Text Classification
Transformers
Safetensors
Chinese
bert
sentiment-analysis
chinese
text-embeddings-inference
Instructions to use bruceant/game-sentiment-student-v8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bruceant/game-sentiment-student-v8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="bruceant/game-sentiment-student-v8")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("bruceant/game-sentiment-student-v8") model = AutoModelForSequenceClassification.from_pretrained("bruceant/game-sentiment-student-v8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
game-sentiment-student-v8
游戏相关中文评论 / 博文情感三分类(负面 / 中性 / 正面)。 底座:IDEA-CCNL/Erlangshen-Roberta-110M-Sentiment,序列长度 256。
标签与 config.json 中 id2label 一致:0 负面、1 中性、2 正面。
v8 训练时在正文前加了平台前缀。推理时请使用同一套前缀,否则分布和训练不一致:
[微博博文][微博评论][B站评论]- 其他或未知来源用
[未知]
仅供个人学习和研究使用。
from transformers import AutoModelForSequenceClassification, AutoTokenizer
repo = "bruceant/game-sentiment-student-v8"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForSequenceClassification.from_pretrained(repo)
python run_student.py --model bruceant/game-sentiment-student-v8 --text "[微博评论] 这游戏太坑了"
- Downloads last month
- 24
Model tree for bruceant/game-sentiment-student-v8
Base model
IDEA-CCNL/Erlangshen-Roberta-110M-Sentiment