pip install -r requirements.txt

git clone https://github.com/Dao-AILab/flash-attention
cd flash-attention && pip install .
# 下方安装可选，安装可能比较缓慢。
# pip install csrc/layer_norm
# 如果flash-attn版本高于2.1.1，下方无需安装。
# pip install csrc/rotary

from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig

# 可选的模型包括: "Qwen/Qwen-7B-Chat", "Qwen/Qwen-14B-Chat"
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)

# 打开bf16精度，A100、H100、RTX3060、RTX3070等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, bf16=True).eval()
# 打开fp16精度，V100、P100、T4等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, fp16=True).eval()
# 使用CPU进行推理，需要约32GB内存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="cpu", trust_remote_code=True).eval()
# 默认使用自动模式，根据设备自动选择精度
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True).eval()

# 可指定不同的生成长度、top_p等相关超参
model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)

# 第一轮对话
response, history = model.chat(tokenizer, "你好", history=None)
print(response)
# 你好！很高兴为你提供帮助。

# 第二轮对话
response, history = model.chat(tokenizer, "给我讲一个年轻人奋斗创业最终取得成功的故事。", history=history)
print(response)
# 这是一个关于一个年轻人奋斗创业最终取得成功的故事。
# 故事的主人公叫李明，他来自一个普通的家庭，父母都是普通的工人。从小，李明就立下了一个目标：要成为一名成功的企业家。
# 为了实现这个目标，李明勤奋学习，考上了大学。在大学期间，他积极参加各种创业比赛，获得了不少奖项。他还利用课余时间去实习，积累了宝贵的经验。
# 毕业后，李明决定开始自己的创业之路。他开始寻找投资机会，但多次都被拒绝了。然而，他并没有放弃。他继续努力，不断改进自己的创业计划，并寻找新的投资机会。
# 最终，李明成功地获得了一笔投资，开始了自己的创业之路。他成立了一家科技公司，专注于开发新型软件。在他的领导下，公司迅速发展起来，成为了一家成功的科技企业。
# 李明的成功并不是偶然的。他勤奋、坚韧、勇于冒险，不断学习和改进自己。他的成功也证明了，只要努力奋斗，任何人都有可能取得成功。

# 第三轮对话
response, history = model.chat(tokenizer, "给这个故事起一个标题", history=history)
print(response)
# 《奋斗创业：一个年轻人的成功之路》

from modelscope import snapshot_download
from transformers import AutoModelForCausalLM, AutoTokenizer

# Downloading model checkpoint to a local dir model_dir
# model_dir = snapshot_download('qwen/Qwen-7B')
# model_dir = snapshot_download('qwen/Qwen-7B-Chat')
# model_dir = snapshot_download('qwen/Qwen-14B')
model_dir = snapshot_download('qwen/Qwen-14B-Chat')

# Loading local checkpoints
# trust_remote_code is still set as True since we still load codes from local dir instead of transformers
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_dir,
    device_map="auto",
    trust_remote_code=True
).eval()

from modelscope import AutoModelForCausalLM, AutoTokenizer
from modelscope import GenerationConfig

# 可选的模型包括: "qwen/Qwen-7B-Chat", "qwen/Qwen-14B-Chat"
tokenizer = AutoTokenizer.from_pretrained("qwen/Qwen-7B-Chat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, fp16=True).eval()
model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参

response, history = model.chat(tokenizer, "你好", history=None)
print(response)
response, history = model.chat(tokenizer, "浙江的省会在哪里？", history=history) 
print(response)
response, history = model.chat(tokenizer, "它有什么好玩的景点", history=history)
print(response)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers import GenerationConfig
from qwen_generation_utils import make_context, decode_tokens, get_stop_words_ids

tokenizer = AutoTokenizer.from_pretrained(
    './',
    pad_token='<|extra_0|>',
    eos_token='<|endoftext|>',
    padding_side='left',
    trust_remote_code=True
)
model = AutoModelForCausalLM.from_pretrained(
    './',
    pad_token_id=tokenizer.pad_token_id,
    device_map="auto",
    trust_remote_code=True
).eval()
model.generation_config = GenerationConfig.from_pretrained('./', pad_token_id=tokenizer.pad_token_id)

all_raw_text = ["我想听你说爱我。", "今天我想吃点啥，甜甜的，推荐下", "我马上迟到了，怎么做才能不迟到"]
batch_raw_text = []
for q in all_raw_text:
    raw_text, _ = make_context(
        tokenizer,
        q,
        system="You are a helpful assistant.",
        max_window_size=model.generation_config.max_window_size,
        chat_format=model.generation_config.chat_format,
    )
    batch_raw_text.append(raw_text)

batch_input_ids = tokenizer(batch_raw_text, padding='longest')
batch_input_ids = torch.LongTensor(batch_input_ids['input_ids']).to(model.device)
batch_out_ids = model.generate(
    batch_input_ids,
    return_dict_in_generate=False,
    generation_config=model.generation_config
)
padding_lens = [batch_input_ids[i].eq(tokenizer.pad_token_id).sum().item() for i in range(batch_input_ids.size(0))]

