HF Model & Benchmark Matrix

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

DLER-R1-1.5B-Research

nvidia/DLER-R1-1.5B-Research

kind
original
quant
bf16 (16-bit)
family
misc
modality
—
root model
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
provider
nvidia
license
—
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
550
likes
19
created
—
last modified
2025-10-25T06:19:56+00:00 (2025)
huggingface
https://huggingface.co/nvidia/DLER-R1-1.5B-Research
tags
safetensorsqwen2endataset:agentica-org/DeepScaleR-Preview-Datasetarxiv:2510.15110base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5Bbase_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5Bregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
MATHmath84.31low| Deepseek-R1-1.5B | 84.31 | 5500 | 29.79 | 16916 | 61.97 | 10967 | 38.41 | 7494 | 44.07 | 11620 | 10499 |

Discussions (0)

none scraped.

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