67 lines
1.7 KiB
Markdown
67 lines
1.7 KiB
Markdown
|
||
# 魔搭环境配置
|
||
## 核心信息
|
||
|
||
- 高带宽机器推荐命令行下载，支持断电断续和高速下载
|
||
|
||
## 环境安装
|
||
|
||
```bash
|
||
pip install modelscope
|
||
```
|
||
|
||
|
||
## 模型下载
|
||
|
||
### 命令行下载（推荐）
|
||
|
||
```bash
|
||
modelscope download --model="Qwen/Qwen2.5-0.5B-Instruct" --local_dir ./model-dir
|
||
```
|
||
|
||
### SDK 下载
|
||
```python
|
||
from modelscope import snapshot_download model_dir = snapshot_download("Qwen/Qwen2.5-0.5B-Instruct")
|
||
```
|
||
|
||
### Git LFS 下载
|
||
```bash
|
||
git lfs install
|
||
git clone https://www.modelscope.cn/Qwen/Qwen2.5-0.5B-Instruct.git
|
||
```
|
||
|
||
|
||
## 模型加载
|
||
|
||
### AutoModel
|
||
|
||
ModelScope 支持原生 pipeline 推理，同时也兼容了由Transformers，Diffusers等提供的AutoModel和Pipeline的加载
|
||
|
||
```bash
|
||
pip install transformers
|
||
```
|
||
|
||
```python
|
||
from modelscope import AutoModelForCausalLM, AutoTokenizer
|
||
|
||
model_name = "Qwen/Qwen2.5-0.5B-Instruct"
|
||
|
||
model = AutoModelForCausalLM.from_pretrained(
|
||
model_name,
|
||
torch_dtype="auto",
|
||
device_map="auto"
|
||
)
|
||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
```
|
||
|
||
### 使用 ModelScope pipeline 加载模型
|
||
```python
|
||
from modelscope.pipelines import pipeline
|
||
word_segmentation = pipeline('word-segmentation',model='damo/nlp_structbert_word-segmentation_chinese-base')
|
||
```
|
||
|
||
## 模型推理
|
||
|
||
```python
|
||
from modelscope.pipelines import pipeline from modelscope.utils.constant import Tasks inference_pipeline = pipeline( task=Tasks.auto_speech_recognition, model='iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch', model_revision="v2.0.4") rec_result = inference_pipeline('https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_vad_punc_example.wav') print(rec_result)
|
||
``` |