Skip to content

GitLab

Commit af59133f authored by dengjb's avatar dengjb
Browse files

update codes

parent eb1405e9
Pipeline #1188 canceled with stages
Show whitespace changes
Inline Side-by-side
Showing with 804 additions and 2 deletions
.gitignore 0 → 100644
View file @ af59133f
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
.hypothesis/
.pytest_cache/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/en/_build/
docs/zh_cn/_build/
# PyBuilder
target/
# Jupyter Notebook
.ipynb_checkpoints
# pyenv
.python-version
# celery beat schedule file
celerybeat-schedule
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.vscode
.idea
.DS_Store
# custom
*.pkl
*.pkl.json
*.log.json
# Pytorch
*.pth
*.py~
*.sh~
\ No newline at end of file
LICENSE 0 → 100644
View file @ af59133f
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
README.md
View file @ af59133f
# starcoder2_pytorch # StarCoder2
StarCoder2模型是一系列3B、7B和15B模型，使用来自Stack-v2数据集的3.3 至4.3万亿个代码标记进行训练，包含600多种编程语言。
## 论文
`StarCoder 2 and The Stack v2: The Next Generation`<br>
[StarCoder2](https://arxiv.org/pdf/2402.19173)
## 模型结构
StarCoder2的模型结构主要基于StarCoderBase模型架构进行了微小的改动，首先使用RoPE旋转位置编码。其次使用了GQA模块替换了MQA模块。
<div align=center>
<img src="./asserts/model_architecture.png"/>
</div>
## 算法原理
使用GQA模块能够带来更好的速度，使用GQA的head数量不同则会带来速度和性能平衡转换<br>
使用了RoPE位置旋转编码来替代Embedding编码，使得模型获得更好的外推性。<br>
<div align=center>
<img src="./asserts/model_blocks.png"/>
</div>
## 环境配置
-v 路径、docker_name和imageID根据实际情况修改
StarCoder2 is a family of code generation models ### Docker（方法一）
\ No newline at end of file
```bash
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-centos7.6-dtk24.04-py310
docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
cd /your_code_path/starcoder2_pytorch
pip install -r requirements.txt -i http://mirrors.huaweicloud.com/repository/pypi/simple
export HF_ENDPOINT=https://hf-mirror.com
```
### Dockerfile（方法二）
```bash
cd docker
docker build --no-cache -t deepseek_coder:latest .
docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro --shm-size=80G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
cd /your_code_path/starcoder2_pytorch
pip install -r requirements.txt -i http://mirrors.huaweicloud.com/repository/pypi/simple
export HF_ENDPOINT=https://hf-mirror.com
```
### Anaconda（方法三）
关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
```
DTK驱动: dtk24.04
python: python3.10
torch: 2.1.0
```
`Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应`
其它非深度学习库安装方式如下：
```bash
pip install -r requirements.txt -i http://mirrors.huaweicloud.com/repository/pypi/simple
export HF_ENDPOINT=https://hf-mirror.com
```
## 数据集
finetune训练样例数据采用bigcode/the-stack-smol 下的子集/data/rust [下载地址](https://hf-mirror.com/datasets/bigcode/the-stack-smol)<br>
```angular2html
├── data │4 37.0C 59.0W auto 300.0W 0% 0% Normal
│ ├── assembly │5 37.0C 62.0W auto 300.0W 0% 0% Normal
│ │ └── data.json
│ ├── rust
│ │ └── data.json
......
