diff --git a/config.json b/config.json new file mode 100644 index 0000000..4b69929 --- /dev/null +++ b/config.json @@ -0,0 +1,37 @@ +{ + "_name_or_path": "./camembert-base-xnli", + "architectures": [ + "CamembertForSequenceClassification" + ], + "attention_probs_dropout_prob": 0.1, + "bos_token_id": 5, + "eos_token_id": 6, + "gradient_checkpointing": false, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 768, + "id2label": { + "0": "entailment", + "1": "neutral", + "2": "contradiction" + }, + "initializer_range": 0.02, + "intermediate_size": 3072, + "label2id": { + "entailment": 0, + "neutral": 1, + "contradiction": 2 + }, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 514, + "model_type": "camembert", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "output_past": true, + "pad_token_id": 1, + "position_embedding_type": "absolute", + "transformers_version": "4.4.2", + "type_vocab_size": 1, + "use_cache": true, + "vocab_size": 32005 +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..35df255 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dfc8751d4d3770210bca130bf5df5c6f298ff091e70df744def057db229d1d7 +size 442587593 diff --git a/sentencepiece.bpe.model b/sentencepiece.bpe.model new file mode 100644 index 0000000..489f0a5 --- /dev/null +++ b/sentencepiece.bpe.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314 +size 810912 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..7591c62 --- /dev/null +++ b/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": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]} \ No newline at end of file diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b267a7e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1 @@ +{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "camembert-base"} \ No newline at end of file