Model saved in epoch 1

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "twigs/bigbird-pegasus-large",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "BigBirdPegasusForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 2,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 16,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 16,
+  "eos_token_id": 1,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 4096,
+  "model_type": "bigbird_pegasus",
+  "num_hidden_layers": 16,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.26.1",
+  "use_bias": false,
+  "use_cache": true,
+  "vocab_size": 96103
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d01507de5e9a89c4eebb0323b18aff43c8d706d2e96675a01786663d8847cc
+size 1154136109