初始化项目，由ModelHub XC社区提供模型
Model: stockmark/gpt-neox-japanese-1.4b Source: Original Platform
This commit is contained in:
ModelHub XC
47
.gitattributes
vendored
Normal file
47
.gitattributes
vendored
Normal file
@@ -0,0 +1,47 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
67
README.md
Normal file
67
README.md
Normal file
@@ -0,0 +1,67 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- ja
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- gpt_neox
|
||||
- gpt-neox
|
||||
- japanese
|
||||
inference:
|
||||
parameters:
|
||||
max_new_tokens: 32
|
||||
do_sample: false
|
||||
repetition_penalty: 1.1
|
||||
---
|
||||
|
||||
# stockmark/gpt-neox-japanese-1.4b
|
||||
|
||||
This repository provides a GPT-NeoX based model with 1.4B parameters pre-trained on Japanese corpus of about 20B tokens. This model is developed by [Stockmark Inc.](https://stockmark.co.jp/)
|
||||
|
||||
## How to use
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
# Use torch.bfloat16 for A100 GPU and torch.flaot16 for the older generation GPUs
|
||||
torch_dtype = torch.bfloat16 if torch.cuda.is_available() and hasattr(torch.cuda, "is_bf16_supported") and torch.cuda.is_bf16_supported() else torch.float16
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("stockmark/gpt-neox-japanese-1.4b", device_map="auto", torch_dtype=torch_dtype)
|
||||
tokenizer = AutoTokenizer.from_pretrained("stockmark/gpt-neox-japanese-1.4b")
|
||||
|
||||
inputs = tokenizer("自然言語処理は", return_tensors="pt").to(model.device)
|
||||
with torch.no_grad():
|
||||
tokens = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=128,
|
||||
repetition_penalty=1.1
|
||||
)
|
||||
|
||||
output = tokenizer.decode(tokens[0], skip_special_tokens=True)
|
||||
print(output)
|
||||
```
|
||||
|
||||
## Example:
|
||||
|
||||
- LoRA tuning: https://huggingface.co/stockmark/gpt-neox-japanese-1.4b/blob/main/notebooks/LoRA.ipynb
|
||||
|
||||
## Training dataset
|
||||
- Japanese Web Corpus (ja): 8.6B tokens (This dataset will not be released.)
|
||||
- Wikipedia (ja): 0.88B tokens
|
||||
- CC100 (ja): 10.5B tokens
|
||||
|
||||
## Training setting
|
||||
- Trained using HuggingFace Trainer and DeepSpeed (ZeRO-2)
|
||||
- 8 A100 GPUs (40GB) at ABCI
|
||||
- Mixed Precision (BF16)
|
||||
|
||||
## License
|
||||
[The MIT license](https://opensource.org/licenses/MIT)
|
||||
|
||||
## Developed by
|
||||
[Stockmark Inc.](https://stockmark.co.jp/)
|
||||
|
||||
## Author
|
||||
[Takahiro Omi](https://huggingface.co/omitakahiro)
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"architectures": [
|
||||
"GPTNeoXForCausalLM"
|
||||
],
|
||||
"bos_token_id": 0,
|
||||
"classifier_dropout": 0.1,
|
||||
"eos_token_id": 0,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 1024,
|
||||
"model_type": "gpt_neox",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 24,
|
||||
"pad_token_id": 1,
|
||||
"rotary_emb_base": 10000,
|
||||
"rotary_pct": 0.25,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.30.2",
|
||||
"use_cache": true,
|
||||
"use_parallel_residual": false,
|
||||
"vocab_size": 50000
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"pad_token_id": 1,
|
||||
"transformers_version": "4.30.2"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2ce45432f8538cee7b698f847dcb7f31cea2e27d0322bcf2fa7bf12796246baf
|
||||
size 2852015168
|
||||
253
notebooks/LoRA.ipynb
Normal file
253
notebooks/LoRA.ipynb
Normal file
@@ -0,0 +1,253 @@
|
||||
{
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 0,
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"provenance": [],
|
||||
"gpuType": "T4"
|
||||
},
|
||||
"kernelspec": {
|
||||
"name": "python3",
|
