PakMosaic-Small / config.json
mahwizzzz's picture
Add Transformers AutoModelForMaskedLM remote code
cebac2b verified
Raw History Blame Contribute Delete
947 Bytes
{
"architectures": ["PakMosaicForMaskedLM"],
"model_type": "pakmosaic",
"auto_map": {
"AutoConfig": "configuration_pakmosaic.PakMosaicConfig",
"AutoModel": "modeling_pakmosaic.PakMosaicModel",
"AutoModelForMaskedLM": "modeling_pakmosaic.PakMosaicForMaskedLM"
},
"vocab_size": 32000,
"hidden_size": 512,
"num_hidden_layers": 12,
"num_attention_heads": 8,
"intermediate_size": 2048,
"max_position_embeddings": 512,
"rope_theta": 10000.0,
"attention_dropout": 0.0,
"hidden_dropout": 0.0,
"ffn_activation": "geglu",
"attention_kind": "full",
"local_window": 128,
"global_every": 3,
"use_bias": false,
"tie_word_embeddings": true,
"pad_token_id": 0,
"bos_token_id": 1,
"eos_token_id": 2,
"unk_token_id": 3,
"mask_token_id": 4,
"layer_norm_eps": 1e-05,
"initializer_range": 0.02,
"script_signal": "none",
"tokenizer_class": "PreTrainedTokenizerFast"
}