```
<div align=center>
<img src="./asserts/dataset.png"/>
</div>
## 训练
### 单机四卡
具体参数更改请在train.sh文件中进行,以下为必要参数 <br>
dataset_name="{数据集地址}" <br>
model_name="{预训练模型加载地址}" <br>
```bash
bash ./train.sh
```
## 推理
基于Huggingface's Transformers进行推理.<br>
模型下载后 默认需存放至weights文件夹中<br>
也可自行更改 inference.py文件中的 model_name 参数<br>
```bash
HIP_VISIBLE_DEVICES=0 python inference.py
```
## Result
prompt：def print_hello_world():",<br>
result：
<div align=center>
<img src="./asserts/result.png"/>
</div>
### 精度
暂无
## 应用场景
### 算法类别
代码生成
### 热点应用行业
制造,能源,教育
## 预训练权重
模型目录结构如下：
```
# starcoder2-7b/
├── config.json
├── generation_config.json
├── merges.txt
├── model-00001-of-00003.safetensors
├── model-00002-of-00003.safetensors
├── model-00003-of-00003.safetensors
├── model.safetensors.index.json
├── README.md
├── special_tokens_map.json
├── tokenizer_config.json
├── tokenizer.json
└── vocab.json
```
## 源码仓库及问题反馈
- https://developer.hpccube.com/codes/modelzoo/deepseek-coder_pytorch
## 参考资料
- https://github.com/deepseek-ai/DeepSeek-Coder
- https://huggingface.co/deepseek-ai
README_ori.md 0 → 100644
View file @ af59133f
# StarCoder 2
<p align="center"><a href="https://huggingface.co/bigcode">[🤗 Models & Datasets]</a> | <a href="https://arxiv.org/abs/2402.19173">[Paper]</a></a>
</p>
StarCoder2 is a family of code generation models (3B, 7B, and 15B), trained on 600+ programming languages from [The Stack v2](https://huggingface.co/datasets/bigcode/the-stack-v2) and some natural language text such as Wikipedia, Arxiv, and GitHub issues. The models use Grouped Query Attention, a context window of 16,384 tokens, with sliding window attention of 4,096 tokens. The 3B & 7B models were trained on 3+ trillion tokens, while the 15B was trained on 4+ trillion tokens. For more details check out the [paper](https://drive.google.com/file/d/17iGn3c-sYNiLyRSY-A85QOzgzGnGiVI3/view).
# Table of Contents
1. [Quickstart](#quickstart)
- [Installation](#installation)
- [Model usage and memory footprint](#model-usage-and-memory-footprint)
- [Text-generation-inference code](#text-generation-inference)
2. [Fine-tuning](#fine-tuning)
- [Setup](#setup)
- [Training](#training)
3. [Evaluation](#evaluation)
# Quickstart
StarCoder2 models are intended for code completion, they are not instruction models and commands like "Write a function that computes the square root." do not work well.
## Installation
First, we have to install all the libraries listed in `requirements.txt`
```bash
pip install -r requirements.txt
# export your HF token, found here: https://huggingface.co/settings/account
export HF_TOKEN=xxx
```
## Model usage and memory footprint
Here are some examples to load the model and generate code, with the memory footprint of the largest model, `StarCoder2-15B`. Ensure you've installed `transformers` from source (it should be the case if you used `requirements.txt`)
```bash
pip install git+https://github.com/huggingface/transformers.git
```
### Running the model on CPU/GPU/multi GPU
* _Using full precision_
```python
# pip install git+https://github.com/huggingface/transformers.git # TODO: merge PR to main
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "bigcode/starcoder2-15b"
device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
# to use Multiple GPUs do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
* _Using `torch.bfloat16`_
```python
# pip install accelerate
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
checkpoint = "bigcode/starcoder2-15b"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
# for fp16 use `torch_dtype=torch.float16` instead
model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto", torch_dtype=torch.bfloat16)
inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to("cuda")
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
```bash
>>> print(f"Memory footprint: {model.get_memory_footprint() / 1e6:.2f} MB")
Memory footprint: 32251.33 MB
```
### Quantized Versions through `bitsandbytes`
* _Using 8-bit precision (int8)_
```python
# pip install bitsandbytes accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
# to use 4bit use `load_in_4bit=True` instead
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
checkpoint = "bigcode/starcoder2-15b_16k"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-15b_16k", quantization_config=quantization_config)
inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to("cuda")
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
```bash
>>> print(f"Memory footprint: {model.get_memory_footprint() / 1e6:.2f} MB")
# load_in_8bit
Memory footprint: 16900.18 MB
# load_in_4bit
>>> print(f"Memory footprint: {model.get_memory_footprint() / 1e6:.2f} MB")
Memory footprint: 9224.60 MB
```
You can also use `pipeline` for the generation:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
checkpoint = "bigcode/starcoder2-15b"
model = AutoModelForCausalLM.from_pretrained(checkpoint)
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)
print( pipe("def hello():") )
```
## Text-generation-inference:
```bash
docker run -p 8080:80 -v $PWD/data:/data -e HUGGING_FACE_HUB_TOKEN=<YOUR BIGCODE ENABLED TOKEN> -d ghcr.io/huggingface/text-generation-inference:latest --model-id bigcode/starcoder2-15b --max-total-tokens 8192
```
For more details, see [here](https://github.com/huggingface/text-generation-inference).
