Backlinks

• concepts:block_attnres
• concepts:chinchilla_scaling
• concepts:expert_routing
• concepts:gradient_highway
• concepts:hidden_state_growth
• concepts:kimi_linear
• concepts:layer_normalization
• concepts:layer_pruning
• concepts:linear_attention
• concepts:model_pruning
• concepts:moe
• concepts:multi_head_attention
• concepts:neural_scaling
• concepts:pipeline_communication
• concepts:positional_encoding
• concepts:postnorm
• concepts:prenorm
• concepts:residual_connections
• concepts:rnn
• concepts:scaled_dot_product_attention
• concepts:scaling_laws
• concepts:softmax_attention
• concepts:transformer
• concepts:vanishing_gradients
• papers:start