4.08 kB

	{
	"architectures": [
	"T5GemmaForConditionalGeneration"
	],
	"classifier_dropout_rate": 0.0,
	"decoder": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_logit_softcapping": 50.0,
	"classifier_dropout_rate": 0.0,
	"cross_attention_hidden_size": 3584,
	"dropout_rate": 0.0,
	"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": true,
	"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,
	"query_pre_attn_scalar": 256,
	"rms_norm_eps": 1e-06,
	"rope_theta": 10000.0,
	"sliding_window": 4096,
	"torch_dtype": "bfloat16",
	"use_cache": true,
	"vocab_size": 256000
	},
	"dropout_rate": 0.0,
	"encoder": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_logit_softcapping": 50.0,
	"classifier_dropout_rate": 0.0,
	"dropout_rate": 0.0,
	"final_logit_softcapping": 30.0,
	"head_dim": 256,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 3584,
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"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,
	"query_pre_attn_scalar": 256,
	"rms_norm_eps": 1e-06,
	"rope_theta": 10000.0,
	"sliding_window": 4096,
	"torch_dtype": "bfloat16",
	"use_cache": true,
	"vocab_size": 256000
	},
	"eos_token_id": [
	1,
	107
	],
	"initializer_range": 0.02,
	"is_encoder_decoder": true,
	"model_type": "t5gemma",
	"pad_token_id": 0,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.53.0.dev0",
	"use_cache": true
	}

Xet Storage Details

Size:: 4.08 kB
Xet hash:: 43a06455bd714b05fe278f529babda2d85f32e5e1277ba21ada192cfd73be25b

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.