orchestra-research/ai-research-skills
GitHubSkill
Installs
ml-paper-writing
171
faiss
70
mlflow
70
serving-llms-vllm
68
tensorrt-llm
67
ray-train
64
prompt-guard
63
ray-data
57
stable-diffusion-image-generation
55
knowledge-distillation
55
qdrant-vector-search
54
crewai-multi-agent
54
speculative-decoding
54
langchain
53
pytorch-lightning
53
sparse-autoencoder-training
53
llamaindex
53
chroma
53
hqq-quantization
53
moe-training
53
awq-quantization
53
unsloth
52
llamaguard
52
optimizing-attention-flash
52
nemo-guardrails
52
quantizing-models-bitsandbytes
52
simpo-training
52
creative-thinking-for-research
52
huggingface-accelerate
52
sglang
52
phoenix-observability
52
blip-2-vision-language
52
gguf-quantization
52
training-llms-megatron
52
clip
52
deepspeed
52
dspy
52
instructor
51
guidance
51
nemo-curator
51
grpo-rl-training
51
gptq
51
openrlhf-training
51
peft-fine-tuning
51
outlines
51
huggingface-tokenizers
51
model-pruning
51
slime-rl-training
51
autogpt-agents
51
sentence-transformers
51
miles-rl-training
51
pinecone
51
langsmith-observability
51
segment-anything-model
51
long-context
51
mamba-architecture
51
whisper
50
pyvene-interventions
50
modal-serverless-gpu
50
constitutional-ai
50
audiocraft-audio-generation
50
skypilot-multi-cloud-orchestration
50
torchforge-rl-training
50
nanogpt
50
lambda-labs-gpu-cloud
50
rwkv-architecture
50
weights-and-biases
50
tensorboard
50
verl-rl-training
50
fine-tuning-with-trl
50
llava
50
nnsight-remote-interpretability
50
model-merging
50
pytorch-fsdp2
50
axolotl
49
sentencepiece
49
llama-cpp
49
distributed-llm-pretraining-torchtitan
49
transformer-lens-interpretability
49
llama-factory
49
evaluating-code-models
49
nemo-evaluator-sdk
49
implementing-llms-litgpt
49
evaluating-llms-harness
48
brainstorming-research-ideas
45
autoresearch
1