HomePricingHow it worksSkills
Log in
GitHub repository

orchestra-research/ai-research-skills

View repository
Skills
98
Installs
2,019
Stars
~12.4K
License
—

Skills in this repository

01
ml-paper-writing
2,019
02
academic-plotting
—
03
ara-compiler
—
04
ara-research-manager
—
05
ara-rigor-reviewer
—
06
audiocraft-audio-generation
—
07
autogpt-agents
—
08
autoresearch
—
09
awq-quantization
—
10
axolotl
—
11
blip-2-vision-language
—
12
brainstorming-research-ideas
—
13
chroma
—
14
clip
—
15
constitutional-ai
—
16
creative-thinking-for-research
—
17
crewai-multi-agent
—
18
deepspeed
—
19
distributed-llm-pretraining-torchtitan
—
20
dspy
—
21
evaluating-code-models
—
22
evaluating-cosmos-policy
—
23
evaluating-llms-harness
—
24
evolving-ai-agents
—
25
experiment-tracking-swanlab
—
26
faiss
—
27
fine-tuning-openvla-oft
—
28
fine-tuning-serving-openpi
—
29
fine-tuning-with-trl
—
30
gguf-quantization
—
31
gptq
—
32
grpo-rl-training
—
33
guidance
—
34
hqq-quantization
—
35
huggingface-accelerate
—
36
huggingface-tokenizers
—
37
implementing-llms-litgpt
—
38
instructor
—
39
knowledge-distillation
—
40
lambda-labs-gpu-cloud
—
41
langchain
—
42
langsmith-observability
—
43
llama-cpp
—
44
llama-factory
—
45
llamaguard
—
46
llamaindex
—
47
llava
—
48
long-context
—
49
mamba-architecture
—
50
miles-rl-training
—
51
mlflow
—
52
ml-training-recipes
—
53
modal-serverless-gpu
—
54
model-merging
—
55
model-pruning
—
56
moe-training
—
57
nanogpt
—
58
nemo-curator
—
59
nemo-evaluator-sdk
—
60
nemo-guardrails
—
61
nnsight-remote-interpretability
—
62
openrlhf-training
—
63
optimizing-attention-flash
—
64
outlines
—
65
peft-fine-tuning
—
66
phoenix-observability
—
67
pinecone
—
68
presenting-conference-talks
—
69
prompt-guard
—
70
pytorch-fsdp2
—
71
pytorch-lightning
—
72
pyvene-interventions
—
73
qdrant-vector-search
—
74
quantizing-models-bitsandbytes
—
75
ray-data
—
76
ray-train
—
77
rwkv-architecture
—
78
segment-anything-model
—
79
sentencepiece
—
80
sentence-transformers
—
81
serving-llms-vllm
—
82
sglang
—
83
simpo-training
—
84
skypilot-multi-cloud-orchestration
—
85
slime-rl-training
—
86
sparse-autoencoder-training
—
87
speculative-decoding
—
88
stable-diffusion-image-generation
—
89
systems-paper-writing
—
90
tensorboard
—
91
tensorrt-llm
—
92
torchforge-rl-training
—
93
training-llms-megatron
—
94
transformer-lens-interpretability
—
95
unsloth
—
96
verl-rl-training
—
97
weights-and-biases
—
98
whisper
—