Qwen-7B-Chat-Int8

Home/Models/Qwen/Qwen-7B-Chat-Int8

Qwen/Qwen-7B-Chat-Int8

kind: gptq
quant: gptq
family: qwen
modality: text-generation
root model: Qwen/Qwen-7B
provider: Qwen
license: —
language: zh, en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 214
likes: 9
created: —
last modified: 2023-12-13T15:44:47+00:00 (2023)
huggingface: https://huggingface.co/Qwen/Qwen-7B-Chat-Int8
tags: transformerssafetensorsqwentext-generationcustom_codezhenarxiv:2309.16609arxiv:2305.08322arxiv:2009.03300arxiv:2305.05280arxiv:2210.036298-bitgptqregion:us

benchmark	category	score	conf	evidence
C-Eval	knowledge	59.4	high	`\| Int8 \| 55.4 \| 59.4 \| 48.3 \| 34.8 \|`
MMLU	knowledge	55.4	high	`\| Int8 \| 55.4 \| 59.4 \| 48.3 \| 34.8 \|`
GSM8K	math	48.3	high	`\| Int8 \| 55.4 \| 59.4 \| 48.3 \| 34.8 \|`
HumanEval	coding	34.8	high	`\| Int8 \| 55.4 \| 59.4 \| 48.3 \| 34.8 \|`

none scraped.