Init commit

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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 +1,49 @@
+---
+license: apache-2.0
+inference: false
+language: ja
+---
+
+# japanese-large-lm-1.7b-instruction-sft
+
+This repository provides a 1.7B parameters Japanese language model, fine-tuned and trained by [LINE Corporation](https://linecorp.com/ja/).
+
+## For Japanese
+
+詳細な説明や実験に関しては「[Instruction Tuningにより対話性能を向上させた3.6B日本語言語モデルを公開します](https://engineering.linecorp.com/ja/blog/3.6b-japanese-language-model-with-improved-dialog-performance-by-instruction-tuning)」をご覧ください。
+
+## How to use
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+ 
+model = AutoModelForCausalLM.from_pretrained("line-corporation/japanese-large-lm-1.7b-instruction-sft")
+tokenizer = AutoTokenizer.from_pretrained("line-corporation/japanese-large-lm-1.7b-instruction-sft", use_fast=False)
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)
+ 
+input_text = """四国の県名を全て列挙してください。"""
+text = generator(
+    f"ユーザー: {input_text}\nシステム: ",
+    max_length = 256,
+    do_sample = True,
+    temperature = 0.7,
+    top_p = 0.9,
+    top_k = 0,
+    repetition_penalty = 1.1,
+    num_beams = 1,
+    pad_token_id = tokenizer.pad_token_id,
+    num_return_sequences = 1,
+)
+print(text)
+# [{'generated_text': 'ユーザー: 四国の県名を全て列挙してください。\nシステム:  香川県、徳島県、愛媛県、高知県'}]
+```
+
+## 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 +1,35 @@
+{
+  "_name_or_path": "/vsfs/deepspeed_chat/base-models/line-gpt-japanese",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "end_token_id": 2,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 2304,
+  "n_head": 24,
+  "n_inner": 9216,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0bbad9b9889642b61619154dd0a16696b45a45f9e7226e4b630d7f1f1c1e43c
+size 3304513471

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

spiece.model

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

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "additional_special_tokens": null,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "keep_accents": true,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}