HF Model & Benchmark Matrix

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

open-instruct-human-mix-65b

allenai/open-instruct-human-mix-65b

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-generation
root model
allenai/open-instruct-human-mix-65b
provider
allenai
license
—
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
158
likes
4
created
—
last modified
2023-06-29T18:51:34+00:00 (2023)
huggingface
https://huggingface.co/allenai/open-instruct-human-mix-65b
tags
transformerspytorchllamatext-generationendataset:databricks/databricks-dolly-15kdataset:OpenAssistant/oasst1arxiv:2306.04751arxiv:2302.13971arxiv:2301.13688arxiv:2304.07327text-generation-inferenceendpoints_compatibleregion:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
MMLUknowledge60.7GSM CoT | BBH CoT | TydiQA Closed-booklow| 60.7 | 61.6 | 8.0 | 57.5 | 50.1 | 52.7 | 58.5 | 15.9 | 24.5 | 43.2 | 46.5 | 43.8 |
TydiQAknowledge58.5GSM CoT | BBH CoT | TydiQA Closed-booklow| 60.7 | 61.6 | 8.0 | 57.5 | 50.1 | 52.7 | 58.5 | 15.9 | 24.5 | 43.2 | 46.5 | 43.8 |
BBHreasoning50.1GSM CoT | BBH CoT | TydiQA Closed-booklow| 60.7 | 61.6 | 8.0 | 57.5 | 50.1 | 52.7 | 58.5 | 15.9 | 24.5 | 43.2 | 46.5 | 43.8 |
Codex-Evalcoding24.5GSM CoT | BBH CoT | TydiQA Closed-booklow| 60.7 | 61.6 | 8.0 | 57.5 | 50.1 | 52.7 | 58.5 | 15.9 | 24.5 | 43.2 | 46.5 | 43.8 |

Discussions (0)

none scraped.

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