实现llava的【单轮对话】调整成【多轮对话】（输入图片/多模态/多轮对话/llava）【多次单轮对话】

llava，多轮对话，多模态

SiYuanFeng

1727人浏览 · 2024-07-08 00:59:20

SiYuanFeng · 2024-07-08 00:59:20 发布

使用llava时，将llava的单轮对话调整成多轮对话

先说好
方法一，直接对官方网站的quick start代码进行修改
方法二：使用bash结合基础的单轮对话代码进行修改
2.1 首先是最基础的llava官网代码回顾
- 2.2 伪多轮对话方法（每次新的prompt输入）
- 2.3 真正的==多轮对话==，也就是每次输入问题prompt的时候，把上次模型的回答（对话历史）也一起输入进去，可以把文件修改成这样：
方法三：多次单轮对话。

先说好

看方法二！看方法二！看方法二！
方法二的帮助更大，格式通俗易懂！输出文件什么的都设置好了写好了
方法一我是一个py文件里实现，但目前效果不太好，因为太费内存了！还是方法二，分开成py和bash文件效果更好！

方法一，直接对官方网站的quick start代码进行修改

llava_github官网里的单轮对话代码，我能跑起来的如下所示：

import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"  # 指定使用 GPU 0

from llava.model.builder import load_pretrained_model
from llava.mm_utils import get_model_name_from_path
from llava.eval.run_llava import eval_model

model_path = "/data1/yjgroup/tym/lab_sync_mac/LLaVA/checkpoints/llava-v1.6-vicuna-7b"

tokenizer, model, image_processor, context_len = load_pretrained_model(
    model_path=model_path,
    model_base=None,
    model_name=get_model_name_from_path(model_path),
    # load_4bit=True,
    # load_8bit=True
)

model_path = "/data1/yjgroup/tym/lab_sync_mac/LLaVA/checkpoints/llava-v1.6-vicuna-7b"
prompt = "What are the things I should be cautious about when I visit here?"
image_file = "/home/data/yjgroup/fsy/VG_100K/1.jpg"

args = type('Args', (), {
    "model_path": model_path,
    "model_base": None,
    "model_name": get_model_name_from_path(model_path),
    "query": prompt,
    "conv_mode": None,
    "image_file": image_file,
    "sep": ",",
    "temperature": 0.2,
    "top_p":None,
    "num_beams": 1,
    'max_new_tokens': 512
})()

eval_model(args)

上面代码都挺好，就是稍微注意一个知识点，就是llava如果不设置是4bit运行或者8bit运行，那么它默认是16bit运行。可以从LLaVA/llava/model/builder.py这个文件的kwargs[‘torch_dtype’] = torch.float16语句中看出来。

现在我希望能够不仅实现输入一张图片后，进行多模态单轮对话，还可以进行多轮对话，我可以将代码修改成如下所示：
但是请注意：这样修改以后会很占内存

import os
from llava.model.builder import load_pretrained_model
from llava.mm_utils import get_model_name_from_path
from llava.eval.run_llava import eval_model

# 设置环境变量
os.environ["CUDA_VISIBLE_DEVICES"] = "0"  # 指定使用 GPU 0

# 加载预训练模型
model_path = "/data1/yjgroup/tym/lab_sync_mac/LLaVA/checkpoints/llava-v1.6-vicuna-7b"
tokenizer, model, image_processor, context_len = load_pretrained_model(
    model_path=model_path,
    model_base=None,
    model_name=get_model_name_from_path(model_path)
)

# 定义初始对话内容和图片路径
initial_prompt = "What are the things I should be cautious about when I visit here?"
image_file = "/home/data/yjgroup/fsy/VG_100K/1.jpg"

