初始化项目，由ModelHub XC社区提供模型

Model: line-corporation/japanese-large-lm-1.7b
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+datasets:
+- wikipedia
+- mc4
+- cc100
+- oscar
+language:
+- ja
+---
+
+# japanese-large-lm-1.7b
+
+This repository provides a 1.7B parameters Japanese language model, trained by [LINE Corporation](https://linecorp.com/ja/).
+
+[Tech Blog](https://engineering.linecorp.com/ja/blog/3.6-billion-parameter-japanese-language-model) explains details.
+
+## How to use
+
+```
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, set_seed
+ 
+model = AutoModelForCausalLM.from_pretrained("line-corporation/japanese-large-lm-1.7b", torch_dtype=torch.float16)
+tokenizer = AutoTokenizer.from_pretrained("line-corporation/japanese-large-lm-1.7b", use_fast=False)
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)
+set_seed(101)
+ 
+text = generator(
+    "おはようございます、今日の天気は",
+    max_length=30,
+    do_sample=True,
+    pad_token_id=tokenizer.pad_token_id,
+    num_return_sequences=5,
+)
+
+for t in text:
+  print(t)
+
+# [{'generated_text': 'おはようございます、今日の天気は雨模様ですね。梅雨のこの時期の ジメジメ、ムシムシはたまらないですねえ~。 皆さんもお'},
+#  {'generated_text': 'おはようございます、今日の天気は快晴。 そして、朝8時15分には、 8月9日現在の、 月島・勝どき・'},
+#  {'generated_text': 'おはようございます、今日の天気は曇りです。 朝起きたら雪がチラついていました。 日中も雪が舞い散るような天気です。 朝から寒いですね。'},
+#  {'generated_text': 'おはようございます、今日の天気は雨です。昨日、天気が悪く洗濯物を干しにベランダに出た時に雨に降られ、風邪が悪化しそうです。今日洗濯'},
+#  {'generated_text': 'おはようございます、今日の天気は晴天ですが涼しい1日です、気温は午後になり 若干下がる予報です。 6月も10日を'}]
+```
+
+## Model architecture
+| Model | Vocab size | Architecture | Position type | Layers | Hidden dim | Attention heads |
+| :---: | :--------: | :----------- | :-----------: | :----: | :--------: | :-------------: |
+| 1.7B  | 51200      | GPT2         | Absolute      | 24     | 2304       | 24 |
+| 3.6B  | 51200      | GPTNeoX      | RoPE          | 30     | 3072       | 32 |
+
+## Training Corpus
+Our training corpus consists of the Japanese portions of publicly available corpus such as C4, CC-100, and Oscar.
+We also incorporated the Web texts crawled by in-house system.
+The total size of our training corpus is about 650 GB.
+The trained model achieves 8.57 perplexity on the internal validation sets of Japanese C4.
+
+## Tokenization
+We use a sentencepiece tokenizer with a unigram language model and byte-fallback.
+We **do not** apply pre-tokenization with Japanese tokenizer.
+Thus, a user may directly feed raw sentences into the tokenizer.
+
+
+## License
+[Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0)

config.json

@@ -0,0 +1 @@
+{"vocab_size": 51200, "n_positions": 2048, "n_embd": 2304, "n_layer": 24, "n_head": 24, "n_inner": 9216, "activation_function": "gelu", "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 1, "eos_token_id": 2, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["GPT2LMHeadModel"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.28.1", "n_ctx": 2048, "gradient_checkpointing": false, "model_type": "gpt2"}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117a987678e808ebcd6b10b06752230f185bf229e76c56968ec8fccf9fc19310
+size 3505823472

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff64e459c67a9f02e7428704530f2ace343360047ad36bc036033c0e14a14ad
+size 3505891417

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c5c56a739832923347681ed8a03a9cbf5afb6d1fe60089a5b01dd2dd063ab71
+size 1208648

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+    "extra_ids": 0,
+    "do_lower_case": false,
+    "keep_accents": true,
+    "bos_token": "<s>",
+    "eos_token": "</s>",
+    "unk_token": "<unk>",
+    "pad_token": "<pad>",
+    "mask_token": "<mask>",
+    "cls_token": "<cls>",
+    "sep_token": "<sep>",
+    "sp_model_kwargs": {},
+    "special_tokens_map_file": null,
+    "tokenizer_class": "T5Tokenizer"
+}