trl-internal-testing/tiny-T5ForConditionalGeneration

1{2  "architectures": [3    "T5ForConditionalGeneration"4  ],5  "classifier_dropout": 0.0,6  "d_ff": 1024,7  "d_kv": 64,8  "d_model": 24,9  "decoder_start_token_id": 0,10  "dense_act_fn": "gelu_new",11  "dropout_rate": 0.1,12  "dtype": "float32",13  "eos_token_id": 1,14  "feed_forward_proj": "gated-gelu",15  "initializer_factor": 1.0,16  "is_encoder_decoder": true,17  "is_gated_act": true,18  "layer_norm_epsilon": 1e-06,19  "model_type": "t5",20  "n_positions": 512,21  "num_decoder_layers": 8,22  "num_heads": 6,23  "num_layers": 8,24  "output_past": true,25  "pad_token_id": 0,26  "relative_attention_max_distance": 128,27  "relative_attention_num_buckets": 32,28  "task_specific_params": {29    "summarization": {30      "early_stopping": true,31      "length_penalty": 2.0,32      "max_length": 200,33      "min_length": 30,34      "no_repeat_ngram_size": 3,35      "num_beams": 4,36      "prefix": "summarize: "37    },38    "translation_en_to_de": {39      "early_stopping": true,40      "max_length": 300,41      "num_beams": 4,42      "prefix": "translate English to German: "43    },44    "translation_en_to_fr": {45      "early_stopping": true,46      "max_length": 300,47      "num_beams": 4,48      "prefix": "translate English to French: "49    },50    "translation_en_to_ro": {51      "early_stopping": true,52      "max_length": 300,53      "num_beams": 4,54      "prefix": "translate English to Romanian: "55    }56  },57  "tie_word_embeddings": false,58  "transformers_version": "4.57.3",59  "use_cache": true,60  "vocab_size": 3212861}62