# 创建一个类来存储对话上下文
class MultiTurnDialog:
    def __init__(self, initial_prompt, image_file):
        self.dialog = [{"role": "user", "content": initial_prompt}]
        self.image_file = image_file

    def add_turn(self, role, content):
        self.dialog.append({"role": role, "content": content})

    def get_dialog(self):
        return "\n".join([f"{turn['role'].capitalize()}: {turn['content']}" for turn in self.dialog])

# 初始化对话
multi_turn_dialog = MultiTurnDialog(initial_prompt, image_file)

# 定义一个函数来运行模型并获取响应
def get_model_response(dialog, image_file):
    args = type('Args', (), {
        "model_path": model_path,
        "model_base": None,
        "model_name": get_model_name_from_path(model_path),
        "query": dialog,
        "conv_mode": None,
        "image_file": image_file,
        "sep": ",",
        "temperature": 0.2,
        "top_p": None,
        "num_beams": 1,
        'max_new_tokens': 512
    })()
    return eval_model(args)

# 初次运行模型获取响应
response = get_model_response(multi_turn_dialog.get_dialog(), multi_turn_dialog.image_file)
print(f"Assistant: {response}")

# 添加初次对话到对话上下文
multi_turn_dialog.add_turn("assistant", response)

# 示例多轮对话
user_inputs = [
    "Can you tell me more about the safety measures?",
    "What about the local customs and traditions?"
]

for user_input in user_inputs:
    # 添加用户输入到对话上下文
    multi_turn_dialog.add_turn("user", user_input)
    # 获取当前对话上下文
    current_dialog = multi_turn_dialog.get_dialog()
    # 运行模型获取响应
    response = get_model_response(current_dialog, multi_turn_dialog.image_file)
    print(f"Assistant: {response}")
    # 添加模型响应到对话上下文
    multi_turn_dialog.add_turn("assistant", response)

# 最终对话内容
print("Final dialog context:")
print(multi_turn_dialog.get_dialog())

模型输出：

（下面这个输出说明一件事。我们的输出内容没有保存好，所以我又重新修改了一下代码）

Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:07<00:00, 2.35s/it]
You are using a model of type llava to instantiate a model of type llava_llama. This is not supported for all configurations of models and can yield errors.
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:06<00:00, 2.25s/it]
When visiting a place like the one shown in the image, which appears to be a city street with parked cars, trees, and pedestrians, here are some general things to be cautious about:

Pedestrian Safety: Always be aware of your surroundings and watch for vehicles when crossing streets.

Parking Regulations: If you're parking your vehicle, make sure to follow the parking signs and regulations to avoid fines or towing.

Traffic Signals: Pay attention to traffic lights and crosswalks to ensure you're following the rules of the road.

Personal Safety: Keep an eye on your belongings to prevent theft, and be mindful of your personal space.

Local Laws and Customs: Familiarize yourself with local laws and customs to avoid inadvertently breaking the law or offending someone.

Weather Conditions: Depending on the season, be prepared for the weather. If it's cold, dress appropriately. If it's hot, stay hydrated.

Health Precautions: Depending on the current health advisories, you may need to take precautions such as wearing a mask or using hand sanitizer.

Communication: If you're in a foreign country, have a way to communicate in case of an emergency, such as a local SIM card for your phone or a translation app.

Emergency Services: Know the local emergency numbers and the location of the nearest embassy or consulate if you're traveling internationally.

Cultural Sensitivity: Be respectful of the local culture and traditions. This includes dress codes, behavior in public spaces, and respect for religious sites.

Remember, these are general tips and the specific precautions you should take may vary depending on the specific location and your own personal circumstances.
You are using a model of type llava to instantiate a model of type llava_llama. This is not supported for all configurations of models and can yield errors.
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:01<00:00, 1.65it/s]
You are using a model of type llava to instantiate a model of type llava_llama. This is not supported for all configurations of models and can yield errors.
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:07<00:00, 2.47s/it]
When visiting an area like the one shown in the image, which appears to be a city street with a sidewalk, here are some general things to be cautious about:

Traffic: Always be aware of the traffic around you, especially if you're walking near the road. Cars and bicycles can move quickly, so make sure to stay on the sidewalk and follow traffic rules.

