Conda环境运行本地模型

conda安装：https://www.anaconda.com/docs/getting-started/miniconda/main

> conda --version
> conda create -n ai-dev python=3.11 -y
> conda activate ai-dev

modelscope安装及模型下载

> pip install modelscope
> modelscope download --model Qwen/Qwen3-0.6B --local_dir /home/llm/models/qwen0.6

模型下载

> modelscope download --model Qwen/Qwen3-0.6B --local_dir /home/llm/models/qwen0.6
> modelscope download --model Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice --local_dir /home/llm/models/qwen3-tts-0.6b

测试：test.py

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch


class ChatHandler:
    def __init__(self, model_path="/home/llm/models/qwen0.6"):
        """
        初始化聊天模型处理器

        Args:
            model_path: 本地模型路径
        """
        self.model_path = model_path
        self.tokenizer = None
        self.model = None
        self._load_model()

    def _load_model(self):
        """
        加载模型和分词器
        """
        print(f"加载模型: {self.model_path}")

        # 加载tokenizer
        self.tokenizer = AutoTokenizer.from_pretrained(
            self.model_path,
            trust_remote_code=True,
            padding_side="right"
        )

        # 加载模型
        self.model = AutoModelForCausalLM.from_pretrained(
            self.model_path,
            dtype=torch.float16,
            device_map="auto",
            trust_remote_code=True
        )
        print("模型加载完成")

    def generate_response(self, messages, max_new_tokens=1024):
        """
        生成模型回复

        Args:
            messages: 对话消息列表，格式为[{"role": "user", "content": "消息内容"}]
            max_new_tokens: 最大生成token数，默认值增大以避免回复被截断

        Returns:
            str: 回复内容
        """
        # 确保生成的回复不会被截断
        if max_new_tokens < 512:
            max_new_tokens = 512
        # 构造对话
        text = self.tokenizer.apply_chat_template(
            messages, tokenize=False, add_generation_prompt=True, enable_thinking=False
        )
        inputs = self.tokenizer(text, return_tensors="pt").to(self.model.device)

        # 生成回复
        outputs = self.model.generate(**inputs, max_new_tokens=max_new_tokens)

        # 解码回复
        response = self.tokenizer.decode(
            outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True
        )

