HF Model & Benchmark Matrix

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

phixtral-2x2_8

mlabonne/phixtral-2x2_8

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-generation
root model
cognitivecomputations/dolphin-2_6-phi-2
provider
mlabonne
license
mit
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
60
likes
150
created
—
last modified
2024-01-14T10:52:51+00:00 (2024)
huggingface
https://huggingface.co/mlabonne/phixtral-2x2_8
tags
transformerssafetensorsphi-msfttext-generationmoenlpcodecognitivecomputations/dolphin-2_6-phi-2lxuechen/phi-2-dpoconversationalcustom_codeenlicense:mitregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
TruthfulQAsafety48.78low| [**phixtral-2x2_8**](https://huggingface.co/mlabonne/phixtral-2x2_8) | **34.1** | **70.44** | **48.78** | **37.82** | **47.78** |
BigBenchreasoning37.82low| [**phixtral-2x2_8**](https://huggingface.co/mlabonne/phixtral-2x2_8) | **34.1** | **70.44** | **48.78** | **37.82** | **47.78** |
AGIEvalreasoning34.1low| [**phixtral-2x2_8**](https://huggingface.co/mlabonne/phixtral-2x2_8) | **34.1** | **70.44** | **48.78** | **37.82** | **47.78** |

Discussions (0)

none scraped.

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