Pedestrian Safety: Look both ways before crossing the street, even if there's a crosswalk. Be mindful of vehicles that may not see you.

Personal Safety: Keep an eye on your belongings to prevent theft. In busy areas, pickpockets can be a concern.

Local Laws and Customs: Be aware of local laws and customs. Some places have specific rules about littering, smoking, or drinking in public.

Weather Conditions: Depending on the season, be prepared for the weather. If it's cold, wear appropriate clothing. If it's hot, stay hydrated and wear sunscreen.

Health Precautions: Depending on the region, there may be health advisories or precautions to take, such as vaccinations or avoiding certain foods.

Communication: Have a way to communicate in case of an emergency. This could be a local phone, a map, or a translation app.

Emergency Services: Know the local emergency numbers and the location of the nearest embassy or consulate if you're traveling internationally.

Scams: Be wary of common tourist scams. They can range from overpriced services to more elaborate cons.

Cultural Sensitivity: Be respectful of local customs and traditions. This can include dress codes, behavior in religious sites, and respect for local laws.

Remember, these are general tips and the specific precautions can vary depending on the exact location and the time of your visit.
Assistant: None
You are using a model of type llava to instantiate a model of type llava_llama. This is not supported for all configurations of models and can yield errors.
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:07<00:00, 2.42s/it]
None
Assistant: None
You are using a model of type llava to instantiate a model of type llava_llama. This is not supported for all configurations of models and can yield errors.
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:07<00:00, 2.49s/it]
None
Assistant: None
Final dialog context:
User: What are the things I should be cautious about when I visit here?
Assistant: None
User: Can you tell me more about the safety measures?
Assistant: None
User: What about the local customs and traditions?
Assistant: None

第三次修改：
这次修改的问题是：确实把输出都保存到prompt里了，但这样修改太占用内存了，所以很容易跑不起来，所以我换了一种思路（方法二）

import os
from llava.model.builder import load_pretrained_model
from llava.mm_utils import get_model_name_from_path
from llava.eval.run_llava import eval_model
from io import StringIO
import sys

# 设置环境变量
os.environ["CUDA_VISIBLE_DEVICES"] = "0"  # 指定使用 GPU 0

# 加载预训练模型
model_path = "/data1/yjgroup/tym/lab_sync_mac/LLaVA/checkpoints/llava-v1.6-vicuna-7b"
tokenizer, model, image_processor, context_len = load_pretrained_model(
    model_path=model_path,
    model_base=None,
    model_name=get_model_name_from_path(model_path)
)

# 定义初始对话内容和图片路径
initial_prompt = "What are the things I should be cautious about when I visit here?"
image_file = "/home/data/yjgroup/fsy/VG_100K/1.jpg"

# 创建一个类来存储对话上下文
class MultiTurnDialog:
    def __init__(self, initial_prompt, image_file):
        self.dialog = [{"role": "user", "content": initial_prompt}]
        self.image_file = image_file

    def add_turn(self, role, content):
        self.dialog.append({"role": role, "content": content})

    def get_dialog(self):
        return "\n".join([f"{turn['role'].capitalize()}: {turn['content']}" for turn in self.dialog])

# 初始化对话
multi_turn_dialog = MultiTurnDialog(initial_prompt, image_file)

# 定义一个函数来运行模型并获取响应
def get_model_response(dialog, image_file):
    args = type('Args', (), {
        "model_path": model_path,
        "model_base": None,
        "model_name": get_model_name_from_path(model_path),
        "query": dialog,
        "conv_mode": None,
        "image_file": image_file,
        "sep": ",",
        "temperature": 0.2,
        "top_p": None,
        "num_beams": 1,
        'max_new_tokens': 512
    })()

