HF Model & Benchmark Matrix

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

tulu-7b

allenai/tulu-7b

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-generation
root model
allenai/tulu-7b
provider
allenai
license
—
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
75
likes
9
created
—
last modified
2023-06-20T17:47:54+00:00 (2023)
huggingface
https://huggingface.co/allenai/tulu-7b
tags
transformerspytorchllamatext-generationendataset:databricks/databricks-dolly-15kdataset:OpenAssistant/oasst1dataset:sahil2801/CodeAlpaca-20karxiv:2306.04751arxiv:2302.13971arxiv:2301.13688arxiv:2304.07327arxiv:2304.03277text-generation-inferenceendpoints_compatibleregion:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
TydiQAknowledge45.7GSM CoT | BBH CoT | TydiQA Closed-booklow| 44.5 | 47.0 | 6.0 | 27.0 | 38.1 | 39.2 | 45.7 | 7.7 | 17.5 | 27.8 | 48.3 | 33.1 |
MMLUknowledge44.5GSM CoT | BBH CoT | TydiQA Closed-booklow| 44.5 | 47.0 | 6.0 | 27.0 | 38.1 | 39.2 | 45.7 | 7.7 | 17.5 | 27.8 | 48.3 | 33.1 |
BBHreasoning38.1GSM CoT | BBH CoT | TydiQA Closed-booklow| 44.5 | 47.0 | 6.0 | 27.0 | 38.1 | 39.2 | 45.7 | 7.7 | 17.5 | 27.8 | 48.3 | 33.1 |
Codex-Evalcoding17.5GSM CoT | BBH CoT | TydiQA Closed-booklow| 44.5 | 47.0 | 6.0 | 27.0 | 38.1 | 39.2 | 45.7 | 7.7 | 17.5 | 27.8 | 48.3 | 33.1 |

Discussions (0)

none scraped.

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