# Fine-tuning
Here, we showcase how you can fine-tune StarCoder2 models. For more fine-tuning resources you can check [StarCoder's GitHub repository](https://github.com/bigcode-project/starcoder) and [SantaCoder-Finetuning](https://github.com/loubnabnl/santacoder-finetuning).
## Setup
Install `pytorch` [see documentation](https://pytorch.org/), for example the following command works with cuda 12.1:
```bash
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
```
Install the requirements (this installs `transformers` from source to support the StarCoder2 architecture):
```bash
pip install -r requirements.txt
```
Before you run any of the scripts make sure you are logged in `wandb` and HuggingFace Hub to push the checkpoints:
```bash
wandb login
huggingface-cli login
```
Now that everything is done, you can clone the repository and get into the corresponding directory.
## Training
To fine-tune efficiently with a low cost, we use [PEFT](https://github.com/huggingface/peft) library for Low-Rank Adaptation (LoRA) training and [bitsandbytes](https://github.com/TimDettmers/bitsandbytes) for 4bit quantization. We also use the `SFTTrainer` from [TRL](https://github.com/huggingface/trl).
For this example, we will fine-tune StarCoder2-3b on the `Rust` subset of [the-stack-smol](https://huggingface.co/datasets/bigcode/the-stack-smol). This is just for illustration purposes; for a larger and cleaner dataset of Rust code, you can use [The Stack dedup](https://huggingface.co/datasets/bigcode/the-stack-dedup).
To launch the training:
```bash
accelerate launch finetune.py \
--model_id "bigcode/starcoder2-3b" \
--dataset_name "bigcode/the-stack-smol" \
--subset "data/rust" \
--dataset_text_field "content" \
--split "train" \
--max_seq_length 1024 \
--max_steps 10000 \
--micro_batch_size 1 \
--gradient_accumulation_steps 8 \
--learning_rate 2e-5 \
--warmup_steps 20 \
--num_proc "$(nproc)"
```
If you want to fine-tune on other text datasets, you need to change `dataset_text_field` argument to the name of the column containing the code/text you want to train on.
# Evaluation
To evaluate StarCoder2 and its derivatives, you can use the [BigCode-Evaluation-Harness](https://github.com/bigcode-project/bigcode-evaluation-harness) for evaluating Code LLMs. You can also check the [BigCode Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard).
finetune.py 0 → 100644
View file @ af59133f
# Code adapted from https://github.com/huggingface/trl/blob/main/examples/research_projects/stack_llama/scripts/supervised_finetuning.py
# and https://huggingface.co/blog/gemma-peft
import argparse
import multiprocessing
import os
import torch
import transformers
from accelerate import PartialState
from datasets import load_dataset
from peft import LoraConfig
from transformers import (
AutoModelForCausalLM,
BitsAndBytesConfig,
logging,
set_seed,
)
from trl import SFTTrainer
def get_args():
parser = argparse.ArgumentParser()
parser.add_argument("--model_id", type=str, default="bigcode/starcoder2-3b")
parser.add_argument("--dataset_name", type=str, default="the-stack-smol")
parser.add_argument("--subset", type=str, default="data/rust")
parser.add_argument("--split", type=str, default="train")
parser.add_argument("--dataset_text_field", type=str, default="content")
parser.add_argument("--max_seq_length", type=int, default=1024)
parser.add_argument("--max_steps", type=int, default=1000)
parser.add_argument("--micro_batch_size", type=int, default=1)
parser.add_argument("--gradient_accumulation_steps", type=int, default=4)
parser.add_argument("--weight_decay", type=float, default=0.01)
parser.add_argument("--bf16", type=bool, default=True)
parser.add_argument("--attention_dropout", type=float, default=0.1)
parser.add_argument("--learning_rate", type=float, default=2e-4)
parser.add_argument("--lr_scheduler_type", type=str, default="cosine")
parser.add_argument("--warmup_steps", type=int, default=100)
parser.add_argument("--seed", type=int, default=0)
parser.add_argument("--output_dir", type=str, default="finetune_starcoder2")
parser.add_argument("--num_proc", type=int, default=None)
parser.add_argument("--push_to_hub", type=bool, default=True)
return parser.parse_args()
def print_trainable_parameters(model):
"""
Prints the number of trainable parameters in the model.
