|
{ |
|
"architectures": [ |
|
"CodeFuse_CGE_Large" |
|
], |
|
"auto_map": { |
|
"AutoConfig": "configuration_codefuse_cge_large.CodeFuseCGELargeConfig", |
|
"AutoModel": "modeling_codefuse_cge_large.CodeFuse_CGE_Large" |
|
}, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 2, |
|
"embedding_dim": 4096, |
|
"embedding_method": "pma", |
|
"encoder_mode": "post_normal", |
|
"eos_token_id": 2, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"inf_seq_length": 1024, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 13440, |
|
"keep_max_layer": 32, |
|
"max_position_embeddings": 65536, |
|
"max_window_layers": 28, |
|
"model_type": "qwen2", |
|
"num_attention_heads": 32, |
|
"num_encoder_layers": 0, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 4, |
|
"padding_side": "right", |
|
"pma_ln": true, |
|
"pma_norm": false, |
|
"pma_norm_mode": "post_normal", |
|
"pma_num_heads": 32, |
|
"compress_dim": 1024, |
|
"rms_norm_eps": 1e-05, |
|
"rope_theta": 1000000, |
|
"rotary_emb_base": 1000000, |
|
"seq_length": 65536, |
|
"sliding_window": null, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.39.2", |
|
"use_cache": true, |
|
"use_sliding_window": false, |
|
"vocab_size": 92416 |
|
} |
|
|