Upload MBartForConditionalGeneration

config.json

@@ -1,29 +1,34 @@
 {
-  "_name_or_path": "/content/drive/My Drive/your_englishSumm",
+  "_name_or_path": "/content/drive/My Drive/your_model_directory1",
   "activation_dropout": 0.1,
-  "activation_function": "relu",
+  "activation_function": "gelu",
   "add_bias_logits": false,
   "add_final_layer_norm": true,
   "architectures": [
-    "PegasusForConditionalGeneration"
+    "MBartForConditionalGeneration"
   ],
   "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 16,
-  "decoder_start_token_id": 0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "do_blenderbot_90_layernorm": false,
   "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 16,
-  "eos_token_id": 1,
-  "extra_pos_embeddings": 1,
-  "forced_eos_token_id": 1,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -36,20 +41,19 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "length_penalty": 0.8,
-  "max_length": 128,
   "max_position_embeddings": 1024,
-  "min_length": 32,
-  "model_type": "pegasus",
+  "model_type": "mbart",
+  "no_repeat_ngram_size": 3,
   "normalize_before": true,
-  "normalize_embedding": false,
-  "num_beams": 8,
-  "num_hidden_layers": 16,
-  "pad_token_id": 0,
-  "scale_embedding": true,
-  "static_position_embeddings": true,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "tokenizer_class": "BarthezTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.40.0",
   "use_cache": true,
-  "vocab_size": 96103
+  "vocab_size": 50002
 }

generation_config.json

@@ -1,13 +1,11 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 0,
-  "decoder_start_token_id": 0,
-  "eos_token_id": 1,
-  "forced_eos_token_id": 1,
-  "length_penalty": 0.8,
-  "max_length": 128,
-  "min_length": 32,
-  "num_beams": 8,
-  "pad_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
   "transformers_version": "4.40.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93ac05e1ed0fa5f4730e090b9c23d48b23e19d427a0330ccad3d97c36c2b39b
-size 2283652852
+oid sha256:2a0d8209e8070bb0651c9271682d4f7bc1e38f571d4518113ad33146adfae8dc
+size 557116312