||||
"display_name": "Python 3"
|
||||
},
|
||||
"language_info": {
|
||||
"name": "python"
|
||||
},
|
||||
"accelerator": "GPU"
|
||||
},
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"このnotebookは`stockmark/gpt-neox-japanese-1.4b`のモデルを`kunishou/databricks-dolly-15k-ja`のデータセットを用いてLoRA tuningするためのコードの例です。以下の例では、学習を1 epochを行います。T4 GPUで実行すると30分ほどかかります。\n",
|
||||
"\n",
|
||||
"- モデル：https://huggingface.co/stockmark/gpt-neox-japanese-1.4b\n",
|
||||
"- データ：https://github.com/kunishou/databricks-dolly-15k-ja\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"また、ここで用いている設定は暫定的なもので、必要に応じて調整してください。"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "BPGgCZtMdMsv"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"# ライブラリのインストール"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "hCZH9e6EcZyj"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "cmn52bx3v5Ha"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!python3 -m pip install -U pip\n",
|
||||
"!python3 -m pip install transformers accelerate datasets peft"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"# 準備"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "4t3Cqs9_ce3J"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"import torch\n",
|
||||
"import datasets\n",
|
||||
"from transformers import AutoTokenizer, AutoModelForCausalLM, Trainer, TrainingArguments\n",
|
||||
"from peft import get_peft_model, LoraConfig, TaskType, PeftModel, PeftConfig\n",
|
||||
"\n",
|
||||
"model_name = \"stockmark/gpt-neox-japanese-1.4b\"\n",
|
||||
"peft_model_name = \"peft_model\"\n",
|
||||
"\n",
|
||||
"prompt_template = \"\"\"### Instruction:\n",
|
||||
"{instruction}\n",
|
||||
"\n",
|
||||
"### Input:\n",
|
||||
"{input}\n",
|
||||
"\n",
|
||||
"### Response:\n",
|
||||
"\"\"\"\n",
|
||||
"\n",
|
||||
"def encode(sample):\n",
|
||||
" prompt = prompt_template.format(instruction=sample[\"instruction\"], input=sample[\"input\"])\n",
|
||||
" target = sample[\"output\"] + tokenizer.eos_token\n",
|
||||
" input_ids_prompt, input_ids_target = tokenizer([prompt, target]).input_ids\n",
|
||||
" input_ids = input_ids_prompt + input_ids_target\n",
|
||||
" labels = input_ids.copy()\n",
|
||||
" labels[:len(input_ids_prompt)] = [-100] * len(input_ids_prompt)\n",
|
||||
" return {\"input_ids\": input_ids, \"labels\": labels}\n",
|
||||
"\n",
|
||||
"def get_collator(tokenizer, max_length):\n",
|
||||
" def collator(batch):\n",
|
||||
" batch = [{ key: value[:max_length] for key, value in sample.items() } for sample in batch ]\n",
|
||||
" batch = tokenizer.pad(batch, padding=True)\n",
|
||||
" batch[\"labels\"] = [ e + [-100] * (len(batch[\"input_ids\"][0]) - len(e)) for e in batch[\"labels\"] ]\n",
|
||||
" batch = { key: torch.tensor(value) for key, value in batch.items() }\n",
|
||||
" return batch\n",
|
||||
"\n",
|
||||
" return collator\n"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "hNdYMGMRzAVn"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"# データセットとモデルの準備\n"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "UqXxPjJ_cliu"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"# prepare dataset\n",
|
||||
"tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
|
||||
"\n",
|
||||
"dataset_name = \"kunishou/databricks-dolly-15k-ja\"\n",
|
||||
"dataset = datasets.load_dataset(dataset_name)\n",
|
||||
"dataset = dataset.map(encode)\n",
|
||||
"dataset = dataset[\"train\"].train_test_split(0.2)\n",
|
||||
"train_dataset = dataset[\"train\"]\n",
|
||||
"val_dataset = dataset[\"test\"]\n",
|
||||
"\n",
|
||||
"# load model\n",
|
||||
"model = AutoModelForCausalLM.from_pretrained(model_name, device_map={\"\": 0}, torch_dtype=torch.float16)\n",
