PhatcatDK's picture
Unbotch model
0dbd5cd verified
{
"architectures": [
"T5GemmaEncoderModel"
],
"bos_token_id": 2,
"classifier_dropout_rate": 0.0,
"dtype": "bfloat16",
"encoder": {
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": 50.0,
"bos_token_id": 2,
"classifier_dropout_rate": 0.0,
"dropout_rate": 0.0,
"dtype": "bfloat16",
"eos_token_id": 1,
"final_logit_softcapping": 30.0,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 14336,
"is_decoder": false,
"layer_types": [
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 8192,
"model_type": "t5_gemma_module",
"num_attention_heads": 16,
"num_hidden_layers": 42,
"num_key_value_heads": 8,
"pad_token_id": 0,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"sliding_window": 4096,
"tie_word_embeddings": true,
"use_cache": true,
"vocab_size": 256000
},
"eos_token_id": [
1,
107
],
"initializer_range": 0.02,
"is_encoder_decoder": false,
"model_type": "t5gemma",
"pad_token_id": 0,
"tie_word_embeddings": true,
"transformers_version": "5.3.0.dev0",
"vocab_size": 256000
}