HF Model & Benchmark Matrix

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

Luna-AI-Llama2-Uncensored-GPTQ

TheBloke/Luna-AI-Llama2-Uncensored-GPTQ

kind
gptq
quant
gptq
family
llama
modality
text-generation
root model
Tap-M/Luna-AI-Llama2-Uncensored
provider
TheBloke
license
cc-by-sa-4.0
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
69
likes
86
created
—
last modified
2023-09-27T12:44:51+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GPTQ
tags
transformerssafetensorsllamatext-generationbase_model:Tap-M/Luna-AI-Llama2-Uncensoredbase_model:quantized:Tap-M/Luna-AI-Llama2-Uncensoredlicense:cc-by-sa-4.0text-generation-inference4-bitgptqregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
ARC-Challengeknowledge55.12_challengemedium| arc_challenge | 0 | acc_norm | 0.5512 | 0.0146 |
TruthfulQAsafety47.16_mcmedium| truthfulqa_mc | 1 | mc2 | 0.4716 | 0.0155 |
MMLUknowledge3.6medium| mmlu | 1 | acc_norm | 0.46521 | 0.036 |

Discussions (0)

none scraped.

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