    # 捕获标准输出
    old_stdout = sys.stdout
    sys.stdout = mystdout = StringIO()

    try:
        eval_model(args)
    finally:
        # 恢复标准输出
        sys.stdout = old_stdout

    # 获取模型输出
    model_output = mystdout.getvalue().strip()
    return model_output

# 初次运行模型获取响应
response = get_model_response(multi_turn_dialog.get_dialog(), multi_turn_dialog.image_file)
print(f"Assistant: {response}")

# 添加初次对话到对话上下文
multi_turn_dialog.add_turn("assistant", response)

# 示例多轮对话
user_inputs = [
    "Can you tell me more about the safety measures?",
    "What about the local customs and traditions?"
]

for user_input in user_inputs:
    # 添加用户输入到对话上下文
    multi_turn_dialog.add_turn("user", user_input)
    # 获取当前对话上下文
    current_dialog = multi_turn_dialog.get_dialog()
    # 运行模型获取响应
    response = get_model_response(current_dialog, multi_turn_dialog.image_file)
    print(f"Assistant: {response}")
    # 添加模型响应到对话上下文
    multi_turn_dialog.add_turn("assistant", response)

# 最终对话内容
print("Final dialog context:")
print(multi_turn_dialog.get_dialog())

方法二：使用bash结合基础的单轮对话代码进行修改

2.1 首先是最基础的llava官网代码回顾

import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"  # 指定使用 GPU 0

from llava.model.builder import load_pretrained_model
from llava.mm_utils import get_model_name_from_path
from llava.eval.run_llava import eval_model

model_path = "/data1/yjgroup/tym/lab_sync_mac/LLaVA/checkpoints/llava-v1.6-vicuna-7b"

tokenizer, model, image_processor, context_len = load_pretrained_model(
    model_path=model_path,
    model_base=None,
    model_name=get_model_name_from_path(model_path),
    # load_4bit=True,
    # load_8bit=True
)

model_path = "/data1/yjgroup/tym/lab_sync_mac/LLaVA/checkpoints/llava-v1.6-vicuna-7b"
prompt = "What are the things I should be cautious about when I visit here?"
image_file = "/home/data/yjgroup/fsy/VG_100K/1.jpg"

args = type('Args', (), {
    "model_path": model_path,
    "model_base": None,
    "model_name": get_model_name_from_path(model_path),
    "query": prompt,
    "conv_mode": None,
    "image_file": image_file,
    "sep": ",",
    "temperature": 0.2,
    "top_p":None,
    "num_beams": 1,
    'max_new_tokens': 512
})()

eval_model(args)

2.2 伪多轮对话方法（每次新的prompt输入）

建立一个Bash 脚本（multi_round_dialogue.sh）

#!/bin/bash

# 定义变量
MODEL_PATH="/data1/yjgroup/tym/lab_sync_mac/LLaVA/checkpoints/llava-v1.6-vicuna-7b"
IMAGE_FILE="/home/data/yjgroup/fsy/VG_100K/1.jpg"
OUTPUT_FILE="dialogue_output.txt"
CUDA_DEVICE="1"  # 指定使用的 CUDA 设备


# 设置 CUDA_VISIBLE_DEVICES 环境变量
export CUDA_VISIBLE_DEVICES=$CUDA_DEVICE

# 检查是否设置成功
echo $CUDA_VISIBLE_DEVICES

# 清空输出文件
> $OUTPUT_FILE

# 设置每轮对话的提示
PROMPTS=(
    "What are the things I should be cautious about when I visit here?"
    "Can you suggest some local foods to try?"
    "What are the best tourist attractions in this area?"
)

# 对话轮数（根据提示数量设置）
ROUNDS=${#PROMPTS[@]}

# 初始化对话历史
DIALOGUE_HISTORY=""

for ((i=0; i<ROUNDS; i++))
do
    PROMPT=${PROMPTS[$i]}
    echo "Round $((i+1))" >> $OUTPUT_FILE
    echo "User: $PROMPT" >> $OUTPUT_FILE