"""
trainable_params = 0
all_param = 0
for _, param in model.named_parameters():
all_param += param.numel()
if param.requires_grad:
trainable_params += param.numel()
print(
f"trainable params: {trainable_params} || all params: {all_param} || trainable%: {100 * trainable_params / all_param}"
)
def main(args):
# config
bnb_config = BitsAndBytesConfig(
load_in_4bit=False,
bnb_4bit_quant_type="nf4",
bnb_4bit_compute_dtype=torch.bfloat16,
)
lora_config = LoraConfig(
r=8,
target_modules=[
"q_proj",
"o_proj",
"k_proj",
"v_proj",
"gate_proj",
"up_proj",
"down_proj",
],
task_type="CAUSAL_LM",
)
# load model and dataset
token = os.environ.get("HF_TOKEN", None)
model = AutoModelForCausalLM.from_pretrained(
args.model_id,
# quantization_config=bnb_config,
device_map={"": PartialState().process_index},
attention_dropout=args.attention_dropout,
)
print_trainable_parameters(model)
data = load_dataset(
args.dataset_name,
data_dir=args.subset,
split=args.split,
token=token,
num_proc=args.num_proc if args.num_proc else multiprocessing.cpu_count(),
)
# setup the trainer
trainer = SFTTrainer(
model=model,
train_dataset=data,
max_seq_length=args.max_seq_length,
args=transformers.TrainingArguments(
per_device_train_batch_size=args.micro_batch_size,
gradient_accumulation_steps=args.gradient_accumulation_steps,
warmup_steps=args.warmup_steps,
max_steps=args.max_steps,
learning_rate=args.learning_rate,
lr_scheduler_type=args.lr_scheduler_type,
weight_decay=args.weight_decay,
bf16=args.bf16,
logging_strategy="steps",
logging_steps=10,
output_dir=args.output_dir,
optim="adamw_hf",
seed=args.seed,
run_name=f"train-{args.model_id.split('/')[-1]}",
report_to="all",
),
peft_config=lora_config,
dataset_text_field=args.dataset_text_field,
)
# launch
print("Training...")
trainer.train()
print("Saving the last checkpoint of the model")
model.save_pretrained(os.path.join(args.output_dir, "final_checkpoint/"))
if args.push_to_hub:
trainer.push_to_hub("Upload model")
print("Training Done! 💥")
if __name__ == "__main__":
args = get_args()
set_seed(args.seed)
os.makedirs(args.output_dir, exist_ok=True)
logging.set_verbosity_error()
main(args)
inference.py 0 → 100644
View file @ af59133f
# pip install git+https://github.com/huggingface/transformers.git # TODO: merge PR to main
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "bigcode/starcoder2-7b"
device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
# for multiple GPUs install accelerate and do `model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")`
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
\ No newline at end of file
model.properties 0 → 100644
View file @ af59133f
# 模型唯一标识
modelCode=650
# 模型名称
modelName=starcoder2_pytorch
# 模型描述
modelDescription=StarCoder2模型是一系列3B、7B和15B模型，使用来自Stack-v2数据集的3.3 至4.3万亿个代码标记进行训练，包含600多种编程语言
# 应用场景
appScenario=推理,训练,代码生成,制造,能源,教育
# 框架类型
frameType=pytorch
\ No newline at end of file
requirements.txt 0 → 100644
View file @ af59133f
transformers==4.39.3
trl==0.9.4
accelerate==0.27.1
datasets>=2.16.1
peft==0.8.2
wandb==0.16.3
huggingface_hub==0.20.3
\ No newline at end of file
train.sh 0 → 100644
View file @ af59133f
export CUDA_VISIBLE_DEVICES=1,2
nproc=2
model_name="/home/starcoder2/starcoder2-7b/"
dataset_name="/home/starcoder2/the-stack-smol/"
accelerate launch finetune.py \
--model_id $model_name \
--dataset_name $dataset_name \
--subset "data/rust" \
--dataset_text_field "content" \
--split "train" \
--max_seq_length 1024 \
--max_steps 10000 \
--micro_batch_size 1 \
--gradient_accumulation_steps 8 \
--learning_rate 2e-5 \
--warmup_steps 20 \
--num_proc "$(nproc)"
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment