| { |
| "_name_or_path": "t5-large", |
| "architectures": [ |
| "T5ForConditionalGeneration" |
| ], |
| "d_ff": 4096, |
| "d_kv": 64, |
| "d_model": 1024, |
| "decoder_start_token_id": 0, |
| "dense_act_fn": "relu", |
| "dropout_rate": 0.1, |
| "eos_token_id": 1, |
| "feed_forward_proj": "relu", |
| "finetuing_config": { |
| "batch_size": 32, |
| "data": "relbert/semeval2012_relational_similarity", |
| "epoch": 3, |
| "gradient_accumulation_steps": 1, |
| "learning_rate": 0.0001, |
| "model": "t5-large", |
| "random_seed": 42, |
| "task_prefix": "generate analogy:", |
| "template_footer": "<subj-b> is to <obj-b>", |
| "template_header": "<subj-a> is to <obj-a>" |
| }, |
| "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": 24, |
| "num_heads": 16, |
| "num_layers": 24, |
| "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 |
| } |
|
|
