orchestra-research/ai-research-skills

100 skills87.3K total installs Github

Github

Github

Skill

Installs

ml-paper-writing

brainstorming-research-ideas

creative-thinking-for-research

academic-plotting

mlflow

serving-llms-vllm

faiss

tensorrt-llm

stable-diffusion-image-generation

peft-fine-tuning

ray-train

autoresearch

weights-and-biases

gguf-quantization

crewai-multi-agent

huggingface-accelerate

unsloth

audiocraft-audio-generation

segment-anything-model

qdrant-vector-search

prompt-guard

evaluating-llms-harness

knowledge-distillation

ray-data

llama-cpp

pytorch-lightning

fine-tuning-with-trl

quantizing-models-bitsandbytes

tensorboard

dspy

grpo-rl-training

optimizing-attention-flash

verl-rl-training

deepspeed

langchain

hqq-quantization

huggingface-tokenizers

axolotl

sentence-transformers

whisper

modal-serverless-gpu

long-context

awq-quantization

chroma

clip

pytorch-fsdp2

instructor

distributed-llm-pretraining-torchtitan

openrlhf-training

sglang

nanogpt

sentencepiece

speculative-decoding

slime-rl-training

llamaindex

llama-factory

evaluating-code-models

transformer-lens-interpretability

outlines

simpo-training

training-llms-megatron

pyvene-interventions

moe-training

sparse-autoencoder-training

guidance

model-merging

nemo-curator

implementing-llms-litgpt

gptq

mamba-architecture

llamaguard

torchforge-rl-training

miles-rl-training

nemo-guardrails

skypilot-multi-cloud-orchestration

autogpt-agents

model-pruning

nnsight-remote-interpretability

langsmith-observability

pinecone

constitutional-ai

rwkv-architecture

blip-2-vision-language

lambda-labs-gpu-cloud

phoenix-observability

nemo-evaluator-sdk

llava

systems-paper-writing

presenting-conference-talks

experiment-tracking-swanlab

ml-training-recipes

fine-tuning-openvla-oft

fine-tuning-serving-openpi

evaluating-cosmos-policy

evolving-ai-agents

ara-rigor-reviewer

ara-compiler

ara-research-manager

writing-systems-papers

pytorch-fsdp