neural-chat-7B-v3-3-GPTQ

Home/Models/TheBloke/neural-chat-7B-v3-3-GPTQ

TheBloke/neural-chat-7B-v3-3-GPTQ

kind: gptq
quant: gptq
family: misc
modality: text-generation
root model: Intel/neural-chat-7b-v3-3
provider: TheBloke
license: apache-2.0
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 69
likes: 3
created: —
last modified: 2023-12-12T10:15:57+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/neural-chat-7B-v3-3-GPTQ
tags: transformerssafetensorsmistraltext-generationbase_model:Intel/neural-chat-7b-v3-3base_model:quantized:Intel/neural-chat-7b-v3-3license:apache-2.0text-generation-inference4-bitgptqregion:us

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	85.26	HellaSwag (10-shot)	medium	`\| HellaSwag (10-shot) \| 85.26 \|`
WinoGrande	knowledge	79.64	Winogrande (5-shot)	medium	`\| Winogrande (5-shot) \| 79.64 \|`
MMLU	knowledge	63.07	MMLU (5-shot)	medium	`\| MMLU (5-shot) \| 63.07 \|`
TruthfulQA	safety	63.01	TruthfulQA (0-shot)	medium	`\| TruthfulQA (0-shot) \| 63.01 \|`
GSM8K	math	61.11	GSM8K (5-shot)	medium	`\| GSM8K (5-shot) \| 61.11 \|`

none scraped.