Upload folder using huggingface_hub

README.md

@@ -0,0 +1,46 @@
+---
+license: apache-2.0
+language:
+- fr
+library_name: transformers
+inference: false
+---
+# CamemBERT-L8
+
+This model is a pruned version of the pre-trained [CamemBERT](https://huggingface.co/camembert-base) checkpoint, obtained by [dropping the top-layers](https://arxiv.org/abs/2004.03844) from the original model.
+
+![](illustration.jpeg)
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModel
+
+tokenizer = AutoTokenizer.from_pretrained('antoinelouis/camembert-L8')
+model = AutoModel.from_pretrained('antoinelouis/camembert-L8')
+```
+
+## Comparison
+
+| Model                                                              | #Params |  Size | Pruning |
+|--------------------------------------------------------------------|:-------:|:-----:|:-------:|
+| [CamemBERT](https://huggingface.co/camembert-base)                 |  110.6M | 445MB |    -    |
+|                                                                    |         |       |         |
+| [CamemBERT-L10](https://huggingface.co/antoinelouis/camembert-L10) |  96.4M  | 368MB |   -13%  |
+| **CamemBERT-L8**                                                   |  82.3M  | 314MB |   -26%  |
+| [CamemBERT-L6](https://huggingface.co/antoinelouis/camembert-L6)   |  68.1M  | 260MB |   -38%  |
+| [CamemBERT-L4](https://huggingface.co/antoinelouis/camembert-L4)   |  53.9M  | 206MB |   -51%  |
+| [CamemBERT-L2](https://huggingface.co/antoinelouis/camembert-L2)   |  39.7M  | 159MB |   -64%  |
+
+## Citation
+
+```bibtex
+@online{louis2023,
+   author    = 'Antoine Louis',
+   title     = 'CamemBERT-L8: A Pruned Version of CamemBERT',
+   publisher = 'Hugging Face',
+   month     = 'october',
+   year      = '2023',
+   url       = 'https://huggingface.co/antoinelouis/camembert-L8',
+}
+```

added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "</s>": 6,
+  "</s>NOTUSED": 2,
+  "<mask>": 32004,
+  "<pad>": 1,
+  "<s>": 5,
+  "<s>NOTUSED": 0,
+  "<unk>": 4
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "camembert-base",
+  "architectures": [
+    "CamembertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 8,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d7ff51d7b47ee5aec30392db4f5436f9e0992679ffda0548f0f42291ebd082
+size 329125542

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
+size 810912

special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}