Qwen-2.5-Nemotron-32B-Reward
nvidia/Qwen-2.5-Nemotron-32B-Reward
- kind
- original
- quant
- bf16 (16-bit)
- family
- qwen
- modality
- text-classification
- root model
- Qwen/Qwen2.5-32B-Instruct
- provider
- nvidia
- license
- other
- language
- en
- context
- —
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 85
- likes
- 3
- created
- —
- last modified
- 2025-06-26T17:54:01+00:00 (2025)
- huggingface
- https://huggingface.co/nvidia/Qwen-2.5-Nemotron-32B-Reward
- tags
- transformerssafetensorsqwen2text-classificationnvidiaqwen2.5reward-modelendataset:nvidia/HelpSteer2dataset:nvidia/HelpSteer3arxiv:2505.11475arxiv:2410.01257arxiv:2410.16184base_model:Qwen/Qwen2.5-32B-Instructbase_model:finetune:Qwen/Qwen2.5-32B-Instructlicense:othertext-embeddings-inferenceregion:us
Benchmark scores (1)
Discussions (0)
none scraped.