Downloads · 30 days
0
dean2023/cn-roberta-wwm-ext-car
cn-roberta-wwm-ext-car is a zero-shot classification model from dean2023. Use it when you need labels you did not train the model on. It is set up for transformers. The card lists the license as mit.
基于 hfl/chinese-roberta-wwm-ext 的领域适配训练模型,支持ONNX推理和RK3588芯片部署。
Downloads · 30 days
0
Access
Public
Updated Feb 23, 2025
Repo size
617 MB
Likes
0
Public
Click a slice to open those files.
.onnx409 MB · 66%
From the Hugging Face model README
基于 hfl/chinese-roberta-wwm-ext 的领域适配训练模型,支持ONNX推理和RK3588芯片部署。
本模型是基于 RoBERTa-wwm-ext 架构,在汽车领域中文文本数据上进行微调的预训练语言模型,特点包括:
✅ 领域适配:使用汽车论坛、维修手册等专业语料微调
✅ 部署友好:提供量化后的ONNX/RKNN模型
✅ 硬件加速:RKNN模型针对NPU计算单元优化
| 格式 | 最低要求 |
|---|---|
| PyTorch | CPU / NVIDIA GPU (显存 ≥4GB) |
| ONNX | 支持ONNX Runtime的CPU/GPU环境 |
| RKNN | Rockchip RK3588开发板 |
pip install -r requirements.txt
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("dean2023/cn-roberta-wwm-ext-car")
model = AutoModelForSequenceClassification.from_pretrained("dean2023/cn-roberta-wwm-ext-car")
inputs = tokenizer("发动机异响可能的原因有哪些?", return_tensors="pt")
outputs = model(**inputs)
from rknnlite.api import RKNNLite
rknn = RKNNLite()
rknn.load_rknn('./models/cn_roberta_v1.rknn')
rknn.init_runtime()
If you want to go further, please refer to the code.