HF Model & Benchmark Matrix

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

laser-dolphin-mixtral-2x7b-dpo-GGUF

TheBloke/laser-dolphin-mixtral-2x7b-dpo-GGUF

kind
gguf
quant
gguf (2-bit)
family
mistral
modality
—
root model
macadeliccc/laser-dolphin-mixtral-2x7b-dpo
provider
TheBloke
license
apache-2.0
language
—
context
32768,
library
transformers
vRAM (GB)
—
size on disk
—
downloads
1,631
likes
50
created
—
last modified
2024-01-15T16:40:16+00:00 (2024)
huggingface
https://huggingface.co/TheBloke/laser-dolphin-mixtral-2x7b-dpo-GGUF
tags
transformersggufmixtralarxiv:2312.13558base_model:macadeliccc/laser-dolphin-mixtral-2x7b-dpobase_model:quantized:macadeliccc/laser-dolphin-mixtral-2x7b-dpolicense:apache-2.0region:us

Benchmark scores (5)

benchmarkcategoryscorecontextconfevidence
BoolQknowledge86.94medium| boolq | Yaml | none | 0 | acc | 0.8694 | ± | 0.0059 |
PIQAknowledge82.1medium| piqa | Yaml | none | 0 | acc | 0.8210 | ± | 0.0089 |
WinoGrandeknowledge75.77medium| winogrande | Yaml | none | 0 | acc | 0.7577 | ± | 0.0120 |
HellaSwagknowledge64.84medium| hellaswag | Yaml | none | 0 | acc | 0.6484 | ± | 0.0048 |
OpenBookQAknowledge35.0medium| openbookqa | Yaml | none | 0 | acc | 0.3500 | ± | 0.0214 |

Discussions (0)

none scraped.

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