Add lilt-camembertv2-base

README

@@ -0,0 +1,34 @@
+# lilt-camembertv2-base
+
+This repository contains **lilt-camembertv2-base** weights exported to `safetensors` format.
+
+## Source
+
+- **Layout encoder**: [`jpwang/lilt-only-base`](https://github.com/jpwang/lilt) — layout-only pretrained checkpoint
+- **Text encoder**: [`almanach/camembertv2-base`](https://huggingface.co/almanach/camembertv2-base) — French language model
+
+## Methodology
+
+Produced by **weight merging** following the official [`gen_weight_roberta_like.py`](https://github.com/jpwang/lilt) procedure. No training or fine-tuning was performed.
+
+Intended as a starting point for downstream fine-tuning on French document understanding tasks (NER, token classification, extractive QA…).
+
+## Files
+
+| File | Description |
+|------|-------------|
+| `model.safetensors` | Model weights |
+| `pytorch_model.bin` | Model weights (PyTorch format) |
+| `config.json` | Model configuration |
+| `tokenizer_config.json` | Tokenizer configuration |
+| `tokenizer.json` | Tokenizer (fast) |
+
+## License
+
+Weights are derived from models released under MIT and Apache-2.0 licenses.
+
+## Acknowledgements
+
+- [LiLT: A Simple yet Effective Language-Independent Layout Transformer](https://arxiv.org/abs/2202.13669) — Wang et al., 2022
+
+> **Note**: This is not an official release from any of the above organizations.

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "camembertv2-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "channel_shrink_ratio": 4,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 1025,
+  "model_name": "camembertv2-base",
+  "model_type": "liltrobertalike",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_biased_input": true,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32768
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c38ecfe3e353478273ace8516e09b2cbb2152ca371aeac49394aa98d739ecd1
+size 468533144

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c85b4decc50d767133b94ca54a3d1f9cf688b3dead631fcc1fe88d381186ad
+size 471118579

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "single_word": false,
+    "lstrip": false,
+    "rstrip": false,
+    "normalized": true
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "single_word": false,
+    "lstrip": true,
+    "rstrip": false,
+    "normalized": true
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "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": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "errors": "replace",
+  "mask_token": "[MASK]",
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "trim_offsets": true,
+  "unk_token": "[UNK]"
+}