Deepseek V2.5

🚀 DeepSeek-V2.5

DeepSeek-V2.5是结合了DeepSeek-V2-Chat和DeepSeek-Coder-V2-Instruct的升级版模型。该新模型整合了前两个版本的通用能力和编码能力。如需了解模型详情，请访问DeepSeek-V2页面获取更多信息。

🚀 快速开始

DeepSeek-V2.5能更好地契合人类偏好，并在写作和指令遵循等多个方面进行了优化：

📦 安装指南

若要使用BF16格式的DeepSeek-V2.5进行推理，需要80GB * 8的GPU。

使用Huggingface的Transformers进行推理

你可以直接使用Huggingface的Transformers进行模型推理。

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_name = "deepseek-ai/DeepSeek-V2.5"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
# `max_memory` 应根据你的设备进行设置
max_memory = {i: "75GB" for i in range(8)}
# `device_map` 不能设置为 `auto`
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, device_map="sequential", torch_dtype=torch.bfloat16, max_memory=max_memory, attn_implementation="eager")
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id

messages = [
    {"role": "user", "content": "Write a piece of quicksort code in C++"}
]
input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)

result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
print(result)

完整的聊天模板可以在Huggingface模型仓库的tokenizer_config.json中找到。

注意：与之前的DeepSeek-V2-Chat版本相比，聊天模板已更新。

聊天模板示例如下：

<｜begin▁of▁sentence｜><｜User｜>{user_message_1}<｜Assistant｜>{assistant_message_1}<｜end▁of▁sentence｜><｜User｜>{user_message_2}<｜Assistant｜>

你还可以添加一个可选的系统消息：

<｜begin▁of▁sentence｜>{system_message}<｜User｜>{user_message_1}<｜Assistant｜>{assistant_message_1}<｜end▁of▁sentence｜><｜User｜>{user_message_2}<｜Assistant｜>

使用vLLM进行推理（推荐）

若要使用vLLM进行模型推理，请将此Pull Request合并到你的vLLM代码库中：https://github.com/vllm-project/vllm/pull/4650。

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

max_model_len, tp_size = 8192, 8
model_name = "deepseek-ai/DeepSeek-V2.5"
tokenizer = AutoTokenizer.from_pretrained(model_name)
llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True, enforce_eager=True)
sampling_params = SamplingParams(temperature=0.3, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])

messages_list = [
    [{"role": "user", "content": "Who are you?"}],
    [{"role": "user", "content": "Translate the following content into Chinese directly: DeepSeek-V2 adopts innovative architectures to guarantee economical training and efficient inference."}],
    [{"role": "user", "content": "Write a piece of quicksort code in C++."}],
]

prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]

outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)

generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)

💻 使用示例

基础用法 - 函数调用

函数调用允许模型调用外部工具以增强其能力。

# 假设 `model` 和 `tokenizer` 已加载
model.generation_config = GenerationConfig(do_sample=False, max_new_tokens=128, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.eos_token_id)

tool_system_prompt = """You are a helpful Assistant.

## Tools

### Function

You have the following functions available:

- `get_current_weather`:
```json
{
    "name": "get_current_weather",
    "description": "Get the current weather in a given location",
    "parameters": {
        "type": "object",
        "properties": {
            "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
            },
            "unit": {
                "type": "string",
                "enum": [
                    "celsius",
                    "fahrenheit"
                ]
            }
        },
        "required": [
            "location"
        ]
    }
}
```"""

tool_call_messages = [{"role": "system", "content": tool_system_prompt}, {"role": "user", "content": "What's the weather like in Tokyo and Paris?"}]
tool_call_inputs = tokenizer.apply_chat_template(tool_call_messages, add_generation_prompt=True, return_tensors="pt")
tool_call_outputs = model.generate(tool_call_inputs.to(model.device))
# 生成的文本: '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>get_current_weather\n```json\n{"location": "Tokyo"}\n```<｜tool▁call▁end｜>\n<｜tool▁call▁begin｜>function<｜tool▁sep｜>get_current_weather\n```json\n{"location": "Paris"}\n```<｜tool▁call▁end｜><｜tool▁calls▁end｜><｜end▁of▁sentence｜>'

# 模拟调用 `get_current_weather` 的响应
tool_messages = [{"role": "tool", "content": '{"location": "Tokyo", "temperature": "10", "unit": null}'}, {"role": "tool", "content": '{"location": "Paris", "temperature": "22", "unit": null}'}]
tool_inputs = tokenizer.apply_chat_template(tool_messages, add_generation_prompt=False, return_tensors="pt")[:, 1:]
tool_inputs = torch.cat([tool_call_outputs, tool_inputs.to(model.device)], dim=1)
tool_outputs = model.generate(tool_inputs)
# 生成的文本: The current weather in Tokyo is 10 degrees, and in Paris, it is 22 degrees.<｜end▁of▁sentence｜>

高级用法 - JSON输出

你可以使用JSON输出模式确保模型生成有效的JSON对象。要激活此模式，应在系统提示中添加一条特殊指令。

# 假设 `model` 和 `tokenizer` 已加载
model.generation_config = GenerationConfig(do_sample=False, max_new_tokens=128, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.eos_token_id)

user_system_prompt = 'The user will provide some exam text. Please parse the "question" and "answer" and output them in JSON format.'
json_system_prompt = f"""{user_system_prompt}

## Response Format

Reply with JSON object ONLY."""

json_messages = [{"role": "system", "content": json_system_prompt}, {"role": "user", "content": "Which is the highest mountain in the world? Mount Everest."}]
json_inputs = tokenizer.apply_chat_template(json_messages, add_generation_prompt=True, return_tensors="pt")
json_outpus = model.generate(json_inputs.to(model.device))
# 生成的文本: '```json\n{\n  "question": "Which is the highest mountain in the world?",\n  "answer": "Mount Everest."\n}\n```<｜end▁of▁sentence｜>'

高级用法 - FIM补全

在FIM（填充中间内容）补全中，你可以提供一个前缀和一个可选的后缀，模型将补全中间的内容。

# 假设 `model` 和 `tokenizer` 已加载
model.generation_config = GenerationConfig(do_sample=False, max_new_tokens=128, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.eos_token_id)

prefix = """def quick_sort(arr):
    if len(arr) <= 1:
        return arr
    pivot = arr[0]
    left = []
    right = []
"""

suffix = """
        if arr[i] < pivot:
            left.append(arr[i])
        else:
            right.append(arr[i])
    return quick_sort(left) + [pivot] + quick_sort(right)"""

fim_prompt = f"<｜fim▁begin｜>{prefix}<｜fim▁hole｜>{suffix}<｜fim▁end｜>"
fim_inputs = tokenizer(fim_prompt, add_special_tokens=True, return_tensors="pt").input_ids
fim_outputs = model.generate(fim_inputs.to(model.device))
# 生成的文本: "    for i in range(1, len(arr)):<｜end▁of▁sentence｜>"

📄 许可证

此代码仓库遵循MIT许可证。DeepSeek-V2基础/聊天模型的使用需遵循模型许可证。DeepSeek-V2系列（包括基础版和聊天版）支持商业使用。

📚 详细文档

引用信息

@misc{deepseekv2,
      title={DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model}, 
      author={DeepSeek-AI},
      year={2024},
      eprint={2405.04434},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

📞 联系我们

如果您有任何问题，请提出问题或通过service@deepseek.com与我们联系。