媒介
前面学习了一些常见多模态模子的架构,现在开始学习使用minicpm-v-2.6模子,记载学习过程,接待品评指正~
排行榜上数据供参考,测试下来qwen2-vl轻微好一点点,然后minivpm-v-2.6稍差一点点
1. 模子文件下载和选择
在modelscope上下载,此中int4的模子推理显存占用7-9GB,效果和全量模子很接近。全量模子下载推理可能轻微慢一些,int4就够用了,而且int4的推理挺快的,平均不到0.5秒一张图,如果同时开4个进程就是一秒钟4张图左右。
- #模型下载
- from modelscope import snapshot_download
- model_dir = snapshot_download('OpenBMB/MiniCPM-V-2_6-int4',cache_dir='要存放模型的路径')
复制代码 2. 环境安装配置
有几个点需要注意的:
- 官方飞书文档里面说微调时deepspeed需要手动安装,不知道为什么手动下载源码的安装的跑不乐成,主动安装的pip install deepspeed最新的比如0.15.0,微调就不会报错
- swift的安装最好直接安装,不要从源代码安装,否则万一删除了源代码环境就无了,然后也不方便,直接pip install ‘ms-swift[llm]’ -U
- 如果要和qwen2-vl的环境通用,注意pip install transformers==4.46.1
- flash-attn可以先在官方github上下载whl文件,如果网速慢的话,一样平常直接pip install flash-attn就行
- 如果要使用vllm安装pip install vllm
3. 模子微调
微调有好几种选择:(1)qlora微调minicpm-v-int4;(2)lora微调minicpm-v;(3)lora微调minicpm-v-int4,然后量化为int4
- 测试下来(1)(2)(3)正确率的差距不大,可能有的情况下(2)比(3)好一点点
- 显卡试了RTX-8000和A100-40/80GB,还是A100比较好,RTX-8000跑大半天,A100半小时到一小时
3.1 qlora微调minicpm-v-int4
qlora微调时需要把–tune_vision设置为false,同时–qlora设置为true
显存开销上,ds_config_zero2和batchsize=1的情况下,qlora大概30-40GB显存开销,如果显存够大用ds_config_zero2,否则用ds_config_zero3(训练速度变慢)。
训练时如果出现data fetch error注意检查路径和数据json文件的格式,应该不会有其他什么问题。
- #!/bin/bash
- GPUS_PER_NODE=1 # 改成你的机器每个节点共有多少张显卡,如果是单机八卡就是8
- NNODES=1 # 改成你的机器有多少个节点,如果就是一台服务器就是1
- NODE_RANK=0 # 使用第几个服务器训练
- MASTER_ADDR=localhost
- MASTER_PORT=6001
- MODEL="/root/ld/ld_model_pretrained/Minicpmv2_6" # 本地模型路径 or openbmb/MiniCPM-V-2.5
- # ATTENTION: specify the path to your training data, which should be a json file consisting of a list of conversations.
- # See the section for finetuning in README for more information.
