ministral

ministral

Ministral (MinistralForCausalLM).

Llama's tree and Llama's block: model.{embed_tokens, layers[i].{input_layernorm, self_attn, post_attention_layernorm, mlp}, norm} and lm_head, the residual added in the block, attention through the shared eager forward. Every block may take a sliding window (layer_types); the window is a mask given to the interface, so the values are read as it applies.

RENAME module-attribute

RENAME = {'model.embed_tokens': 'embed_tokens', 'model.layers': 'layers', 'model.norm': 'norm'}

ENVOYS module-attribute

ENVOYS = {MinistralDecoderLayer: Layer, MinistralAttention: Attention, MinistralMLP: Mlp}