Text Classification
Transformers
Safetensors
qwen3
reward-model
rlhf
dpo
alignment
wildchat
text-embeddings-inference
Instructions to use THU-KEG/WildReward-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use THU-KEG/WildReward-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="THU-KEG/WildReward-4B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("THU-KEG/WildReward-4B") model = AutoModelForSequenceClassification.from_pretrained("THU-KEG/WildReward-4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download merges.txt from THU-KEG/WildReward-4B: direct link, hf CLI and curl.
- Browser
- Download file 1.67 MB
-
https://huggingface.co/THU-KEG/WildReward-4B/resolve/main/merges.txt
- Command line
-
hf download hf://THU-KEG/WildReward-4B/merges.txt
-
curl -L -o merges.txt https://huggingface.co/THU-KEG/WildReward-4B/resolve/main/merges.txt
1.67 MB
File too large to display, you can check the raw version instead.