Cosmos-Reason1-7B
nvidia/Cosmos-Reason1-7B
- kind
- original
- quant
- bf16 (16-bit)
- family
- misc
- modality
- image-text-to-text
- root model
- Qwen/Qwen2.5-VL-7B-Instruct
- provider
- nvidia
- license
- other
- language
- en
- context
- —
- library
- transformers
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 28,385
- likes
- 243
- created
- —
- last modified
- 2025-12-10T00:08:29+00:00 (2025)
- huggingface
- https://huggingface.co/nvidia/Cosmos-Reason1-7B
- tags
- transformerssafetensorsqwen2_5_vlimage-text-to-textnvidiacosmosconversationalendataset:nvidia/Cosmos-Reason1-SFT-Datasetdataset:nvidia/Cosmos-Reason1-RL-Datasetdataset:nvidia/Cosmos-Reason1-Benchmarkarxiv:2503.15558base_model:Qwen/Qwen2.5-VL-7B-Instructbase_model:finetune:Qwen/Qwen2.5-VL-7B-Instructlicense:othertext-generation-inferenceendpoints_compatibledeploy:azureregion:us
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.