- DATA="/root/ld/ld_project/MiniCPM-V/finetune/mllm_demo.json" # 训练数据文件地址
- LLM_TYPE="qwen2" # if use openbmb/MiniCPM-V-2, please set LLM_TYPE=minicpm
- export NCCL_P2P_DISABLE=1 # a100等支持nccl_p2p的显卡去掉此行
- export NCCL_IB_DISABLE=1 # a100等显卡去掉此行
- DISTRIBUTED_ARGS="
- --nproc_per_node $GPUS_PER_NODE \
- --nnodes $NNODES \
- --node_rank $NODE_RANK \
- --master_addr $MASTER_ADDR \
- --master_port $MASTER_PORT
- "
- .conda/envs/yourenv/python -m torchrun $DISTRIBUTED_ARGS finetune.py \
- --model_name_or_path $MODEL \
- --llm_type $LLM_TYPE \
- --data_path $DATA \
- --remove_unused_columns false \
- --label_names "labels" \ # 数据构造,不要动
- --prediction_loss_only false \
- --bf16 false \ # 使用bf16精度训练,4090,a100,h100等可以开启
- --bf16_full_eval false \ # 使用bf16精度测试
- --fp16 true \ # 使用fp16精度训练
- --fp16_full_eval true \ # 使用pf16精度测试
- --do_train \ # 是否训练
- --tune_vision true \ # 是否微调siglip(vit)模块
- --tune_llm false \ # 是否微调大语言模型模块
- --use_lora true \ # 是否lora微调
- --lora_target_modules "llm\..*layers\.\d+\.self_attn\.(q_proj|k_proj|v_proj)" \ #lora插入的层,这里写的是正则表达式,建议不改
- --model_max_length 2048 \ # 模型训练的最大长度
- --max_slice_nums 9 \ # 模型最大切分次数
- --max_steps 1000 \ # 最多训练步数
- --output_dir output/output_minicpmv2_lora \ # 模型lora保存地址
- --logging_dir output/output_minicpmv2_lora \ # 日志保存地址
- --logging_strategy "steps" \ # 日志输出策略(可选epoch)
- --per_device_train_batch_size 2 \ # 每张卡训练的batch_size
- --gradient_accumulation_steps 1 \ # 梯度累积,当显存少时可以增大这个参数从而减少per_device_train_batch_size
- --save_strategy "steps" \ # 保存策略(可选epoch)与save_steps同时起作用
- --save_steps 1000 \ # 1000个step保存一次
- --save_total_limit 1 \ # 最大储存总数
- --learning_rate 1e-6 \ # 学习率
- --weight_decay 0.1 \ # 权重正则化参数
- --adam_beta2 0.95 \ #
- --warmup_ratio 0.01 \ # 总步数的预热率,即:总训练步数*warmup_ratio=预热步数
- --lr_scheduler_type "cosine" \ # 学习率调整器
- --logging_steps 10 \
- --gradient_checkpointing false \ # 梯度检查点,建议开启,极大减少显存使用
- --deepspeed ds_config_zero2.json \ # 使用zero3,显存充足建议使用ds_config_zero2.json
复制代码 3.2 lora微调minicpm-v
显存开销上,ds_config_zero2和batchsize=1的情况下,lora大概77-79GB显存开销,如果显存够大用ds_config_zero2,否则用ds_config_zero3(训练速度变慢)
3.3 merge_lora
使用官方飞书文档里面的copy之后,注意需要检查是否拷贝全了,通常会由于原始模子目次下面产生了asset等临时文件,会报错然后漏拷贝image_processing_minicpmv.py、preprocessor_config.json和processing_minicpmv.py。
- 注意,这里如果存的是bin而不是safetensor格式的文件,后面使用官方飞书文档里面的awq量化会报错,awq量化那里输入要求safetensor格式存储的模子
- from peft import PeftModel
- from transformers import AutoModel, AutoTokenizer
- import os
- import shutil
- model_type = "原始minicpm-v模型地址" # Local model path or huggingface id
- path_to_adapter = "存放输出lora文件的地址" # Path to the saved LoRA adapter
- merge_path = "合并后模型地址" # Path to save the merged model
- # 保证原始模型的各个文件不遗漏保存到merge_path中
- def copy_files_not_in_B(A_path, B_path):
- """
- Copies files from directory A to directory B if they exist in A but not in B.
- :param A_path: Path to the source directory (A).
- :param B_path: Path to the destination directory (B).
- """
- # 保证路径存在
- if not os.path.exists(A_path):
- raise FileNotFoundError(f"The directory {A_path} does not exist.")
