Text Classification
Transformers
Safetensors
English
qwen2
nvidia
qwen2.5
reward-model
text-embeddings-inference
Instructions to use nvidia/Qwen-2.5-Nemotron-32B-Reward with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/Qwen-2.5-Nemotron-32B-Reward with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="nvidia/Qwen-2.5-Nemotron-32B-Reward")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("nvidia/Qwen-2.5-Nemotron-32B-Reward") model = AutoModelForSequenceClassification.from_pretrained("nvidia/Qwen-2.5-Nemotron-32B-Reward", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 48eeadea41576ef600c5df19aac43c7fe6bf8c5d8bb7b7586a5bc4a0595b870b
- Size of remote file:
- 4.47 GB
- SHA256:
- f1dee916d46490bb0e60e6b2f664cd1fd68ba737f40d1ebfcc81b70c1738698e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.