batch_response = [
    decode_tokens(
        batch_out_ids[i][padding_lens[i]:],
        tokenizer,
        raw_text_len=len(batch_raw_text[i]),
        context_length=(batch_input_ids[i].size(0)-padding_lens[i]),
        chat_format="chatml",
        verbose=False,
        errors='replace'
    ) for i in range(len(all_raw_text))
]
print(batch_response)

response, _ = model.chat(tokenizer, "我想听你说爱我。", history=None)
print(response)

response, _ = model.chat(tokenizer, "今天我想吃点啥，甜甜的，推荐下", history=None)
print(response)

response, _ = model.chat(tokenizer, "我马上迟到了，怎么做才能不迟到", history=None)
print(response)

model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="cpu", trust_remote_code=True).eval()

export DASHSCOPE_API_KEY="YOUR_DASHSCOPE_API_KEY"

pip install dashscope

<!-- https://mvnrepository.com/artifact/com.alibaba/dashscope-sdk-java -->
<dependency>
    <groupId>com.alibaba</groupId>
    <artifactId>dashscope-sdk-java</artifactId>
    <version>the-latest-version</version>
</dependency>

import random
from http import HTTPStatus
from dashscope import Generation


def call_with_messages():
    messages = [{'role': 'system', 'content': 'You are a helpful assistant.'},
                {'role': 'user', 'content': '如何做西红柿鸡蛋？'}]
    gen = Generation()
    response = gen.call(
        Generation.Models.qwen_turbo,
        messages=messages,
        seed=random.randint(1, 10000),  # set the random seed, optional, default to 1234 if not set
        result_format='message',  # set the result to be "message" format.
    )
    return response


if __name__ == '__main__':
    response = call_with_messages()
    if response.status_code == HTTPStatus.OK:
        print(response)
    else:
        print('Request id: %s, Status code: %s, error code: %s, error message: %s' % (
            response.request_id, response.status_code,
            response.code, response.message
        ))

pip install auto-gptq optimum

# 可选模型包括："Qwen/Qwen-7B-Chat-Int4", "Qwen/Qwen-14B-Chat-Int4"
model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen-7B-Chat-Int4",
    device_map="auto",
    trust_remote_code=True
).eval()
response, history = model.chat(tokenizer, "Hi", history=None)

model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen-7B-Chat",
     device_map="auto",
     trust_remote_code=True,
     use_cache_quantization=True,
     use_cache_kernel=True,
     use_flash_attn=False
)

    qv,scale,zero_point=quantize_cache_v(v)

    layer_past=((q_key,key_scale,key_zero_point),
                (q_value,value_scale,value_zero_point))

    layer_past=(key,value)

    v=dequantize_cache_torch(qv,scale,zero_point)

pip install "peft<0.8.0" deepspeed

[
  {
    "id": "identity_0",
    "conversations": [
      {
        "from": "user",
        "value": "你好"
      },
      {
        "from": "assistant",
        "value": "我是一个语言模型，我叫通义千问。"
      }
    ]
  }
]

# 分布式训练。由于显存限制将导致单卡训练失败，我们不提供单卡训练脚本。
bash finetune/finetune_ds.sh

# 单卡训练
bash finetune/finetune_lora_single_gpu.sh
# 分布式训练
bash finetune/finetune_lora_ds.sh

# 单卡训练
bash finetune/finetune_qlora_single_gpu.sh
# 分布式训练
bash finetune/finetune_qlora_ds.sh

from peft import AutoPeftModelForCausalLM

model = AutoPeftModelForCausalLM.from_pretrained(
    path_to_adapter, # path to the output directory
    device_map="auto",
    trust_remote_code=True
).eval()

from peft import AutoPeftModelForCausalLM

model = AutoPeftModelForCausalLM.from_pretrained(
    path_to_adapter, # path to the output directory
    device_map="auto",
    trust_remote_code=True
).eval()

merged_model = model.merge_and_unload()
# max_shard_size and safe serialization are not necessary. 
# They respectively work for sharding checkpoint and save the model to safetensors
merged_model.save_pretrained(new_model_directory, max_shard_size="2048MB", safe_serialization=True)

