add model sentence-flaubert-base

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -1,3 +1,8 @@
 ---
-license: mit
----
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+

config.json

@@ -0,0 +1,80 @@
+{
+  "_name_or_path": "/home/nhut/.cache/torch/sentence_transformers/inokufu_flaubert-base-uncased-xnli-sts/",
+  "amp": 1,
+  "architectures": [
+    "FlaubertModel"
+  ],
+  "asm": false,
+  "attention_dropout": 0.1,
+  "bos_index": 0,
+  "bos_token_id": 0,
+  "bptt": 512,
+  "causal": false,
+  "clip_grad_norm": 5,
+  "dropout": 0.1,
+  "emb_dim": 768,
+  "embed_init_std": 0.02209708691207961,
+  "encoder_only": true,
+  "end_n_top": 5,
+  "eos_index": 1,
+  "fp16": true,
+  "gelu_activation": true,
+  "group_by_size": true,
+  "id2lang": {
+    "0": "fr"
+  },
+  "init_std": 0.02,
+  "is_encoder": true,
+  "lang2id": {
+    "fr": 0
+  },
+  "lang_id": 0,
+  "langs": [
+    "fr"
+  ],
+  "layer_norm_eps": 1e-12,
+  "layerdrop": 0.0,
+  "lg_sampling_factor": -1,
+  "lgs": "fr",
+  "mask_index": 5,
+  "mask_token_id": 0,
+  "max_batch_size": 0,
+  "max_position_embeddings": 512,
+  "max_vocab": -1,
+  "mlm_steps": [
+    [
+      "fr",
+      null
+    ]
+  ],
+  "model_type": "flaubert",
+  "n_heads": 12,
+  "n_langs": 1,
+  "n_layers": 12,
+  "pad_index": 2,
+  "pad_token_id": 2,
+  "pre_norm": false,
+  "sample_alpha": 0,
+  "share_inout_emb": true,
+  "sinusoidal_embeddings": false,
+  "start_n_top": 5,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "tokens_per_batch": -1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "unk_index": 3,
+  "use_lang_emb": true,
+  "vocab_size": 67542,
+  "word_blank": 0,
+  "word_dropout": 0,
+  "word_keep": 0.1,
+  "word_mask": 0.8,
+  "word_mask_keep_rand": "0.8,0.1,0.1",
+  "word_pred": 0.15,
+  "word_rand": 0.1,
+  "word_shuffle": 0
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.1.0",
+    "transformers": "4.11.3",
+    "pytorch": "1.9.0+cu102"
+  }
+}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d457176b68bf773fa5260c22dfb1b8f72a0fef662b072dba891705942ad4166
+size 549347869

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<special0>",
+    "<special1>",
+    "<special2>",
+    "<special3>",
+    "<special4>",
+    "<special5>",
+    "<special6>",
+    "<special7>",
+    "<special8>",
+    "<special9>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "</s>",
+  "mask_token": "<special1>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,140 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<special0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<special1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<special2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<special3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<special4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<special5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<special6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<special7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<special8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<special9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<special0>",
+    "<special1>",
+    "<special2>",
+    "<special3>",
+    "<special4>",
+    "<special5>",
+    "<special6>",
+    "<special7>",
+    "<special8>",
+    "<special9>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "</s>",
+  "do_lower_case": false,
+  "id2lang": null,
+  "lang2id": null,
+  "mask_token": "<special1>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "FlaubertTokenizer",
+  "unk_token": "<unk>"
+}