional-ai

sparse-autoencoder-training

pytorch-lightning

guidance

awq-quantization

axolotl

evaluating-llms-harness

instructor

miles-rl-training

gguf-quantization

audiocraft-audio-generation

long-context

weights-and-biases

llama-cpp

distributed-llm-pretraining-torchtitan

llama-factory

fine-tuning-with-trl

simpo-training

slime-rl-training

sentencepiece

langsmith-observability

moe-training

pytorch-fsdp2

optimizing-attention-flash

transformer-lens-interpretability

clip

nanogpt

gptq

peft-fine-tuning

lambda-labs-gpu-cloud

blip-2-vision-language

whisper

pinecone

huggingface-tokenizers

phoenix-observability

skypilot-multi-cloud-orchestration

mamba-architecture

autogpt-agents

tensorboard

segment-anything-model

llava

nnsight-remote-interpretability

model-pruning

rwkv-architecture

evaluating-code-models

model-merging

implementing-llms-litgpt

nemo-evaluator-sdk

academic-plotting

autoresearch

experiment-tracking-swanlab

fine-tuning-serving-openpi

fine-tuning-openvla-oft

evaluating-cosmos-policy

ml-training-recipes

presenting-conference-talks

systems-paper-writing

evolving-ai-agents

ara-rigor-reviewer

ara-research-manager

ara-compiler

writing-systems-papers