|
||||
"\n",
|
||||
"peft_config = LoraConfig(\n",
|
||||
" task_type=TaskType.CAUSAL_LM,\n",
|
||||
" inference_mode=False,\n",
|
||||
" target_modules=[\"query_key_value\"],\n",
|
||||
" r=16,\n",
|
||||
" lora_alpha=32,\n",
|
||||
" lora_dropout=0.05\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"model = get_peft_model(model, peft_config)\n",
|
||||
"model.print_trainable_parameters()"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "ZWdN-p7t0Grk"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"# LoRA tuning"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "XCrdVAJYc88c"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"training_args = TrainingArguments(\n",
|
||||
" output_dir=\"./train_results\",\n",
|
||||
" learning_rate=2e-4,\n",
|
||||
" per_device_train_batch_size=4,\n",
|
||||
" gradient_accumulation_steps=4,\n",
|
||||
" per_device_eval_batch_size=16,\n",
|
||||
" num_train_epochs=1,\n",
|
||||
" logging_strategy='steps',\n",
|
||||
" logging_steps=10,\n",
|
||||
" save_strategy='epoch',\n",
|
||||
" evaluation_strategy='epoch',\n",
|
||||
" load_best_model_at_end=True,\n",
|
||||
" metric_for_best_model=\"eval_loss\",\n",
|
||||
" greater_is_better=False,\n",
|
||||
" save_total_limit=2\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"trainer = Trainer(\n",
|
||||
" model=model,\n",
|
||||
" args=training_args,\n",
|
||||
" train_dataset=train_dataset,\n",
|
||||
" eval_dataset=val_dataset,\n",
|
||||
" data_collator=get_collator(tokenizer, 512)\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"trainer.train()\n",
|
||||
"model = trainer.model\n",
|
||||
"model.save_pretrained(peft_model_name)"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "4LH9tOCTJVk1"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"# 学習したモデルのロード"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "ORgzOPAqdEZR"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
|
||||
"model = AutoModelForCausalLM.from_pretrained(model_name, device_map={\"\": 0}, torch_dtype=torch.float16)\n",
|
||||
"model = PeftModel.from_pretrained(model, peft_model_name)"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "yrExyO9EOvzR"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"# 推論"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "-dttR6tkdG0k"
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"prompt = prompt_template.format(instruction=\"日本で人気のスポーツは？\", input=\"\")\n",
|
||||
"\n",
|
||||
"inputs = tokenizer(prompt, return_tensors=\"pt\").to(model.device)\n",
|
||||
"with torch.no_grad():\n",
|
||||
" tokens = model.generate(\n",
|
||||
" **inputs,\n",
|
||||
" max_new_tokens=128,\n",
|
||||
" repetition_penalty=1.1\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"output = tokenizer.decode(tokens[0], skip_special_tokens=True)\n",
|
||||
"print(output)"
|
||||
],
|
||||
"metadata": {
|
||||
"id": "pC5t9F1GJuFN"
|
||||
},
|
||||
"execution_count": null,
|
||||
"outputs": []
|
||||
}
|
||||
]
|
||||
}
|
||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2039be3d49e59904559ab49df85fa8ed58a35967e535d19f174b296a8695b300
|
||||
size 2852090557
|
||||
6
special_tokens_map.json
Normal file
6
special_tokens_map.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"pad_token": "<|padding|>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
99801
tokenizer.json
Normal file
99801
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
10
tokenizer_config.json
Normal file
10
tokenizer_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<|padding|>",
|
||||
"tokenizer_class": "GPTNeoXTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
Reference in New Issue
Block a user