HF Model & Benchmark Matrix

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

Home/Orgs/allenai/allenai/open-instruct-self-instruct-7b

allenai/open-instruct-self-instruct-7b

family misc · 1 variants · unknown

provider: allenai
released: —
huggingface: https://huggingface.co/allenai/open-instruct-self-instruct-7b
best scores: MMLU: 35.7BBH: 29.9TydiQA: 35.4Codex-Eval: 6.2

Best scores per benchmark

benchmark	category	best score
MMLU	knowledge	35.7
TydiQA	knowledge	35.4
BBH	reasoning	29.9
Codex-Eval	coding	6.2

Variants (1)

variant	kind	quant	bits	vRAM	dl	org	year
open-instruct-self-instruct-7b	original	bf16	16.0		63	allenai	2023

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