HF Model & Benchmark Matrix

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

GML-Mistral-merged-v1

mlabonne/GML-Mistral-merged-v1

kind
merge
quant
merge
family
mistral
modality
text-generation
root model
mlabonne/GML-Mistral-merged-v1
provider
mlabonne
license
apache-2.0
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
93
likes
1
created
—
last modified
2024-03-04T15:14:25+00:00 (2024)
huggingface
https://huggingface.co/mlabonne/GML-Mistral-merged-v1
tags
transformerssafetensorsmistraltext-generationmergemergekitlicense:apache-2.0model-indextext-generation-inferenceendpoints_compatibleregion:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
WinoGrandeknowledge73.88Winogrande (5-shot)medium| Winogrande (5-shot) | 73.88 |
MMLUknowledge64.13MMLU (5-Shot)medium| MMLU (5-Shot) | 64.13 |
HellaSwagknowledge57.89HellaSwag (10-Shot)medium| HellaSwag (10-Shot) | 57.89 |
TruthfulQAsafety51.58TruthfulQA (0-shot)medium| TruthfulQA (0-shot) | 51.58 |

Discussions (0)

none scraped.

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