HF Model & Benchmark Matrix

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

Iambe-RP-v3-20B-GGUF

TheBloke/Iambe-RP-v3-20B-GGUF

kind
gguf
quant
gguf (2-bit)
family
misc
modality
—
root model
athirdpath/Iambe-RP-v3-20b
provider
TheBloke
license
cc-by-nc-4.0
language
en
context
4096,
library
—
vRAM (GB)
—
size on disk
—
downloads
89
likes
8
created
—
last modified
2024-01-04T11:36:50+00:00 (2024)
huggingface
https://huggingface.co/TheBloke/Iambe-RP-v3-20B-GGUF
tags
transformersggufllamanot-for-all-audiencesendataset:athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW-v1base_model:athirdpath/Iambe-RP-v3-20bbase_model:quantized:athirdpath/Iambe-RP-v3-20blicense:cc-by-nc-4.0region:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
WinoGrandeknowledge73.8medium| winogrande | Yaml | none | 5 | acc | 0.738 | ± | 0.0124 |
TruthfulQAsafety55.51_mc2medium| truthfulqa_mc2 | Yaml | none | 0 | acc | 0.5551 | ± | 0.0158 |
ARC-Challengeknowledge25.0_challengemedium| arc_challenge | Yaml | none | 25 | acc | 0.6101 | ± | 0.0143 |

Discussions (0)

none scraped.

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