Update config.json

config.json

@@ -0,0 +1,81 @@
+{
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "torchscript": false,
+    "use_bfloat16": false,
+    "pruned_heads": {},
+    "is_encoder_decoder": true,
+    "is_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "num_return_sequences": 1,
+    "architectures": [
+        "T5WithLMHeadModel"
+    ],
+    "finetuning_task": null,
+    "_num_labels": 2,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "prefix": null,
+    "bos_token_id": null,
+    "pad_token_id": 0,
+    "eos_token_id": 1,
+    "decoder_start_token_id": 0,
+    "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: "
+        }
+    },
+    "model_type": "t5",
+    "vocab_size": 32128,
+    "n_positions": 512,
+    "d_model": 768,
+    "d_kv": 64,
+    "d_ff": 3072,
+    "num_layers": 12,
+    "num_heads": 12,
+    "relative_attention_num_buckets": 32,
+    "dropout_rate": 0.1,
+    "layer_norm_epsilon": 1e-06,
+    "initializer_factor": 1.0
+}