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(
    path_to_adapter, # path to the output directory
    trust_remote_code=True
)
tokenizer.save_pretrained(new_model_directory)

pip install auto-gptq optimum

python run_gptq.py \
    --model_name_or_path $YOUR_LORA_MODEL_PATH \
    --data_path $DATA \
    --out_path $OUTPUT_PATH \
    --bits 4 # 4 for int4; 8 for int8

from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig

tokenizer = AutoTokenizer.from_pretrained("/path/to/your/model", trust_remote_code=True)

model = AutoModelForCausalLM.from_pretrained(
    "/path/to/your/model",
    device_map="auto",
    trust_remote_code=True
).eval()

response, history = model.chat(tokenizer, "你好", history=None)
print(response)

pip install vllm

from vllm_wrapper import vLLMWrapper

model = vLLMWrapper('Qwen/Qwen-7B-Chat', tensor_parallel_size=1)

response, history = model.chat(query="你好", history=None)
print(response)
response, history = model.chat(query="给我讲一个年轻人奋斗创业最终取得成功的故事。", history=history)
print(response)
response, history = model.chat(query="给这个故事起一个标题", history=history)
print(response)

pip install "fschat[model_worker,webui]"

python -m fastchat.serve.controller

python -m fastchat.serve.vllm_worker --model-path $model_path --trust-remote-code --dtype bfloat16
# python -m fastchat.serve.vllm_worker --model-path $model_path --trust-remote-code --dtype float16 # 运行int4模型

python -m fastchat.serve.vllm_worker --model-path $model_path --trust-remote-code --tensor-parallel-size 4 --dtype bfloat16
# python -m fastchat.serve.vllm_worker --model-path $model_path --trust-remote-code --tensor-parallel-size 4 --dtype float16 # 运行int4模型

python -m fastchat.serve.gradio_web_server

python -m fastchat.serve.openai_api_server --host localhost --port 8000

pip install -r requirements_web_demo.txt

python web_demo.py

python cli_demo.py

pip install fastapi uvicorn "openai<1.0" pydantic sse_starlette

python openai_api.py

import openai
openai.api_base = "http://localhost:8000/v1"
openai.api_key = "none"

# 使用流式回复的请求
for chunk in openai.ChatCompletion.create(
    model="Qwen",
    messages=[
        {"role": "user", "content": "你好"}
    ],
    stream=True
    # 流式输出的自定义stopwords功能尚未支持，正在开发中
):
    if hasattr(chunk.choices[0].delta, "content"):
        print(chunk.choices[0].delta.content, end="", flush=True)

# 不使用流式回复的请求
response = openai.ChatCompletion.create(
    model="Qwen",
    messages=[
        {"role": "user", "content": "你好"}
    ],
    stream=False,
    stop=[] # 在此处添加自定义的stop words 例如ReAct prompting时需要增加： stop=["Observation:"]。
)
print(response.choices[0].message.content)

# 配置docker
sudo systemctl start docker
# 测试docker是否安装正确
sudo docker run hello-world

# 配置nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker
# 测试nvidia-container-toolkit是否安装正确
sudo docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi

IMAGE_NAME=qwenllm/qwen:cu117
PORT=8901
CHECKPOINT_PATH=/path/to/Qwen-7B-Chat   # 下载到本地的模型及代码路径

bash docker/docker_openai_api.sh -i ${IMAGE_NAME} -c ${CHECKPOINT_PATH} --port ${PORT}

bash docker/docker_web_demo.sh -i ${IMAGE_NAME} -c ${CHECKPOINT_PATH} --port ${PORT}

bash docker/docker_cli_demo.sh -i ${IMAGE_NAME} -c ${CHECKPOINT_PATH}

Successfully started web demo. Open '...' to try!
Run `docker logs ...` to check demo status.
Run `docker rm -f ...` to stop and remove the demo.

IMAGE_NAME=qwenllm/qwen:cu117
CHECKPOINT_PATH=/path/to/Qwen-7B                # 下载的模型和代码路径
#CHECKPOINT_PATH=/path/to/Qwen-7B-Chat-Int4     # 下载的模型和代码路径 (Q-LoRA)
DATA_PATH=/path/to/data/root                    # 准备微调数据放在 ${DATA_PATH}/example.json
OUTPUT_PATH=/path/to/output/checkpoint          # 微调输出路径

# 默认使用主机所有GPU
DEVICE=all
# 如果需要指定用于训练的GPU，按照以下方式设置device（注意：内层的引号不可省略）
#DEVICE='"device=0,1,2,3"'

mkdir -p ${OUTPUT_PATH}

# 单卡LoRA微调
docker run --gpus ${DEVICE} --rm --name qwen \
    --mount type=bind,source=${CHECKPOINT_PATH},target=/data/shared/Qwen/Qwen-7B \
    --mount type=bind,source=${DATA_PATH},target=/data/shared/Qwen/data \
    --mount type=bind,source=${OUTPUT_PATH},target=/data/shared/Qwen/output_qwen \
    --shm-size=2gb \
    -it ${IMAGE_NAME} \
    bash finetune/finetune_lora_single_gpu.sh -m /data/shared/Qwen/Qwen-7B/ -d /data/shared/Qwen/data/example.json

bash finetune/finetune_qlora_single_gpu.sh -m /data/shared/Qwen/Qwen-7B-Chat-Int4/ -d /data/shared/Qwen/data/example.json

@article{qwen,
  title={Qwen Technical Report},
  author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
  journal={arXiv preprint arXiv:2309.16609},
  year={2023}
}