t5-base-samsum-fsl / config.json
gcesare's picture
Upload T5ForConditionalGeneration
e423de2
raw
history blame
2.02 kB
{
"_name_or_path": "t5-base",
"adapters": {
"adapters": {
"samsum": "2e3d1fb61268c5a4"
},
"config_map": {
"2e3d1fb61268c5a4": {
"alpha": 16,
"architecture": "lora",
"attn_matrices": [
"q",
"v"
],
"composition_mode": "add",
"dropout": 0.0,
"init_weights": "lora",
"intermediate_lora": true,
"output_lora": true,
"r": 8,
"selfattn_lora": true,
"use_gating": false
}
},
"fusion_config_map": {},
"fusions": {}
},
"architectures": [
"T5ForConditionalGeneration"
],
"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",
"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,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"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: "
}
},
"torch_dtype": "float32",
"transformers_version": "4.26.1",
"use_cache": true,
"vocab_size": 32128
}