InstructCell-chat / config.json
ZJU-Fangyin
First model version
0a2321d
raw
history blame
1.83 kB
{
"_name_or_path": "../t5-base",
"architectures": [
"T5ForConditionalGeneration"
],
"classifier_dropout": 0.0,
"d_ff": 3072,
"d_kv": 64,
"d_model": 768,
"decoder_start_token_id": 0,
"dense_act_fn": "relu",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "relu",
"ignore_index": -100,
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": false,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"n_positions": 512,
"num_decoder_layers": 12,
"num_heads": 12,
"num_layers": 12,
"num_signal_tokens": 1,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"special_tokens_dict": {
"end_tag": "</CELL>",
"placeholder": "<CELL0>",
"signal_tokens": [
"<CELL1>"
],
"start_tag": "<CELL>"
},
"special_tokens_index_dict": {
"end_tag": 32101,
"first_signal_token": 32103,
"placeholder": 32102,
"start_tag": 32100
},
"task_specific_params": {
"summarization": {
"early_stopping": true,
"length_penalty": 2.0,
"max_length": 200,
"min_length": 30,
"no_repeat_ngram_size": 3,
"num_beams": 4,
"prefix": "summarize: "
},
"translation_en_to_de": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to German: "
},
"translation_en_to_fr": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to French: "
},
"translation_en_to_ro": {
"early_stopping": true,
"max_length": 300,
"num_beams": 4,
"prefix": "translate English to Romanian: "
}
},
"transformers_version": "4.33.3",
"use_cache": true,
"vocab_size": 32112
}