    # 组合当前对话历史和新的提示
    if [ -z "$DIALOGUE_HISTORY" ]; then
        INPUT_PROMPT="$PROMPT"
    else
        INPUT_PROMPT="$DIALOGUE_HISTORY\nUser: $PROMPT"
    fi

    # 调用 Python 脚本并获取输出
    RESPONSE=$(CUDA_VISIBLE_DEVICES=$CUDA_DEVICE python3 run_llava_dialogue.py "$MODEL_PATH" "$IMAGE_FILE" "$INPUT_PROMPT")

    echo "Assistance: $RESPONSE" >> $OUTPUT_FILE
    echo "" >> $OUTPUT_FILE

    # 更新对话历史
    DIALOGUE_HISTORY="$INPUT_PROMPT\nAssistance: $RESPONSE"
done

建立一个修改后的 Python 脚本（run_llava_dialogue.py）

import os
import sys
from llava.model.builder import load_pretrained_model
from llava.mm_utils import get_model_name_from_path
from llava.eval.run_llava import eval_model

# 从命令行参数获取输入
model_path = sys.argv[1]
image_file = sys.argv[2]
prompt = sys.argv[3]

os.environ["CUDA_VISIBLE_DEVICES"] = os.getenv("CUDA_VISIBLE_DEVICES", "0")  # 获取 CUDA 设备

# 加载预训练模型
tokenizer, model, image_processor, context_len = load_pretrained_model(
    model_path=model_path,
    model_base=None,
    model_name=get_model_name_from_path(model_path),
    # load_4bit=True,
    # load_8bit=True
)

args = type('Args', (), {
    "model_path": model_path,
    "model_base": None,
    "model_name": get_model_name_from_path(model_path),
    "query": prompt,
    "conv_mode": None,
    "image_file": image_file,
    "sep": ",",
    "temperature": 0.2,
    "top_p": None,
    "num_beams": 1,
    'max_new_tokens': 512
})()

# 运行模型评估
response = eval_model(args)

# 打印响应以便 Bash 脚本捕获
print(response)

使用方法：
- 确保 multi_round_dialogue.sh 和 run_llava_dialogue.py 放在同一目录下。
- 给Bash脚本添加可执行权限：
```
chmod +x multi_round_dialogue.sh
```
- 运行 Bash 脚本：
```
./multi_round_dialogue.sh
```

这个脚本会运行三轮对话，并将每轮对话的用户输入和助手响应保存到 dialogue_output.txt 文件中。每轮对话的问题已经提前设置好，并在每次运行时指定 CUDA 的卡号。

2.3 真正的多轮对话，也就是每次输入问题prompt的时候，把上次模型的回答（对话历史）也一起输入进去，可以把文件修改成这样：

修改后的 Bash 脚本（multi_round_dialogue.sh）

#!/bin/bash

# 定义变量
MODEL_PATH="/data1/yjgroup/tym/lab_sync_mac/LLaVA/checkpoints/llava-v1.6-vicuna-7b"
IMAGE_FILE="/home/data/yjgroup/fsy/VG_100K/1.jpg"
OUTPUT_FILE="dialogue_output.txt"
CUDA_DEVICE="0"  # 指定使用的 CUDA 设备

# 清空输出文件
> $OUTPUT_FILE

# 设置每轮对话的提示
PROMPTS=(
    "What are the things I should be cautious about when I visit here?"
    "Can you suggest some local foods to try?"
    "What are the best tourist attractions in this area?"
)

# 对话轮数（根据提示数量设置）
ROUNDS=${#PROMPTS[@]}

# 初始化对话历史
DIALOGUE_HISTORY=""

for ((i=0; i<ROUNDS; i++))
do
    PROMPT=${PROMPTS[$i]}
    echo "Round $((i+1))" >> $OUTPUT_FILE
    echo "User: $PROMPT" >> $OUTPUT_FILE