- if not os.path.exists(B_path):
- os.makedirs(B_path)
- # 获取路径A中所有非权重文件
- files_in_A = os.listdir(A_path)
- files_in_A = set([file for file in files_in_A if not (".bin" in file or "safetensors" in file)])
- # List all files in directory B
- files_in_B = set(os.listdir(B_path))
- # 找到所有A中存在但B中不存在的文件
- files_to_copy = files_in_A - files_in_B
- # 将这些文件复制到B路径下
- for file in files_to_copy:
- if os.path.isfile(file):
- src_file = os.path.join(A_path, file)
- dst_file = os.path.join(B_path, file)
- shutil.copy2(src_file, dst_file)
- # 加载原始模型
- model = AutoModel.from_pretrained(
- model_type,
- trust_remote_code=True
- )
- # 加载lora模块到原始模型中
- lora_model = PeftModel.from_pretrained(
- model,
- path_to_adapter,
- device_map="auto",
- trust_remote_code=True
- ).eval()
- # 将加载的lora模块合并到原始模型中
- merge_model = lora_model.merge_and_unload()
- # 将新合并的模型进行保存
- merge_model.save_pretrained(merge_path, safe_serialization=True)
- # 加载分词器
- tokenizer = AutoTokenizer.from_pretrained(model_type, trust_remote_code=True)
- tokenizer.save_pretrained(merge_path)
- copy_files_not_in_B(model_type,merge_path)
复制代码 3.4 lora微调后量化int4
- 这里的注意点和merge_lora一样,如果使用bnb量化,按照官方飞书文档,量化完了之后记得确认文件是否都在,否则拷贝即可
- awq量化,最好重新conda create一个新的环境专门装这个,而且保证模子是safetensor格式存储即可进行awq量化,awq环境需要使用官方飞书文档里面先容的环境
- from datasets import load_dataset
- from awq import AutoAWQForCausalLM
- from transformers import AutoTokenizer
- import os
- import shutil
- model_path = 'minicpm-v-2_6路径'
- quant_path = '存储量化模型路径'
- quant_config = { "zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMM"}
- # Load model
- model = AutoAWQForCausalLM.from_pretrained(model_path,trust_remote_code=True,device_map='cuda')
- tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True,device_map='cuda')
- def copy_files_not_in_B(A_path, B_path):
- """
- Copies files from directory A to directory B if they exist in A but not in B.
- :param A_path: Path to the source directory (A).
- :param B_path: Path to the destination directory (B).
- """
- # 保证路径存在
- if not os.path.exists(A_path):
- raise FileNotFoundError(f"The directory {A_path} does not exist.")
- if not os.path.exists(B_path):
- os.makedirs(B_path)
- # 获取路径A中所有非权重文件
- files_in_A = os.listdir(A_path)
- files_in_A = set([file for file in files_in_A if not (".bin" in file or "safetensors" in file )])
- # List all files in directory B
- files_in_B = set(os.listdir(B_path))
- # 找到所有A中存在但B中不存在的文件
- files_to_copy = files_in_A - files_in_B
- # 将这些文件复制到B路径下
- for file in files_to_copy:
- src_file = os.path.join(A_path, file)
- dst_file = os.path.join(B_path, file)
- shutil.copy2(src_file, dst_file)
- # Define data loading methods
- def load_alpaca():
- #data = load_dataset('/root/ld/pull_request/MiniCPM/quantize/quantize_data/alpaca', split="train")
- data = load_dataset('tatsu-lab/alpaca', split="train")
- # concatenate data
- def concatenate_data(x):
- msgs=[{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": x['input']},{"role": "system", "content": x['output']}]
- data=tokenizer.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)
- return {"text": data}
-
- concatenated = data.map(concatenate_data)
- return [text for text in concatenated["text"]][:1000]
- def load_wikitext():
- data = load_dataset('wikitext', 'wikitext-2-raw-v1', split="train")
- return [text for text in data["text"] if text.strip() != '' and len(text.split(' ')) > 20]
- # Quantize
- model.quantize(tokenizer, quant_config=quant_config, calib_data=load_alpaca())
- # Save quantized model
- model.save_quantized(quant_path)
- tokenizer.save_pretrained(quant_path)
- print(f'Model is quantized and saved at "{quant_path}"')
- copy_files_not_in_B(model_path,quant_path)
复制代码 4. 模子推理
4.1 huggingface API
- huggingface的方式进行batch inference时,需要找到模子的modeling_minicpmv.py文件,定位里面的chat()函数,把if batched is False后面else那部分注释掉,int4的A100-80GB可以把batch size开到26
- def chat(
- self,
- image,
- msgs,
- tokenizer,
- processor=None,
- vision_hidden_states=None,
- max_new_tokens=2048,
- min_new_tokens=0,
- sampling=True,
- max_inp_length=8192,
- system_prompt='',
- stream=False,
- max_slice_nums=None,
- use_image_id=None,
- **kwargs
- ):
- if isinstance(msgs[0], list):
- batched = True
- else:
- batched = False
- msgs_list = msgs
- images_list = image
-
- if batched is False:
- images_list, msgs_list = [images_list], [msgs_list]
- #else:
- # assert images_list is None, "Please integrate image to msgs when using batch inference."
