HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

DLER-R1-7B-Research

nvidia/DLER-R1-7B-Research

kind
original
quant
bf16 (16-bit)
family
misc
modality
—
root model
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
provider
nvidia
license
—
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
85
likes
16
created
—
last modified
2025-10-25T06:20:13+00:00 (2025)
huggingface
https://huggingface.co/nvidia/DLER-R1-7B-Research
tags
safetensorsqwen2endataset:agentica-org/DeepScaleR-Preview-Datasetarxiv:2510.15110base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-7Bbase_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-7Bregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
MATHmath93.6low| Deepseek-R1-7B | 93.60 | 3999 | 55.40 | 13241 | 82.90 | 7461 | 49.79 | 5199 | 58.21 | 8837 | 7747 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.