Back to tags
Tag

Agent Skills with tag: Training]

9 skills match this tag. Use tags to discover related Agent Skills and explore similar workflows.

distributed-training-pytorch-fsdp

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

[DistributedTrainingPyTorchFSDP
Orchestra Research
Orchestra Research
33,1943,891

emerging-techniques-moe-training

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

[EmergingTechniquesMoEMixture
Orchestra Research
Orchestra Research
33,1943,891

model-architecture-nanogpt

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

[ModelArchitectureNanoGPTGPT-2
Orchestra Research
Orchestra Research
33,1943,891

post-training-simpo

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

[Post-TrainingSimPOPreferenceOptimization
Orchestra Research
Orchestra Research
33,1943,891

post-training-verl

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

[ReinforcementLearningRLHFGRPO
Orchestra Research
Orchestra Research
33,1943,891

pytorch-fsdp

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

[DistributedTrainingPyTorchFSDP
poorrican
poorrican
0

simpo-training

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

[Post-TrainingSimPOPreferenceOptimization
poorrican
poorrican
0

pytorch-fsdp

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

[DistributedTrainingPyTorchFSDP
PoorRican
PoorRican
0

simpo-training

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

[Post-TrainingSimPOPreferenceOptimization
PoorRican
PoorRican
0