Text Classification
Transformers
Safetensors
English
qwen3
code
reward-model
multilingual
text-embeddings-inference
Instructions to use project-themis/Themis-RM-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use project-themis/Themis-RM-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="project-themis/Themis-RM-4B")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("project-themis/Themis-RM-4B") model = AutoModelForSequenceClassification.from_pretrained("project-themis/Themis-RM-4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 2dc672afa158ebf879912635a56dbe7c8c56c0a25c7ed8eab0681f4c09f32de8
- Size of remote file:
- 4.99 GB
- SHA256:
- d0aeb31c4a5b2bceda0f667f1228cda9005b1d585ae55ea1a61a91e3542ea6a9
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.