zechenzhangagi/ai-research-skills
GitHubSkill
Installs
ml-paper-writing
519
qdrant-vector-search
45
crewai-multi-agent
43
optimizing-attention-flash
42
huggingface-tokenizers
42
peft-fine-tuning
42
sparse-autoencoder-training
41
guidance
41
speculative-decoding
41
implementing-llms-litgpt
41
rwkv-architecture
41
dspy
41
whisper
41
mamba-architecture
41
unsloth
41
llama-factory
41
nnsight-remote-interpretability
41
mlflow
41
skypilot-multi-cloud-orchestration
41
autogpt-agents
41
long-context
41
langchain
41
modal-serverless-gpu
41
serving-llms-vllm
41
audiocraft-audio-generation
41
nanogpt
41
fine-tuning-with-trl
40
nemo-evaluator-sdk
40
openrlhf-training
40
huggingface-accelerate
40
stable-diffusion-image-generation
40
pytorch-lightning
40
nemo-guardrails
40
weights-and-biases
40
sglang
40
tensorboard
40
nemo-curator
40
model-merging
40
sentencepiece
40
tensorrt-llm
40
outlines
40
grpo-rl-training
40
llamaguard
40
llama-cpp
40
gptq
40
knowledge-distillation
40
chroma
40
pinecone
40
quantizing-models-bitsandbytes
40
ray-data
40
clip
40
sentence-transformers
40
simpo-training
40
awq-quantization
39
phoenix-observability
39
moe-training
39
axolotl
39
pyvene-interventions
39
instructor
39
deepspeed
39
model-pruning
39
segment-anything-model
39
evaluating-llms-harness
39
constitutional-ai
39
gguf-quantization
39
evaluating-code-models
39
transformer-lens-interpretability
39
distributed-llm-pretraining-torchtitan
39
blip-2-vision-language
39
llamaindex
39
faiss
39
miles-rl-training
39
slime-rl-training
38
hqq-quantization
38
verl-rl-training
38
ray-train
38
llava
38
langsmith-observability
38
training-llms-megatron
38
pytorch-fsdp2
38
lambda-labs-gpu-cloud
38
torchforge-rl-training
38
prompt-guard
36
creative-thinking-for-research
34
brainstorming-research-ideas
31
autoresearch
18
fine-tuning-openvla-oft
15
fine-tuning-serving-openpi
15
evaluating-cosmos-policy
15
experiment-tracking-swanlab
15
academic-plotting
13
ml-training-recipes
5
pytorch-fsdp
2