tritiumoxide's picture
should make this repo work with candle
5171663
raw
history blame contribute delete
805 Bytes
{
"architectures": [
"T5ForConditionalGeneration"
],
"classifier_dropout": 0.0,
"d_ff": 8192,
"d_kv": 128,
"d_model": 2048,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 2,
"feed_forward_proj": "gated-gelu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"n_positions": 512,
"num_decoder_layers": 48,
"num_heads": 16,
"num_layers": 48,
"output_past": true,
"pad_token_id": 1,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"task_specific_params": {},
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.35.0",
"use_cache": true,
"vocab_size": 256000
}