openchat_3.5-GPTQ

Home/Models/TheBloke/openchat_3.5-GPTQ

TheBloke/openchat_3.5-GPTQ

kind: gptq
quant: gptq
family: misc
modality: text-generation
root model: openchat/openchat_3.5
provider: TheBloke
license: apache-2.0
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 56
likes: 17
created: —
last modified: 2023-11-02T21:40:18+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/openchat_3.5-GPTQ
tags: transformerssafetensorsmistraltext-generationarxiv:2309.11235arxiv:2303.08774arxiv:2212.10560base_model:openchat/openchat_3.5base_model:quantized:openchat/openchat_3.5license:apache-2.0text-generation-inference4-bitgptqregion:us

benchmark	category	score	context	conf	evidence
GSM8K	math	77.3	BBH CoT	low	`\| OpenChat-3.5 \| 7B \| 61.6 \| 7.81 \| 47.4 \| 47.6 \| 59.1 \| 64.3 \| 55.5 \| 63.5 \| 77.3 \|`
MMLU	knowledge	64.3	BBH CoT	low	`\| OpenChat-3.5 \| 7B \| 61.6 \| 7.81 \| 47.4 \| 47.6 \| 59.1 \| 64.3 \| 55.5 \| 63.5 \| 77.3 \|`
TruthfulQA	safety	59.1	BBH CoT	low	`\| OpenChat-3.5 \| 7B \| 61.6 \| 7.81 \| 47.4 \| 47.6 \| 59.1 \| 64.3 \| 55.5 \| 63.5 \| 77.3 \|`
HumanEval	coding	55.5	BBH CoT	low	`\| OpenChat-3.5 \| 7B \| 61.6 \| 7.81 \| 47.4 \| 47.6 \| 59.1 \| 64.3 \| 55.5 \| 63.5 \| 77.3 \|`
BBH	reasoning	47.6	BBH CoT	low	`\| OpenChat-3.5 \| 7B \| 61.6 \| 7.81 \| 47.4 \| 47.6 \| 59.1 \| 64.3 \| 55.5 \| 63.5 \| 77.3 \|`
AGIEval	reasoning	47.4	BBH CoT	low	`\| OpenChat-3.5 \| 7B \| 61.6 \| 7.81 \| 47.4 \| 47.6 \| 59.1 \| 64.3 \| 55.5 \| 63.5 \| 77.3 \|`
MT-Bench	chat	7.81	BBH CoT	low	`\| OpenChat-3.5 \| 7B \| 61.6 \| 7.81 \| 47.4 \| 47.6 \| 59.1 \| 64.3 \| 55.5 \| 63.5 \| 77.3 \|`

none scraped.