first commit

README.md

@@ -0,0 +1,109 @@
+---
+license: cc-by-sa-4.0
+language:
+  - en
+  - ja
+programming_language:
+  - C
+  - C++
+  - C#
+  - Go
+  - Java
+  - JavaScript
+  - Lua
+  - PHP
+  - Python
+  - Ruby
+  - Rust
+  - Scala
+  - TypeScript
+library_name: transformers
+tags:
+  - deberta
+  - deberta-v3
+  - fill-mask
+datasets:
+  - wikipedia
+  - EleutherAI/pile
+  - bigcode/the-stack
+  - mc4
+metrics:
+  - accuracy
+mask_token: "[MASK]"
+widget:
+    - text: "京都大学で自然言語処理を[MASK]する。"
+---
+
+# Model Card for Japanese DeBERTa V2 base
+
+## Model description
+
+This is a Japanese DeBERTa V3 base model pre-trained on LLM-jp corpus v1.0.
+
+## How to use
+
+You can use this model for masked language modeling as follows:
+
+```python
+from transformers import AutoTokenizer, AutoModelForMaskedLM
+tokenizer = AutoTokenizer.from_pretrained('ku-nlp/deberta-v2-base-japanese')
+model = AutoModelForMaskedLM.from_pretrained('ku-nlp/deberta-v2-base-japanese')
+
+sentences = [
+    "京都大学で自然言語処理を[MASK]する。",
+    "I [MASK] NLP at Kyoto University.",
+    'int main() { printf("Hello, [MASK]!"); return 0; }',
+]
+encodings = tokenizer(sentences, return_tensors='pt')
+...
+```
+
+You can also fine-tune this model on downstream tasks.
+
+## Tokenization
+
+The tokenizer of this model is based on [huggingface/tokenizers](https://github.com/huggingface/tokenizers) Unigram byte-fallback model.
+The vocabulary entries were converted from [`llm-jp-tokenizer v2.2 (100k)`](https://github.com/llm-jp/llm-jp-tokenizer/releases/tag/v2.2).
+Please refer to [README.md](https://github.com/llm-jp/llm-jp-tokenizer) of `llm-jp/llm-ja-tokenizer` for details on the vocabulary construction procedure.
+
+Note that unlike [ku-nlp/deberta-v2-base-japanese](https://huggingface.co/ku-nlp/deberta-v2-base-japanese), pre-segmentation by a morphological analyzer (e.g., Juman++) is no longer required for this model.
+
+## Training data
+
+We used the [LLM-jp corpus](https://github.com/llm-jp/llm-jp-corpus) v1.0.1 for pre-training.
+The corpus consists of the following corpora:
+
+- Japanese
+  - Wikipedia (1B tokens)
+  - mC4 (129B tokens)
+- English
+  - Wikipedia (4B tokens)
+  - The Pile (126B tokens)
+- Code
+  - The Stack (10B tokens)
+
+We shuffled the corpora, which has 270B tokens in total, and trained the model for 2 epochs.
+Thus, the total number of tokens fed to the model was 540B.
+
+## Training procedure
+
+We slightly modified [the official implementation of DeBERTa V3](https://github.com/microsoft/DeBERTa) and followed the official training procedure.
+The modified code is available at [nobu-g/DeBERTa](https://github.com/nobu-g/DeBERTa).
+
+The following hyperparameters were used during pre-training:
+
+- learning_rate: 1e-4
+- per_device_train_batch_size: 800
+- num_devices: 8
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 2400
+- max_seq_length: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
+- lr_scheduler_type: linear schedule with warmup
+- training_steps: 475,000
+- warmup_steps: 10,000
+
+## Acknowledgments
+
+This work was supported by Joint Usage/Research Center for Interdisciplinary Large-scale Information Infrastructures (JHPCN) through General Collaboration Project no. jh221004, "Developing a Platform for Constructing and Sharing of Large-Scale Japanese Language Models".
+For training models, we used the mdx: a platform for the data-driven future.

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 96871,
+  "[MASK]": 96867,
+  "[PAD]": 96869,
+  "[SEP]": 96868,
+  "[UNK]": 96870
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "norm_rel_ebd": "layer_norm",
+  "model_type": "deberta-v2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 0,
+  "vocab_size": 96900
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe7489b46b879cee9f6d35ec6d6a13f15e49f7e1cb41ee5cfa8e45501259e44
+size 471366482

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fefde905766244f5e613a490d6e35236043d6483c4aae0eaac4b4a8fc365a88
+size 1658609

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "96867": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96868": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96869": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96870": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96871": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]"
+}