    # 组合当前对话历史和新的提示
    if [ -z "$DIALOGUE_HISTORY" ]; then
        INPUT_PROMPT="$PROMPT"
    else
        INPUT_PROMPT="$DIALOGUE_HISTORY\nUser: $PROMPT"
    fi

    # 调用 Python 脚本并获取输出
    RESPONSE=$(CUDA_VISIBLE_DEVICES=$CUDA_DEVICE python3 run_llava_dialogue.py "$MODEL_PATH" "$IMAGE_FILE" "$INPUT_PROMPT")

    echo "Assistance: $RESPONSE" >> $OUTPUT_FILE
    echo "" >> $OUTPUT_FILE

    # 更新对话历史
    DIALOGUE_HISTORY="$INPUT_PROMPT\nAssistance: $RESPONSE"
done

修改后的 Python 脚本（run_llava_dialogue.py）

import os
import sys
from llava.model.builder import load_pretrained_model
from llava.mm_utils import get_model_name_from_path
from llava.eval.run_llava import eval_model

# 从命令行参数获取输入
model_path = sys.argv[1]
image_file = sys.argv[2]
prompt = sys.argv[3]

# os.environ["CUDA_VISIBLE_DEVICES"] = os.getenv("CUDA_VISIBLE_DEVICES", "0")     
# 上面这行注释掉，因为我们已经在sh文件里默认设置CUDA_VISIBLE_DEVICES只有一张卡了。那映射过来，设备将只有一张0号卡（物理卡号映射成虚拟卡号）。
# 这里但凡再写一次CUDA_VISIBLE_DEVICES是0号卡以外的其他卡号，就运行不了了

# 加载预训练模型
tokenizer, model, image_processor, context_len = load_pretrained_model(
    model_path=model_path,
    model_base=None,
    model_name=get_model_name_from_path(model_path),
    # load_4bit=True,
    # load_8bit=True     # 如果不是8bit跑，需要占用30944mib
)


args = type('Args', (), {
    "model_path": model_path,
    "model_base": None,
    "model_name": get_model_name_from_path(model_path),
    "query": prompt,
    "conv_mode": None,
    "image_file": image_file,
    "sep": ",",
    "temperature": 0.2,
    "top_p": None,
    "num_beams": 1,
    'max_new_tokens': 512
})()

# 运行模型评估
response = eval_model(args)

# 打印响应以便 Bash 脚本捕获
print(response)

使用方法：

把multi_round_dialogue.sh 和 run_llava_dialogue.py 放在同一目录下。
给 Bash 脚本添加可执行权限：

chmod +x multi_round_dialogue.sh

运行 Bash 脚本：

./multi_round_dialogue.sh

这个脚本会运行三轮对话，并将每轮对话的用户输入和助手响应保存到 dialogue_output.txt 文件中。每轮对话的问题会与之前的对话历史一起作为输入传递给模型，从而实现真正的多轮对话。

方法三：多次单轮对话。

因为后来我发现使用多轮对话好像效果还不如一次把一个单轮对话prompt调整好，之后做调整呢。
多轮对话炸显存。

所以我写了一个函数，生成了无数个一条的bash命令，然后让bash命令一条一条读取吧。

Step 1: 使用Python脚本生成一系列包含prompt的bash命令

import json

# JSON 文件路径
data_file = '/home/data/yjgroup/fsy/gt_and_pred_english.json'

# 输出 shell 脚本文件路径
output_shell_file = './generated_commands.sh'

# 读取 JSON 数据文件
with open(data_file, 'r') as f:
    data = json.load(f)

# 打开输出 shell 脚本文件
with open(output_shell_file, 'w') as out_f:
    # 写入 shell 脚本的头部
    out_f.write("#!/bin/bash\n\n")

    # 遍历每一张图片的数据并生成命令
    for image in data:
        image_name = image['image_path']
        pred_classes = image['pred_classes']
        image_file = f"/home/data/yjgroup/fsy/VG_100K/{image_name}"

        prompt = (
            "Generate relation triples for the objects in the image. Relation categories: "
            "Input image: '{}', objects: {}. Generate triples and confidences."
        ).format(image_name, pred_classes)

