Upload folder using huggingface_hub

config.json

@@ -0,0 +1,125 @@
+{
+  "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
+  "_num_labels": 3,
+  "activation_dropout": 0.1,
+  "activation_function": "relu",
+  "adaptor_activation_function": "gelu",
+  "adaptor_dropout": 0.1,
+  "adaptor_hidden_size": 512,
+  "adaptor_init_std": 0.02,
+  "adaptor_scaling_factor": 1.0,
+  "adaptor_tuning": false,
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "additional_source_wait_k": -1,
+  "alibi_encoding": false,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "asymmetric_alibi_encoding": false,
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "bottleneck_mid_fusion_tokens": 4,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_adaptor_tying_config": null,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "decoder_tying_config": null,
+  "deep_adaptor_tuning": false,
+  "deep_adaptor_tuning_ffn_only": false,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "embed_low_rank_dim": 0,
+  "encoder_adaptor_tying_config": null,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "encoder_tying_config": null,
+  "eos_token_id": 2,
+  "expert_ffn_size": 128,
+  "features_embed_dims": null,
+  "features_vocab_sizes": null,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "gradient_reversal_for_domain_classifier": false,
+  "hypercomplex": false,
+  "hypercomplex_n": 2,
+  "ia3_adaptors": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "initialization_scheme": "static",
+  "inititialization_scheme": "static",
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layernorm_adaptor_input": false,
+  "layernorm_prompt_projection": false,
+  "lora_adaptor_rank": 2,
+  "lora_adaptors": false,
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "mid_fusion_layers": 3,
+  "model_type": "mbart",
+  "moe_adaptors": false,
+  "multi_source": false,
+  "multi_source_method": null,
+  "multilayer_softmaxing": null,
+  "no_embed_norm": false,
+  "no_positional_encoding_decoder": false,
+  "no_positional_encoding_encoder": false,
+  "no_projection_prompt": false,
+  "no_scale_attention_embedding": false,
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_domains_for_domain_classifier": -1,
+  "num_experts": 8,
+  "num_hidden_layers": 12,
+  "num_moe_adaptor_experts": 4,
+  "num_prompts": 100,
+  "num_sparsify_blocks": 8,
+  "output_past": true,
+  "pad_token_id": 1,
+  "parallel_adaptors": false,
+  "positional_encodings": false,
+  "postnorm_decoder": false,
+  "postnorm_encoder": false,
+  "prompt_dropout": 0.1,
+  "prompt_init_std": 0.02,
+  "prompt_projection_hidden_size": 4096,
+  "prompt_tuning": false,
+  "recurrent_projections": 1,
+  "residual_connection_adaptor": false,
+  "residual_connection_prompt": false,
+  "rope_encoding": false,
+  "scale_embedding": true,
+  "softmax_bias_tuning": false,
+  "softmax_temperature": 1.0,
+  "sparsification_temperature": 3.0,
+  "sparsify_attention": false,
+  "sparsify_ffn": false,
+  "static_position_embeddings": false,
+  "target_vocab_size": 0,
+  "temperature_calibration": false,
+  "tokenizer_class": "MBart50Tokenizer",
+  "transformers_version": "4.3.2",
+  "unidirectional_encoder": false,
+  "use_cache": true,
+  "use_moe": false,
+  "use_tanh_activation_prompt": false,
+  "vocab_size": 250054,
+  "wait_k": -1
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154c3030e1c4eb37fbcbba33b9c9afb4880c2d07eefa1039cddd11b9e0e1cd39
+size 2444725607

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"src_lang": null, "tgt_lang": null, "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "bos_token": "<s>", "tokenizer_file": null, "language_codes": "ML50", "special_tokens_map_file": "/home/suraj/projects/mbart-50/mbart-50/special_tokens_map.json", "name_or_path": "facebook/mbart-large-50-many-to-many-mmt", "use_fast": false}