MCPcopy Create free account
hub / github.com/THUDM/LongWriter / __init__

Method __init__

train/patch/modeling_chatglm.py:422–444  ·  view source on GitHub ↗
(self, config: ChatGLMConfig, layer_number, device=None)

Source from the content-addressed store, hash-verified

420 """
421
422 def __init__(self, config: ChatGLMConfig, layer_number, device=None):
423 super(GLMBlock, self).__init__()
424 self.layer_number = layer_number
425
426 self.apply_residual_connection_post_layernorm = config.apply_residual_connection_post_layernorm
427
428 self.fp32_residual_connection = config.fp32_residual_connection
429
430 LayerNormFunc = RMSNorm if config.rmsnorm else LayerNorm
431 # Layernorm on the input data.
432 self.input_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device,
433 dtype=config.torch_dtype)
434
435 # Self attention.
436 self.self_attention = SelfAttention(config, layer_number, device=device)
437 self.hidden_dropout = config.hidden_dropout
438
439 # Layernorm on the attention output
440 self.post_attention_layernorm = LayerNormFunc(config.hidden_size, eps=config.layernorm_epsilon, device=device,
441 dtype=config.torch_dtype)
442
443 # MLP
444 self.mlp = MLP(config, device=device)
445
446 def forward(
447 self, hidden_states, attention_mask, rotary_pos_emb, kv_cache=None, use_cache=True,

Callers

nothing calls this directly

Calls 3

SelfAttentionClass · 0.85
MLPClass · 0.85
__init__Method · 0.45

Tested by

no test coverage detected