t5_3B_fp16_untuned / config.json
tlkh's picture
Initial commit
087ec19
{
"_name_or_path": "t5-3b",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 16384,
"d_kv": 128,
"d_model": 1024,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "relu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"n_positions": 512,
"num_decoder_layers": 24,
"num_heads": 32,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"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": "float16",
"transformers_version": "4.11.3",
"use_cache": true,
"vocab_size": 32128
}