- # images_list = [None] * len(msgs_list)
- # assert len(images_list) == len(msgs_list), "The batch dim of images_list and msgs_list should be the same."
- if processor is None:
- if self.processor is None:
- self.processor = AutoProcessor.from_pretrained(self.config._name_or_path, trust_remote_code=True)
- processor = self.processor
复制代码 推理时,使用如下代码:
- prompt = 'What can you see in the image?'
- msgs = [{'role': 'user', 'content': prompt}]
- img1 = Image.open('AAA.jpg')
- img2 = Image.open('BBB.jpg')
- images_input_list.append(img1)
- images_input_list.append(img2)
- prompt_input_list.append(msgs)
- prompt_input_list.append(msgs)
- # batch inference
- with torch.inference_mode():
- res = model.chat(images_input_list,msgs=prompt_input_list,tokenizer=tokenizer,sampling=False,max_new_tokens=30)
复制代码
- 可以使用flash-attention加速,只需要网络良好的情况下,pip install flash-attn,然后加载模子时,指定attn_implementation=‘flash_attention_2’
- model = AutoModel.from_pretrained('/', trust_remote_code=True,attn_implementation='flash_attention_2')
复制代码 4.2 swift API
(A) swift(不支持batch inference)
- import os
- os.environ['CUDA_VISIBLE_DEVICES'] = '0'
- os.environ['MAX_SLICE_NUMS'] = '9'
- from swift.llm import (
- get_model_tokenizer, get_template, inference, ModelType,
- get_default_template_type, inference_stream
- )
- from swift.utils import seed_everything
- import torch
- model_type = ModelType.minicpm_v_v2_6_chat
- template_type = get_default_template_type(model_type)
- print(f'template_type: {template_type}')
- model_id_or_path = '模型地址'
- model, tokenizer = get_model_tokenizer(model_type, torch.bfloat16,model_id_or_path=model_id_or_path,
- model_kwargs={'device_map': 'auto'})
- model.generation_config.max_new_tokens = 256
- template = get_template(template_type, tokenizer)
- seed_everything(42)
- model.generation_config.do_sample = False
- query = """<img>要推理的图片存储地址</img>"""
- prompt=" What can you see in this image?"
- query = query+prompt
- response, history = inference(model, template, query)
- print(f'query: {query}')
- print(f'response: {response}')
复制代码 minicpm-v-awq-int4的,不能使用swift的vllm推理,可以使用原始的VLLM推理,不外速度上差异倒不是特别大
(B) swift的VLLM
- # swift的infer
- import os
- os.environ['CUDA_VISIBLE_DEVICES'] = '0'
- os.environ['TENSOR_PARALLEL_SIZE'] = '1'
- from swift.llm import (
- ModelType, get_vllm_engine, get_default_template_type,
- get_template, inference_vllm, inference_stream_vllm
- )
- from swift.utils import seed_everything
- import torch
- model_type = ModelType.minicpm_v_v2_6_chat
- model_id_or_path = '模型路径'
- llm_engine = get_vllm_engine(model_type, model_id_or_path=model_id_or_path)
- template_type = get_default_template_type(model_type)
- template = get_template(template_type, llm_engine.hf_tokenizer)
- generation_info = {}
- query1 = """<img>图片路径1</img>"""
- query2 = """<img>图片路径2</img>"""
- query1 = '.......'
- query2 = '.......'
