[Init] first commit

README.md

@@ -1,3 +1,108 @@
 ---
+language: ja
+tags:
+- ja
+- japanese
+- gpt2
+- text-generation
+- lm
+- nlp
 license: mit
+datasets:
+- cc100
+- wikipedia
+- oscar
+widget:
+- text: "人とAIが協調するためには、"
 ---
+
+# gpt2-large-japanese
+
+This repository provides a large sized Japanese GPT-2 model. The model was trained by [ABEJA, Inc](https://abejainc.com/en/)
+
+# How to use
+
+When using pipeline for text generation.
+
+``` python
+from transformers import pipeline
+
+
+generator = pipeline("text-generation", model="abeja/gpt2-large-japanese")
+generated = generator(
+    "人とAIが協調するためには、",
+    max_length=30,
+    do_sample=True,
+    num_return_sequences=3,
+    top_p=0.95,
+    top_k=50,
+    pad_token_id=3
+)
+print(*generated, sep="\n")
+
+"""
+[out]
+{'generated_text': '人とAIが協調するためには、社会的なルールをきちんと理解して、人と共存し、協働して生きていくのが重要だという。'}
+{'generated_text': '人とAIが協調するためには、それぞれが人間性を持ち、またその人間性から生まれるインタラクションを調整しなければならないことはいうまで'}
+{'generated_text': '人とAIが協調するためには、AIが判断すべきことを人間が決める必要がある。人工知能の目的は、人間の知性、記憶、理解、'}
+"""
+```
+
+When using PyTorch.
+
+``` python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+
+tokenizer = AutoTokenizer.from_pretrained("abeja/gpt2-large-japanese")
+model = AutoModelForCausalLM.from_pretrained("abeja/gpt2-large-japanese")
+
+input_text = "人とAIが協調するためには、"
+input_ids = tokenizer.encode(input_text, return_tensors="pt")
+
+gen_tokens = model.generate(
+    input_ids,
+    max_length=100,
+    do_sample=True,
+    num_return_sequences=3,
+    top_p=0.95,
+    top_k=50,
+    pad_token_id=tokenizer.pad_token_id
+)
+for gen_text in tokenizer.batch_decode(gen_tokens, skip_special_tokens=True):
+    print(gen_text)
+```
+
+When using TensorFlow.
+
+```python
+from transformers import AutoTokenizer, TFAutoModelForCausalLM
+
+
+tokenizer = AutoTokenizer.from_pretrained("abeja/gpt2-large-japanese")
+model = TFAutoModelForCausalLM.from_pretrained("abeja/gpt2-large-japanese", from_pt=True)
+
+input_text = "人とAIが協調するためには、"
+input_ids = tokenizer.encode(input_text, return_tensors="tf")
+
+gen_tokens = model.generate(
+    input_ids,
+    max_length=100,
+    do_sample=True,
+    num_return_sequences=3,
+    top_p=0.95,
+    top_k=50,
+    pad_token_id=tokenizer.pad_token_id
+)
+for gen_text in tokenizer.batch_decode(gen_tokens, skip_special_tokens=True):
+    print(gen_text)
+```
+
+# Dataset
+The model was trained on [Japanese CC-100](http://data.statmt.org/cc-100/ja.txt.xz), [Japanese Wikipedia](https://dumps.wikimedia.org/other/cirrussearch), and [Japanese OSCAR](https://huggingface.co/datasets/oscar).
+
+# Tokenization
+The model uses a [sentencepiece](https://github.com/google/sentencepiece)-based tokenizer, the vocabulary was trained on the Japanese Wikipedia.
+
+# Licenese
+[The MIT license](https://opensource.org/licenses/MIT)

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "checkpoint-huggingface/gpt2-large-japanese",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb5575dce810c32790f2806f28d1813627a7d55d6df6e378ab15b313c0365481
+size 3040548553

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebbc2b0963521ffc640f69782e4e27c7209b1a6fff8f8d3083f599f8cfe2abb
+size 783792

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350e954b93459963bc2c0ea333cfa8b1b2bd3e72cb74688561763c654764b26a
+size 3003153768

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "[PAD]", "extra_ids": 0, "additional_special_tokens": [], "sp_model_kwargs": {}, "bos_token": "<s>", "cls_token": "[CLS]", "sep_token": "[SEP]", "mask_token": "[MASK]", "do_lower_case": true, "tokenizer_class": "T5Tokenizer"}