HF Model & Benchmark Matrix

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

phixtral-4x2_8-GPTQ

TheBloke/phixtral-4x2_8-GPTQ

kind
gptq
quant
gptq
family
misc
modality
text-generation
root model
mlabonne/phixtral-4x2_8
provider
TheBloke
license
mit
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
52
likes
24
created
—
last modified
2024-01-11T15:36:02+00:00 (2024)
huggingface
https://huggingface.co/TheBloke/phixtral-4x2_8-GPTQ
tags
transformerssafetensorsphi-msfttext-generationmoenlpcodecognitivecomputations/dolphin-2_6-phi-2lxuechen/phi-2-dpoYhyu13/phi-2-sft-dpo-gpt4_en-ep1mrm8488/phi-2-coderconversationalcustom_codeenbase_model:mlabonne/phixtral-4x2_8base_model:quantized:mlabonne/phixtral-4x2_8license:mit4-bitgptqregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
TruthfulQAsafety48.78low| [**phixtral-4x2_8**](https://huggingface.co/mlabonne/phixtral-4x2_8) | **33.91** | **70.44** | **48.78** | **37.68** | **47.7** |
BigBenchreasoning37.68low| [**phixtral-4x2_8**](https://huggingface.co/mlabonne/phixtral-4x2_8) | **33.91** | **70.44** | **48.78** | **37.68** | **47.7** |
AGIEvalreasoning33.91low| [**phixtral-4x2_8**](https://huggingface.co/mlabonne/phixtral-4x2_8) | **33.91** | **70.44** | **48.78** | **37.68** | **47.7** |

Discussions (0)

none scraped.

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