firecrawl/ai-research-skills
GitHubSkill
Installs
llama-cpp
32
speculative-decoding
28
knowledge-distillation
28
unsloth
27
stable-diffusion-image-generation
27
audiocraft-audio-generation
27
sentence-transformers
26
llamaindex
26
whisper
26
ml-paper-writing
25
sglang
25
dspy
25
chroma
25
long-context
25
transformer-lens-interpretability
24
crewai-multi-agent
24
segment-anything-model
24
tensorboard
24
torchforge-rl-training
24
serving-llms-vllm
24
evaluating-llms-harness
24
clip
23
prompt-guard
23
langchain
23
awq-quantization
23
nemo-curator
23
huggingface-tokenizers
23
ray-train
23
blip-2-vision-language
23
hqq-quantization
23
model-merging
23
guidance
23
evaluating-code-models
23
pyvene-interventions
23
langsmith-observability
23
outlines
23
sentencepiece
23
tensorrt-llm
23
pinecone
23
modal-serverless-gpu
23
optimizing-attention-flash
23
llava
23
faiss
22
slime-rl-training
22
weights-and-biases
22
training-llms-megatron
22
rwkv-architecture
22
lambda-labs-gpu-cloud
22
llamaguard
22
miles-rl-training
22
nemo-evaluator-sdk
22
grpo-rl-training
22
gptq
22
implementing-llms-litgpt
22
mamba-architecture
22
llama-factory
22
peft-fine-tuning
22
deepspeed
22
constitutional-ai
22
gguf-quantization
22
model-pruning
22
qdrant-vector-search
22
autogpt-agents
22
verl-rl-training
22
sparse-autoencoder-training
22
moe-training
22
phoenix-observability
22
pytorch-lightning
22
fine-tuning-with-trl
22
simpo-training
22
openrlhf-training
22
nemo-guardrails
22
huggingface-accelerate
22
pytorch-fsdp2
22
ray-data
22
nnsight-remote-interpretability
22
distributed-llm-pretraining-torchtitan
22
axolotl
22
quantizing-models-bitsandbytes
22
skypilot-multi-cloud-orchestration
22
nanogpt
22
mlflow
22
instructor
22