- request_list = [{'query':query1},{'query':query2}]
- resp_list = inference_vllm(llm_engine, template, request_list, generation_info=generation_info)
- for request, resp in zip(request_list, resp_list):
- print(f"query: {request['query']}")
- print(f"response: {resp['response']}")
- print(generation_info)
复制代码 4.3 VLLM
(A) 单个推理
- from PIL import Image
- from transformers import AutoTokenizer
- from vllm import LLM, SamplingParams
- # 图像文件路径列表
- IMAGES = [
- "图片路径", # 本地图片路径
- ]
- # 改成你量化后的awq路径/ 原始minicpm-v的路径
- # awq模型路径
- MODEL_NAME = '模型路径'
- # 打开并转换图像
- image = Image.open(IMAGES[0]).convert("RGB")
- # 初始化分词器
- tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
- # 初始化语言模型
- llm = LLM(model=MODEL_NAME,
- gpu_memory_utilization=0.5, # 1表示使用全部GPU内存,如果希望gpu占用率降低,就减少gpu_memory_utilization
- trust_remote_code=True,
- max_model_len=2048) # 根据内存状况可调整此值
- # 构建对话消息
- messages = [{'role': 'user', 'content': '(<image>./</image>)\n' + '请描述这张图片'}]
- # 应用对话模板到消息
- prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
- # 设置停止符ID
- # 2.0
- # stop_token_ids = [tokenizer.eos_id]
- # 2.5
- #stop_token_ids = [tokenizer.eos_id, tokenizer.eot_id]
- # 2.6
- stop_tokens = ['<|im_end|>', '<|endoftext|>']
- stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]
- # 设置生成参数
- sampling_params = SamplingParams(
- stop_token_ids=stop_token_ids,
- # temperature=0.7,
- # top_p=0.8,
- # top_k=100,
- # seed=3472,
- max_tokens=1024,
- # min_tokens=150,
- temperature=0,
- use_beam_search=True,
- # length_penalty=1.2,
- best_of=3)
- # 获取模型输出
- outputs = llm.generate({
- "prompt": prompt,
- "multi_modal_data": {
- "image": img1_path
- }
- }, sampling_params=sampling_params)
- print(outputs[0].outputs[0].text)
复制代码 (B) batch inference
- from PIL import Image
- from transformers import AutoTokenizer
- from vllm import LLM, SamplingParams
- # 所有待输入的图像
- IMAGES = [
- "图片地址1",
- "图片地址2"
- ]
- # MODEL_NAME = "HwwwH/MiniCPM-V-2" # If you use the local MiniCPM-V-2 model, please update the model code from HwwwH/MiniCPM-V-2
- # If using a local model, please update the model code to the latest
- MODEL_NAME = '模型路径'
- images = [Image.open(i).convert("RGB") for i in IMAGES]
- tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
- llm = LLM(model=MODEL_NAME,
- gpu_memory_utilization=1,
- trust_remote_code=True,
- max_model_len=1024)
- prompt = 'What can you see in this image?'
- messages = [{'role': 'user', 'content': '(<image>./</image>)\n' + prompt}]
- prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
- # Construct multiple inputs. This example shares prompt, or you don’t need to share prompt.
- inputs=[{"prompt": prompt,"multi_modal_data": {"image": i }} for i in images]
- # 2.0
- # stop_token_ids = [tokenizer.eos_id]
- # 2.5
- #stop_token_ids = [tokenizer.eos_id, tokenizer.eot_id]
- # 2.6
- stop_tokens = ['<|im_end|>', '<|endoftext|>']
- stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]
- sampling_params = SamplingParams(
- stop_token_ids=stop_token_ids,
- # temperature=0.7,
- # top_p=0.8,
- # top_k=100,
- # seed=3472,
- max_tokens=200,
- # min_tokens=150,
- temperature=0,
- use_beam_search=True,
- # length_penalty=1.2,
- best_of=3)
- outputs = llm.generate(inputs, sampling_params=sampling_params)
- for i in range(len(inputs)):
- print(outputs[i].outputs[0].text)
复制代码 5. 参考链接
- minicpm-v的官方飞书文档,真的学到了许多,群里面有问题回复也超及时,感谢官方和社区分享:https://modelbest.feishu.cn/wiki/SgGpwVz4aiSDwNkVMrmcMpHsnAF
- swift的官方文档:https://swift.readthedocs.io/en/stable/index.html
免责声明:如果侵犯了您的权益,请联系站长,我们会及时删除侵权内容,谢谢合作!更多信息从访问主页:qidao123.com:ToB企服之家,中国第一个企服评测及商务社交产业平台。 |