        return response

环境依赖导出

> conda env export --no-builds > environment.yml

environment.yml

name: ai-dev
channels:
  - defaults
dependencies:
  - _libgcc_mutex=0.1
  - _openmp_mutex=5.1
  - bzip2=1.0.8
  - ca-certificates=2025.12.2
  - expat=2.7.3
  - ld_impl_linux-64=2.44
  - libexpat=2.7.3
  - libffi=3.4.4
  - libgcc=15.2.0
  - libgcc-ng=15.2.0
  - libgomp=15.2.0
  - libnsl=2.0.0
  - libstdcxx=15.2.0
  - libstdcxx-ng=15.2.0
  - libuuid=1.41.5
  - libxcb=1.17.0
  - libzlib=1.3.1
  - ncurses=6.5
  - openssl=3.0.18
  - packaging=25.0
  - pip=25.3
  - pthread-stubs=0.3
  - python=3.11.14
  - readline=8.3
  - setuptools=80.10.1
  - sqlite=3.51.1
  - tk=8.6.15
  - tzdata=2025c
  - wheel=0.46.3
  - xorg-libx11=1.8.12
  - xorg-libxau=1.0.12
  - xorg-libxdmcp=1.1.5
  - xorg-xorgproto=2024.1
  - xz=5.6.4
  - zlib=1.3.1
  - pip:
      - accelerate==1.12.0
      - aiofiles==24.1.0
      - aiohappyeyeballs==2.6.1
      - aiohttp==3.13.3
      - aiosignal==1.4.0
      - annotated-doc==0.0.4
      - annotated-types==0.7.0
      - anyio==4.12.1
      - attrs==25.4.0
      - audioread==3.1.0
      - brotli==1.2.0
      - certifi==2026.1.4
      - cffi==2.0.0
      - charset-normalizer==3.4.4
      - click==8.3.1
      - coloredlogs==15.0.1
      - cuda-bindings==12.9.4
      - cuda-pathfinder==1.3.3
      - datasets==4.5.0
      - decorator==5.2.1
      - dill==0.4.0
      - einops==0.8.2
      - fastapi==0.128.0
      - ffmpy==1.0.0
      - filelock==3.20.3
      - flatbuffers==25.12.19
      - frozenlist==1.8.0
      - fsspec==2025.10.0
      - gradio==6.5.1
      - gradio-client==2.0.3
      - groovy==0.1.2
      - h11==0.16.0
      - hf-xet==1.2.0
      - httpcore==1.0.9
      - httpx==0.28.1
      - huggingface-hub==0.36.0
      - humanfriendly==10.0
      - idna==3.11
      - jinja2==3.1.6
      - joblib==1.5.3
      - lazy-loader==0.4
      - librosa==0.11.0
      - llvmlite==0.46.0
      - markdown-it-py==4.0.0
      - markupsafe==3.0.3
      - mdurl==0.1.2
      - modelscope==1.34.0
      - mpmath==1.3.0
      - msgpack==1.1.2
      - multidict==6.7.1
      - multiprocess==0.70.18
      - networkx==3.6.1
      - numba==0.63.1
      - numpy==2.3.5
      - nvidia-cublas-cu12==12.8.4.1
      - nvidia-cuda-cupti-cu12==12.8.90
      - nvidia-cuda-nvrtc-cu12==12.8.93
      - nvidia-cuda-runtime-cu12==12.8.90
      - nvidia-cudnn-cu12==9.10.2.21
      - nvidia-cufft-cu12==11.3.3.83
      - nvidia-cufile-cu12==1.13.1.3
      - nvidia-curand-cu12==10.3.9.90
      - nvidia-cusolver-cu12==11.7.3.90
      - nvidia-cusparse-cu12==12.5.8.93
      - nvidia-cusparselt-cu12==0.7.1
      - nvidia-nccl-cu12==2.27.5
      - nvidia-nvjitlink-cu12==12.8.93
      - nvidia-nvshmem-cu12==3.4.5
      - nvidia-nvtx-cu12==12.8.90
      - onnxruntime==1.23.2
      - orjson==3.11.6
      - pandas==3.0.0
      - peft==0.18.1
      - pillow==12.1.0
      - platformdirs==4.5.1
      - pooch==1.9.0
      - propcache==0.4.1
      - protobuf==6.33.5
      - psutil==7.2.2
      - pyarrow==23.0.0
      - pycparser==3.0
      - pydantic==2.12.5
      - pydantic-core==2.41.5
      - pydub==0.25.1
      - pygments==2.19.2
      - python-dateutil==2.9.0.post0
      - python-multipart==0.0.22
      - pytz==2025.2
      - pyyaml==6.0.3
      - qwen-tts==0.0.5
      - regex==2026.1.15
      - requests==2.32.5
      - rich==14.3.1
      - safehttpx==0.1.7
      - safetensors==0.7.0
      - scikit-learn==1.8.0
      - scipy==1.17.0
      - semantic-version==2.10.0
      - shellingham==1.5.4
      - six==1.17.0
      - soundfile==0.13.1
      - sox==1.5.0
      - soxr==1.0.0
      - starlette==0.50.0
      - sympy==1.14.0
      - threadpoolctl==3.6.0
      - tokenizers==0.22.2
      - tomlkit==0.13.3
      - torch==2.10.0
      - torchaudio==2.10.0
      - torchvision==0.25.0
      - tqdm==4.67.1
      - transformers==4.57.3
      - triton==3.6.0
      - typer==0.21.1
      - typer-slim==0.21.1
      - typing-extensions==4.15.0
      - typing-inspection==0.4.2
      - urllib3==2.6.3
      - uvicorn==0.40.0
      - xxhash==3.6.0
      - yarl==1.22.0
prefix: /root/miniconda3/envs/ai-dev