        # 如果要修改指定卡号，直接在这个命令里修改就可以了。
        command = f"CUDA_VISIBLE_DEVICES=1 python3 run_llava_dialogue.py '/data1/yjgroup/tym/lab_sync_mac/LLaVA/checkpoints/llava-v1.6-vicuna-7b' '{image_file}' '{prompt}' >> dialogue_output.txt\n"
        out_f.write(command)

print(f"Commands have been written to {output_shell_file}")

Step 2: 修改后的 Shell 脚本逐行读取并执行命令

这个 shell 脚本会逐行读取 generated_commands.sh 文件中的命令并执行它们，同时允许通过变量指定 CUDA 设备号。

#!/bin/bash

# 生成的Shell脚本路径
generated_shell_file='./generated_commands.sh'

# 检查生成的Shell脚本是否存在
if [ ! -f "$generated_shell_file" ]; then
    echo "Generated shell script not found: $generated_shell_file"
    exit 1
fi

# 逐行读取并执行命令
while IFS= read -r line
do
    # 跳过空行和注释行
    if [[ -z "$line" || "$line" =~ ^# ]]; then
        continue
    fi

    # 打印并执行命令
    echo "Executing: $line"
    eval "$line"
done < "$generated_shell_file"

运行步骤

运行 Python 脚本生成 generated_commands.sh 文件。
将上述脚本保存为一个新的 Bash 文件，例如 execute_generated_commands.sh。然后，给这个脚本赋予执行权限并运行它：

例如：

chmod +x execute_generated_commands.sh
./execute_generated_commands.sh

这个脚本会逐行读取 generated_commands.sh 文件中的命令，并执行每一行命令。它会跳过空行和以 # 开头的注释行。

开放原子开发者工作坊

开放原子开发者工作坊旨在鼓励更多人参与开源活动，与志同道合的开发者们相互交流开发经验、分享开发心得、获取前沿技术趋势。工作坊有多种形式的开发者活动，如meetup、训练营等，主打技术交流，干货满满，真诚地邀请各位开发者共同参与！

更多推荐

第二届开放原子大赛首批创新成果集结武汉，诚邀广大开发者共鉴开源技术盛宴

开放原子开发者工作坊

诚邀报名 | 开源基础设施能力建设分论坛：打造开源生态的“心脏”

开放原子开发者工作坊

诚邀报名 | 编程语言分论坛：AI时代的技术革新与开源实践

开放原子开发者工作坊

所有评论(0)

查看更多评论

SiYuanFeng

@weixin_44151034

已为社区贡献9条内容

实现llava的【单轮对话】调整成【多轮对话】 （输入图片/多模态/多轮对话/llava）【多次单轮对话】

SiYuanFeng

使用llava时，将llava的单轮对话调整成多轮对话

先说好

方法一，直接对官方网站的quick start代码进行修改

方法二：使用bash结合基础的单轮对话代码进行修改

2.1 首先是最基础的llava官网代码回顾

2.2 伪多轮对话方法（每次新的prompt输入）

2.3 真正的多轮对话，也就是每次输入问题prompt的时候，把上次模型的回答（对话历史）也一起输入进去，可以把文件修改成这样：

方法三：多次单轮对话。

Step 1: 使用Python脚本生成一系列包含prompt的bash命令

Step 2: 修改后的 Shell 脚本逐行读取并执行命令

运行步骤

所有评论(0)

SiYuanFeng

实现llava的【单轮对话】调整成【多轮对话】（输入图片/多模态/多轮对话/llava）【多次单轮对话】