HF Model & Benchmark Matrix

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

open-instruct-baize-7b

allenai/open-instruct-baize-7b

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-generation
root model
allenai/open-instruct-baize-7b
provider
allenai
license
—
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
61
likes
0
created
—
last modified
2023-06-20T17:44:44+00:00 (2023)
huggingface
https://huggingface.co/allenai/open-instruct-baize-7b
tags
transformerspytorchllamatext-generationenarxiv:2306.04751arxiv:2302.13971arxiv:2304.01196text-generation-inferenceendpoints_compatibleregion:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
MMLUknowledge40.3GSM CoT | BBH CoT | TydiQA Closed-booklow| 40.3 | 38.6 | 3.5 | 5.5 | 30.6 | 32.4 | 29.8 | 7.9 | 12.2 | 23.8 | 23.5 | 22.6 |
BBHreasoning30.6GSM CoT | BBH CoT | TydiQA Closed-booklow| 40.3 | 38.6 | 3.5 | 5.5 | 30.6 | 32.4 | 29.8 | 7.9 | 12.2 | 23.8 | 23.5 | 22.6 |
TydiQAknowledge29.8GSM CoT | BBH CoT | TydiQA Closed-booklow| 40.3 | 38.6 | 3.5 | 5.5 | 30.6 | 32.4 | 29.8 | 7.9 | 12.2 | 23.8 | 23.5 | 22.6 |
Codex-Evalcoding12.2GSM CoT | BBH CoT | TydiQA Closed-booklow| 40.3 | 38.6 | 3.5 | 5.5 | 30.6 | 32.4 | 29.8 | 7.9 | 12.2 | 23.8 | 23.5 | 22.6 |

Discussions (0)

none scraped.

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