HF Model & Benchmark Matrix

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

open-instruct-oasst1-7b

allenai/open-instruct-oasst1-7b

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-generation
root model
allenai/open-instruct-oasst1-7b
provider
allenai
license
—
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
60
likes
0
created
—
last modified
2023-06-20T17:44:05+00:00 (2023)
huggingface
https://huggingface.co/allenai/open-instruct-oasst1-7b
tags
transformerspytorchllamatext-generationendataset:OpenAssistant/oasst1arxiv:2306.04751arxiv:2302.13971arxiv:2304.07327text-generation-inferenceendpoints_compatibleregion:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
MMLUknowledge32.9GSM CoT | BBH CoT | TydiQA Closed-booklow| 32.9 | 29.7 | 6.0 | 6.5 | 20.4 | 29.5 | 26.8 | 7.8 | 10.1 | 20.4 | 47.8 | 23.8 |
TydiQAknowledge26.8GSM CoT | BBH CoT | TydiQA Closed-booklow| 32.9 | 29.7 | 6.0 | 6.5 | 20.4 | 29.5 | 26.8 | 7.8 | 10.1 | 20.4 | 47.8 | 23.8 |
BBHreasoning20.4GSM CoT | BBH CoT | TydiQA Closed-booklow| 32.9 | 29.7 | 6.0 | 6.5 | 20.4 | 29.5 | 26.8 | 7.8 | 10.1 | 20.4 | 47.8 | 23.8 |
Codex-Evalcoding10.1GSM CoT | BBH CoT | TydiQA Closed-booklow| 32.9 | 29.7 | 6.0 | 6.5 | 20.4 | 29.5 | 26.8 | 7.8 | 10.1 | 20.4 | 47.8 | 23.8 |

Discussions (0)

none scraped.

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