r1-1776-distill-llama-70b-GGUF

Home/Models/unsloth/r1-1776-distill-llama-70b-GGUF

unsloth/r1-1776-distill-llama-70b-GGUF

kind: gguf
quant: gguf (16-bit)
family: llama
modality: text-generation
root model: perplexity-ai/r1-1776-distill-llama-70b
provider: unsloth
license: mit
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 2,342
likes: 24
created: —
last modified: 2025-02-27T01:55:59+00:00 (2025)
huggingface: https://huggingface.co/unsloth/r1-1776-distill-llama-70b-GGUF
tags: transformersggufllamatext-generationdeepseekdeepseek_v3unslothenarxiv:2501.12948base_model:perplexity-ai/r1-1776-distill-llama-70bbase_model:quantized:perplexity-ai/r1-1776-distill-llama-70blicense:mitendpoints_compatibleregion:usconversational

benchmark	category	score	context	conf	evidence
MATH-500	math	94.5	MATH-500	medium	`\| MATH-500 \| 94.5 \| 94.8 \|`
MMLU	knowledge	88.52	MMLU	medium	`\| MMLU \| 88.52 * \| 88.40 \|`
DROP	reasoning	84.55	DROP	medium	`\| DROP \| 84.55 * \| 84.83 \|`
AIME 2024	math	70.0	AIME 2024	medium	`\| AIME 2024 \| 70 \| 70 \|`
GPQA	reasoning	65.2	GPQA	medium	`\| GPQA \| 65.2 \| 65.05 \|`

none scraped.