# Deepseek-VL 最佳实践
## 目录
- [环境准备](#环境准备)
- [推理](#推理)
- [微调](#微调)
- [微调后推理](#微调后推理)
## 环境准备
```shell
pip install 'ms-swift[llm]' -U
pip install attrdict
```
模型链接:
- deepseek-vl-1_3b-chat: [https://www.modelscope.cn/models/deepseek-ai/deepseek-vl-1.3b-chat/summary](https://www.modelscope.cn/models/deepseek-ai/deepseek-vl-1.3b-chat/summary)
- deepseek-vl-7b-chat: [https://www.modelscope.cn/models/deepseek-ai/deepseek-vl-7b-chat/summary](https://www.modelscope.cn/models/deepseek-ai/deepseek-vl-7b-chat/summary)
## 推理
推理deepseek-vl-7b-chat:
```shell
# Experimental environment: A100
# 30GB GPU memory
CUDA_VISIBLE_DEVICES=0 swift infer --model_type deepseek-vl-7b-chat
# 如果你想在3090上运行, 可以推理1.3b模型
CUDA_VISIBLE_DEVICES=0 swift infer --model_type deepseek-vl-1_3b-chat
```
7b模型效果展示: (支持传入本地路径或URL)
```python
"""
<<< 你是谁?
我是一个人工智能助手,专门设计来帮助用户解答问题和提供信息。我可以帮助你了解各种主题,从语言学习到视觉识别技术。有什么我可以帮助你的吗?
--------------------------------------------------
<<<
http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/animal.png
http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/cat.png这两张图片有什么区别
这两张图片的主要区别在于它们描绘的动物和场景。
第一张图片展示了一只小猫,它有着醒目的蓝色眼睛和灰白色的毛皮。小猫坐在一个模糊的背景前,看起来像是一张白色的床单或毯子。小猫的目光直直地对着相机,给人一种好奇和警觉的印象。
第二张图片展示了一群羊站在一个绿色的田野中。羊的毛皮是白色和棕色的,它们站在一片绿色的草地上,背景中可以看到山脉。羊群看起来很平静,没有特别指向相机,这表明它们可能正在吃草或仅仅是享受田野。
两张图片的背景都是模糊的,这有助于将焦点集中在动物上。然而,第一张图片中的背景更简单,只有一张白色的床单,而第二张图片中的背景更复杂,包括了绿色的田野和远处的山脉。
总的来说,这两张图片捕捉了两种不同的场景:一只小猫在室内环境中,而一群羊在户外环境中。
--------------------------------------------------
<<<
http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/animal.png图中有几只羊
图中有四只羊。
--------------------------------------------------
<<<
http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/math.png计算结果是多少
将1452和45304相加的结果是1452 + 45304 = 46756。
--------------------------------------------------
<<<
http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/poem.png根据图片中的内容写首诗
星辉洒落湖面静,
独舟轻摇夜色中。
灯火摇曳伴星辰,
波光粼粼映山影。
轻风拂过水面涟,
舟儿前行不自知。
夜深人静思绪远,
孤舟独行心悠然。
"""
```
示例图片如下:
cat:
animal:
math:
poem:
**单样本推理**
```python
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
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.deepseek_vl_7b_chat
template_type = get_default_template_type(model_type)
print(f'template_type: {template_type}')
model, tokenizer = get_model_tokenizer(model_type, torch.float16,
model_kwargs={'device_map': 'auto'})
model.generation_config.max_new_tokens = 256
template = get_template(template_type, tokenizer)
seed_everything(42)
query = '
http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/road.png距离各城市多远?'
response, history = inference(model, template, query)
print(f'query: {query}')
print(f'response: {response}')
# 流式
query = '距离最远的城市是哪?'
gen = inference_stream(model, template, query, history)
print_idx = 0
print(f'query: {query}\nresponse: ', end='')
for response, history in gen:
delta = response[print_idx:]
print(delta, end='', flush=True)
print_idx = len(response)
print()
print(f'history: {history}')
"""
query:
http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/road.png距离各城市多远?
response: 这个标志显示了从当前位置到以下城市的距离:
- 马塔(Mata):14公里
- 阳江(Yangjiang):62公里
- 广州(Guangzhou):293公里
这些信息是根据图片中的标志提供的。
query: 距离最远的城市是哪?
response: 根据图片中的标志,距离最远的城市是广州,距离为293公里。
history: [['
http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/road.png距离各城市多远?', '这个标志显示了从当前位置到以下城市的距离:\n\n- 马塔(Mata):14公里\n- 阳江(Yangjiang):62公里\n- 广州(Guangzhou):293公里\n\n这些信息是根据图片中的标志提供的。'], ['距离最远的城市是哪?', '根据图片中的标志,距离最远的城市是广州,距离为293公里。']]
"""
```
示例图片如下:
road:
## 微调
多模态大模型微调通常使用**自定义数据集**进行微调. 这里展示可直接运行的demo:
LoRA微调:
(默认只对LLM部分的qkv进行lora微调. 如果你想对所有linear含vision模型部分都进行微调, 可以指定`--lora_target_modules ALL`)
```shell
# Experimental environment: A10, 3090, V100
# 20GB GPU memory
CUDA_VISIBLE_DEVICES=0 swift sft \
--model_type deepseek-vl-7b-chat \
--dataset coco-en-mini \
```
全参数微调:
```shell
# Experimental environment: 4 * A100
# 4 * 70GB GPU memory
NPROC_PER_NODE=4 CUDA_VISIBLE_DEVICES=0,1,2,3 swift sft \
--model_type deepseek-vl-7b-chat \
--dataset coco-en-mini \
--sft_type full \
--use_flash_attn true \
--deepspeed default-zero2
```
[自定义数据集](../LLM/自定义与拓展.md#-推荐命令行参数的形式)支持json, jsonl样式, 以下是自定义数据集的例子:
(支持多轮对话, 支持每轮对话含多张图片或不含图片, 支持传入本地路径或URL)
```json
[
{"conversations": [
{"from": "user", "value": "
img_path11111"},
{"from": "assistant", "value": "22222"}
]},
{"conversations": [
{"from": "user", "value": "
img_path
img_path2
img_path3aaaaa"},
{"from": "assistant", "value": "bbbbb"},
{"from": "user", "value": "
img_pathccccc"},
{"from": "assistant", "value": "ddddd"}
]},
{"conversations": [
{"from": "user", "value": "AAAAA"},
{"from": "assistant", "value": "BBBBB"},
{"from": "user", "value": "CCCCC"},
{"from": "assistant", "value": "DDDDD"}
]}
]
```
## 微调后推理
直接推理:
```shell
CUDA_VISIBLE_DEVICES=0 swift infer \
--ckpt_dir output/deepseek-vl-7b-chat/vx-xxx/checkpoint-xxx \
--load_dataset_config true \
```
**merge-lora**并推理:
```shell
CUDA_VISIBLE_DEVICES=0 swift export \
--ckpt_dir output/deepseek-vl-7b-chat/vx-xxx/checkpoint-xxx \
--merge_lora true
CUDA_VISIBLE_DEVICES=0 swift infer \
--ckpt_dir output/deepseek-vl-7b-chat/vx-xxx/checkpoint-xxx-merged \
--load_dataset_config true
```