HF Model & Benchmark Matrix

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

Home/Models/nvidia/Nemotron-4-340B-Base

Nemotron-4-340B-Base

nvidia/Nemotron-4-340B-Base

kind: original
quant: bf16 (16-bit)
family: nemotron
modality: —
root model: nvidia/Nemotron-4-340B-Base
provider: nvidia
license: other
language: —
context: 4,096
library: nemo
vRAM (GB): —
size on disk: —
downloads: 266
likes: 150
created: —
last modified: 2024-06-28T04:59:08+00:00 (2024)
huggingface: https://huggingface.co/nvidia/Nemotron-4-340B-Base
tags: nemonvidialicense:otherregion:us

Benchmark scores (4)

benchmark	category	score	context	conf	evidence
ARC-Challenge	knowledge	94.28		low	`\| 90.53 \| 89.50 \| 85.44 \| 94.28 \|`
HellaSwag	knowledge	90.53		low	`\| 90.53 \| 89.50 \| 85.44 \| 94.28 \|`
WinoGrande	knowledge	89.5		low	`\| 90.53 \| 89.50 \| 85.44 \| 94.28 \|`
BBH	reasoning	85.44		low	`\| 90.53 \| 89.50 \| 85.44 \| 94.28 \|`

Discussions (0)

none scraped.

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