First model version push
Browse files- config.json +15 -21
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +20 -0
config.json
CHANGED
|
@@ -1,35 +1,29 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 7 |
"classifier_dropout": null,
|
| 8 |
-
"
|
|
|
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
| 12 |
-
"id2label": {
|
| 13 |
-
"0": "NEGATIVE",
|
| 14 |
-
"1": "POSITIVE"
|
| 15 |
-
},
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
"intermediate_size": 3072,
|
| 18 |
-
"
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
"layer_norm_eps": 1e-12,
|
| 23 |
-
"max_position_embeddings": 512,
|
| 24 |
-
"model_type": "bert",
|
| 25 |
"num_attention_heads": 12,
|
| 26 |
"num_hidden_layers": 12,
|
| 27 |
-
"
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"type_vocab_size": 2,
|
| 33 |
"use_cache": true,
|
| 34 |
-
"vocab_size":
|
| 35 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
"architectures": [
|
| 4 |
+
"CamembertForMaskedLM"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 5,
|
| 8 |
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 6,
|
| 11 |
"hidden_act": "gelu",
|
| 12 |
"hidden_dropout_prob": 0.1,
|
| 13 |
"hidden_size": 768,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"initializer_range": 0.02,
|
| 15 |
"intermediate_size": 3072,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "camembert",
|
|
|
|
|
|
|
|
|
|
| 20 |
"num_attention_heads": 12,
|
| 21 |
"num_hidden_layers": 12,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 1,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"transformers_version": "5.22.1",
|
| 26 |
+
"type_vocab_size": 1,
|
|
|
|
| 27 |
"use_cache": true,
|
| 28 |
+
"vocab_size": 32005
|
| 29 |
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2785d2e45752c5c93021cd3277207734dee67409ca1c6c98da4f6b9d709a5cec
|
| 3 |
+
size 442646188
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"extra_special_tokens": [
|
| 8 |
+
"<s>NOTUSED",
|
| 9 |
+
"</s>NOTUSED",
|
| 10 |
+
"<unk>NOTUSED"
|
| 11 |
+
],
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"mask_token": "<mask>",
|
| 15 |
+
"model_max_length": 512,
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"tokenizer_class": "CamembertTokenizer",
|
| 19 |
+
"unk_token": "<unk>"
|
| 20 |
+
}
|