mistral_small_model_descriptor#

Classes

`MistralSmallModelDescriptor`
`MistralFFNIntermediateLayerDescriptor`	MistralFFNIntermediateLayerDescriptor(down_proj_name: str = 'mlp.down_proj', ffn_prefix_name: str = 'model.layers.{layer_idx}.mlp', linear_weight_names: List[str] = <factory>)
`MistralKVHeadsLayerDescriptor`	MistralKVHeadsLayerDescriptor(o_proj_name: str = 'self_attn.o_proj', attn_prefix_name: str = 'model.layers.{layer_idx}.self_attn', qkvo_weight_names: List[str] = <factory>)

class MistralFFNIntermediateLayerDescriptor#

Bases: FFNIntermediateLayerDescriptor

MistralFFNIntermediateLayerDescriptor(down_proj_name: str = ‘mlp.down_proj’, ffn_prefix_name: str = ‘model.layers.{layer_idx}.mlp’, linear_weight_names: List[str] = <factory>)

__init__(down_proj_name='mlp.down_proj', ffn_prefix_name='model.layers.{layer_idx}.mlp', linear_weight_names=<factory>)#

Parameters:

down_proj_name (str)
ffn_prefix_name (str)
linear_weight_names (List[str])

Return type:

None

down_proj_name: str = 'mlp.down_proj'#

ffn_prefix_name: str = 'model.layers.{layer_idx}.mlp'#

linear_weight_names: List[str]#

class MistralKVHeadsLayerDescriptor#

Bases: KVHeadsLayerDescriptor

MistralKVHeadsLayerDescriptor(o_proj_name: str = ‘self_attn.o_proj’, attn_prefix_name: str = ‘model.layers.{layer_idx}.self_attn’, qkvo_weight_names: List[str] = <factory>)

__init__(o_proj_name='self_attn.o_proj', attn_prefix_name='model.layers.{layer_idx}.self_attn', qkvo_weight_names=<factory>)#

Parameters:

o_proj_name (str)
attn_prefix_name (str)
qkvo_weight_names (List[str])

Return type:

None

attn_prefix_name: str = 'model.layers.{layer_idx}.self_attn'#

o_proj_name: str = 'self_attn.o_proj'#

qkvo_weight_names: List[str]#

class MistralSmallModelDescriptor#

Bases: ModelDescriptor

static attn_no_op_post_init(decoder_layer)#

Parameters:: decoder_layer (MistralDecoderLayer)

static block_config_to_layer_overrides(block_config)#

Parameters:: block_config (BlockConfig)

static decoder_layer_cls()#

static final_norm_name()#

static init_rotary_embedding(model, runtime)#

Parameters:: model (MistralForCausalLM)

static input_embedding_name()#

static layer_block_name(index)#

Parameters:: index (int)

static layer_name_predicates(num_layers)#

Parameters:: num_layers (int)
Return type:: Dict[str, Pattern]

static mlp_no_op_post_init(decoder_layer)#

Parameters:: decoder_layer (MistralDecoderLayer)

static output_embedding_name()#