orchestra-research/ai-research-skills

100 skills68.3K total installs Github

Github

Github

Skill

Installs

ml-paper-writing

brainstorming-research-ideas

creative-thinking-for-research

academic-plotting

mlflow

serving-llms-vllm

tensorrt-llm

faiss

stable-diffusion-image-generation

ray-train

weights-and-biases

unsloth

crewai-multi-agent

prompt-guard

huggingface-accelerate

peft-fine-tuning

knowledge-distillation

quantizing-models-bitsandbytes

qdrant-vector-search

ray-data

evaluating-llms-harness

audiocraft-audio-generation

gguf-quantization

dspy

langchain

deepspeed

llama-cpp

optimizing-attention-flash

pytorch-lightning

fine-tuning-with-trl

tensorboard

segment-anything-model

whisper

grpo-rl-training

sglang

instructor

huggingface-tokenizers

long-context

axolotl

modal-serverless-gpu

chroma

sentence-transformers

openrlhf-training

hqq-quantization

verl-rl-training

sentencepiece

moe-training

speculative-decoding

outlines

training-llms-megatron

nanogpt

awq-quantization

autoresearch

distributed-llm-pretraining-torchtitan

sparse-autoencoder-training

pytorch-fsdp2

clip

pyvene-interventions

llamaindex

nemo-curator

guidance

nemo-guardrails

model-merging

gptq

llama-factory

simpo-training

llamaguard

transformer-lens-interpretability

autogpt-agents

skypilot-multi-cloud-orchestration

constitutional-ai

implementing-llms-litgpt

nnsight-remote-interpretability

slime-rl-training

rwkv-architecture

torchforge-rl-training

miles-rl-training

model-pruning

mamba-architecture

blip-2-vision-language

pinecone

evaluating-code-models

langsmith-observability

phoenix-observability

llava

lambda-labs-gpu-cloud

nemo-evaluator-sdk

experiment-tracking-swanlab

systems-paper-writing

presenting-conference-talks

fine-tuning-openvla-oft

fine-tuning-serving-openpi

evaluating-cosmos-policy

ml-training-recipes

evolving-ai-agents

ara-rigor-reviewer

ara-compiler

ara-research-manager

writing-systems-papers

pytorch-fsdp