DeepSeek-R1

Home/Models/unsloth/DeepSeek-R1

unsloth/DeepSeek-R1

kind: original
quant: bf16 (16-bit)
family: deepseek
modality: text-generation
root model: deepseek-ai/DeepSeek-R1
provider: unsloth
license: mit
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 71
likes: 52
created: —
last modified: 2025-04-23T07:21:47+00:00 (2025)
huggingface: https://huggingface.co/unsloth/DeepSeek-R1
tags: transformerssafetensorsdeepseek_v3text-generationdeepseekunslothconversationalcustom_codeenarxiv:2501.12948base_model:deepseek-ai/DeepSeek-R1base_model:finetune:deepseek-ai/DeepSeek-R1license:mittext-generation-inferenceendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
MATH-500	math	74.6		low	`\| GPT-4o-0513 \| 9.3 \| 13.4 \| 74.6 \| 49.9 \| 32.9 \| 759 \|`
GPQA Diamond	reasoning	49.9		low	`\| GPT-4o-0513 \| 9.3 \| 13.4 \| 74.6 \| 49.9 \| 32.9 \| 759 \|`
LiveCodeBench	coding	32.9		low	`\| GPT-4o-0513 \| 9.3 \| 13.4 \| 74.6 \| 49.9 \| 32.9 \| 759 \|`
MATH	math	16.0	Math	medium	`\| Math \| AIME 2024 (Pass@1) \| 16.0 \| 9.3 \| 39.2 \| 63.6 \| 79.2 \| 79.8 \|`
AIME 2024	math	9.3		low	`\| GPT-4o-0513 \| 9.3 \| 13.4 \| 74.6 \| 49.9 \| 32.9 \| 759 \|`

none scraped.