Skills

akillness/ai-research-skills

90 skills90 total installsGithubGithubGitHub

audiocraft-audio-generation

1

ray-train

1

autoresearch

1

awq-quantization

1

axolotl

1

blip-2-vision-language

1

brainstorming-research-ideas

1

chroma

1

clip

1

constitutional-ai

1

creative-thinking-for-research

1

crewai-multi-agent

1

deepspeed

1

distributed-llm-pretraining-torchtitan

1

dspy

1

evaluating-code-models

1

evaluating-cosmos-policy

1

evaluating-llms-harness

1

experiment-tracking-swanlab

1

faiss

1

fine-tuning-openvla-oft

1

fine-tuning-serving-openpi

1

fine-tuning-with-trl

1

autogpt-agents

1

gptq

1

grpo-rl-training

1

guidance

1

hqq-quantization

1

huggingface-accelerate

1

huggingface-tokenizers

1

implementing-llms-litgpt

1

instructor

1

knowledge-distillation

1

lambda-labs-gpu-cloud

1

langchain

1

langsmith-observability

1

llama-cpp

1

llama-factory

1

llamaguard

1

llamaindex

1

llava

1

long-context

1

mamba-architecture

1

miles-rl-training

1

ml-paper-writing

1

mlflow

1

modal-serverless-gpu

1

model-merging

1

model-pruning

1

moe-training

1

nanogpt

1

nemo-curator

1

nemo-evaluator-sdk

1

nemo-guardrails

1

nnsight-remote-interpretability

1

openrlhf-training

1

optimizing-attention-flash

1

outlines

1

peft-fine-tuning

1

phoenix-observability

1

pinecone

1

prompt-guard

1

pytorch-fsdp2

1

pytorch-lightning

1

pyvene-interventions

1

qdrant-vector-search

1

quantizing-models-bitsandbytes

1

ray-data

1

whisper

1

rwkv-architecture

1

segment-anything-model

1

sentence-transformers

1

sentencepiece

1

serving-llms-vllm

1

sglang

1

simpo-training

1

skypilot-multi-cloud-orchestration

1

slime-rl-training

1

sparse-autoencoder-training

1

speculative-decoding

1

stable-diffusion-image-generation

1

tensorboard

1

tensorrt-llm

1

torchforge-rl-training

1

training-llms-megatron

1

transformer-lens-interpretability

1

unsloth

1

verl-rl-training

1

weights-and-biases

1

gguf-quantization

1