CollectiveCognition-v1.1-Mistral-7B-GGUF

Home/Models/TheBloke/CollectiveCognition-v1.1-Mistral-7B-GGUF

TheBloke/CollectiveCognition-v1.1-Mistral-7B-GGUF

kind: gguf
quant: gguf (2-bit)
family: mistral
modality: —
root model: teknium/CollectiveCognition-v1.1-Mistral-7B
provider: TheBloke
license: apache-2.0
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 939
likes: 34
created: —
last modified: 2023-10-05T16:21:56+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/CollectiveCognition-v1.1-Mistral-7B-GGUF
tags: transformersggufmistralmistral-7binstructfinetunegpt4synthetic datadistillationsharegptendataset:CollectiveCognition/chats-data-2023-09-27base_model:teknium/CollectiveCognition-v1.1-Mistral-7Bbase_model:quantized:teknium/CollectiveCognition-v1.1-Mistral-7Blicense:apache-2.0region:us

benchmark	category	score	context	conf	evidence
BoolQ	knowledge	84.95		medium	`\| boolq \| 1 \| acc \| 0.8495 \| ± \| 0.0063 \|`
PIQA	knowledge	79.92		medium	`\| piqa \| 0 \| acc \| 0.7992 \| ± \| 0.0093 \|`
WinoGrande	knowledge	73.48		medium	`\| winogrande \| 0 \| acc \| 0.7348 \| ± \| 0.0124 \|`
HellaSwag	knowledge	63.99		medium	`\| hellaswag \| 0 \| acc \| 0.6399 \| ± \| 0.0048 \|`
AGIEval	reasoning	60.68	_sat_en	medium	`\| agieval_sat_en \| 0 \| acc \| 0.6068 \| ± \| 0.0341 \|`
ARC-Challenge	knowledge	50.85	_challenge	medium	`\| arc_challenge \| 0 \| acc \| 0.5085 \| ± \| 0.0146 \|`
AGIEval	reasoning	47.21	_lsat_rc	medium	`\| agieval_lsat_rc \| 0 \| acc \| 0.4721 \| ± \| 0.0305 \|`
TruthfulQA	safety	40.51	_mc	medium	`\| truthfulqa_mc \| 1 \| mc1 \| 0.4051 \| ± \| 0.0172 \|`
AGIEval	reasoning	39.32	_sat_en_without_passage	medium	`\| agieval_sat_en_without_passage \| 0 \| acc \| 0.3932 \| ± \| 0.0341 \|`
AGIEval	reasoning	34.12	_lsat_lr	medium	`\| agieval_lsat_lr \| 0 \| acc \| 0.3412 \| ± \| 0.0210 \|`
OpenBookQA	knowledge	32.4		medium	`\| openbookqa \| 0 \| acc \| 0.3240 \| ± \| 0.0210 \|`
AGIEval	reasoning	31.34	_logiqa_en	medium	`\| agieval_logiqa_en \| 0 \| acc \| 0.3134 \| ± \| 0.0182 \|`
AGIEval	reasoning	28.64	_sat_math	medium	`\| agieval_sat_math \| 0 \| acc \| 0.2864 \| ± \| 0.0305 \|`
AGIEval	reasoning	22.17	_lsat_ar	medium	`\| agieval_lsat_ar \| 0 \| acc \| 0.2217 \| ± \| 0.0275 \|`
AGIEval	reasoning	19.29	_aqua_rat	medium	`\| agieval_aqua_rat \| 0 \| acc \| 0.1929 \| ± \| 0.0248 \|`

none scraped.