CollectiveCognition-v1-Mistral-7B-GGUF

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

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

kind: gguf
quant: gguf (2-bit)
family: mistral
modality: —
root model: teknium/CollectiveCognition-v1-Mistral-7B
provider: TheBloke
license: apache-2.0
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 459
likes: 4
created: —
last modified: 2023-10-13T06:58:44+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/CollectiveCognition-v1-Mistral-7B-GGUF
tags: transformersggufmistralmistral-7binstructfinetunegpt4synthetic datadistillationsharegptendataset:CollectiveCognition/chats-data-2023-09-27base_model:teknium/CollectiveCognition-v1-Mistral-7Bbase_model:quantized:teknium/CollectiveCognition-v1-Mistral-7Blicense:apache-2.0region:us

benchmark	category	score	context	conf	evidence
BoolQ	knowledge	85.38		medium	`\| boolq \| 1 \| acc \| 0.8538 \| ± \| 0.0062 \|`
PIQA	knowledge	80.85		medium	`\| piqa \| 0 \| acc \| 0.8085 \| ± \| 0.0092 \|`
WinoGrande	knowledge	74.51		medium	`\| winogrande \| 0 \| acc \| 0.7451 \| ± \| 0.0122 \|`
HellaSwag	knowledge	64.59		medium	`\| hellaswag \| 0 \| acc \| 0.6459 \| ± \| 0.0048 \|`
AGIEval	reasoning	59.71	_sat_en	medium	`\| agieval_sat_en \| 0 \| acc \| 0.5971 \| ± \| 0.0343 \|`
ARC-Challenge	knowledge	54.01	_challenge	medium	`\| arc_challenge \| 0 \| acc \| 0.5401 \| ± \| 0.0146 \|`
AGIEval	reasoning	42.01	_lsat_rc	medium	`\| agieval_lsat_rc \| 0 \| acc \| 0.4201 \| ± \| 0.0301 \|`
AGIEval	reasoning	40.29	_sat_en_without_passage	medium	`\| agieval_sat_en_without_passage \| 0 \| acc \| 0.4029 \| ± \| 0.0343 \|`
TruthfulQA	safety	37.94	_mc	medium	`\| truthfulqa_mc \| 1 \| mc1 \| 0.3794 \| ± \| 0.0170 \|`
OpenBookQA	knowledge	33.8		medium	`\| openbookqa \| 0 \| acc \| 0.3380 \| ± \| 0.0212 \|`
AGIEval	reasoning	33.73	_lsat_lr	medium	`\| agieval_lsat_lr \| 0 \| acc \| 0.3373 \| ± \| 0.0210 \|`
AGIEval	reasoning	30.45	_sat_math	medium	`\| agieval_sat_math \| 0 \| acc \| 0.3045 \| ± \| 0.0311 \|`
AGIEval	reasoning	26.11	_logiqa_en	medium	`\| agieval_logiqa_en \| 0 \| acc \| 0.2611 \| ± \| 0.0172 \|`
AGIEval	reasoning	20.87	_lsat_ar	medium	`\| agieval_lsat_ar \| 0 \| acc \| 0.2087 \| ± \| 0.0269 \|`
AGIEval	reasoning	18.9	_aqua_rat	medium	`\| agieval_aqua_rat \| 0 \| acc \| 0.1890 \| ± \| 0.0246 \|`

none scraped.