First model version
Browse files- added_tokens.json +0 -3
- config.json +0 -28
- model.safetensors +0 -3
- sentencepiece.bpe.model +0 -3
- special_tokens_map.json +0 -20
- tokenizer.json +0 -0
- tokenizer_config.json +0 -83
added_tokens.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"<unk>NOTUSED": 32005
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
config.json
DELETED
|
@@ -1,28 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "camembert-base",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"CamembertForMaskedLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"bos_token_id": 5,
|
| 8 |
-
"classifier_dropout": null,
|
| 9 |
-
"eos_token_id": 6,
|
| 10 |
-
"hidden_act": "gelu",
|
| 11 |
-
"hidden_dropout_prob": 0.1,
|
| 12 |
-
"hidden_size": 768,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 3072,
|
| 15 |
-
"layer_norm_eps": 1e-05,
|
| 16 |
-
"max_position_embeddings": 514,
|
| 17 |
-
"model_type": "camembert",
|
| 18 |
-
"num_attention_heads": 12,
|
| 19 |
-
"num_hidden_layers": 12,
|
| 20 |
-
"output_past": true,
|
| 21 |
-
"pad_token_id": 1,
|
| 22 |
-
"position_embedding_type": "absolute",
|
| 23 |
-
"torch_dtype": "float32",
|
| 24 |
-
"transformers_version": "4.46.3",
|
| 25 |
-
"type_vocab_size": 1,
|
| 26 |
-
"use_cache": true,
|
| 27 |
-
"vocab_size": 32005
|
| 28 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7ec33e2edeca9c3e2d59609b5b074bfa7d2f8de7757b6de945ea3824c31778c0
|
| 3 |
-
size 442646188
|
|
|
|
|
|
|
|
|
|
|
|
sentencepiece.bpe.model
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
|
| 3 |
-
size 810912
|
|
|
|
|
|
|
|
|
|
|
|
special_tokens_map.json
DELETED
|
@@ -1,20 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<s>NOTUSED",
|
| 4 |
-
"</s>NOTUSED",
|
| 5 |
-
"<unk>NOTUSED"
|
| 6 |
-
],
|
| 7 |
-
"bos_token": "<s>",
|
| 8 |
-
"cls_token": "<s>",
|
| 9 |
-
"eos_token": "</s>",
|
| 10 |
-
"mask_token": {
|
| 11 |
-
"content": "<mask>",
|
| 12 |
-
"lstrip": true,
|
| 13 |
-
"normalized": false,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
},
|
| 17 |
-
"pad_token": "<pad>",
|
| 18 |
-
"sep_token": "</s>",
|
| 19 |
-
"unk_token": "<unk>"
|
| 20 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
DELETED
|
@@ -1,83 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "<s>NOTUSED",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "<pad>",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "</s>NOTUSED",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"4": {
|
| 28 |
-
"content": "<unk>",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"5": {
|
| 36 |
-
"content": "<s>",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
},
|
| 43 |
-
"6": {
|
| 44 |
-
"content": "</s>",
|
| 45 |
-
"lstrip": false,
|
| 46 |
-
"normalized": false,
|
| 47 |
-
"rstrip": false,
|
| 48 |
-
"single_word": false,
|
| 49 |
-
"special": true
|
| 50 |
-
},
|
| 51 |
-
"32004": {
|
| 52 |
-
"content": "<mask>",
|
| 53 |
-
"lstrip": true,
|
| 54 |
-
"normalized": false,
|
| 55 |
-
"rstrip": false,
|
| 56 |
-
"single_word": false,
|
| 57 |
-
"special": true
|
| 58 |
-
},
|
| 59 |
-
"32005": {
|
| 60 |
-
"content": "<unk>NOTUSED",
|
| 61 |
-
"lstrip": false,
|
| 62 |
-
"normalized": false,
|
| 63 |
-
"rstrip": false,
|
| 64 |
-
"single_word": false,
|
| 65 |
-
"special": true
|
| 66 |
-
}
|
| 67 |
-
},
|
| 68 |
-
"additional_special_tokens": [
|
| 69 |
-
"<s>NOTUSED",
|
| 70 |
-
"</s>NOTUSED",
|
| 71 |
-
"<unk>NOTUSED"
|
| 72 |
-
],
|
| 73 |
-
"bos_token": "<s>",
|
| 74 |
-
"clean_up_tokenization_spaces": false,
|
| 75 |
-
"cls_token": "<s>",
|
| 76 |
-
"eos_token": "</s>",
|
| 77 |
-
"mask_token": "<mask>",
|
| 78 |
-
"model_max_length": 512,
|
| 79 |
-
"pad_token": "<pad>",
|
| 80 |
-
"sep_token": "</s>",
|
| 81 |
-
"tokenizer_class": "CamembertTokenizer",
|
| 82 |
-
"unk_token": "<unk>"
|
| 83 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|