Qwen-72B-Chat-Int8

Home/Models/Qwen/Qwen-72B-Chat-Int8

Qwen/Qwen-72B-Chat-Int8

kind: gptq
quant: gptq
family: qwen
modality: text-generation
root model: Qwen/Qwen-72B
provider: Qwen
license: other
language: zh, en
context: 5
library: —
vRAM (GB): —
size on disk: —
downloads: 100
likes: 17
created: —
last modified: 2024-01-04T06:42:00+00:00 (2024)
huggingface: https://huggingface.co/Qwen/Qwen-72B-Chat-Int8
tags: transformerssafetensorsqwentext-generationcustom_codezhenarxiv:2309.16609arxiv:2305.08322arxiv:2009.03300arxiv:2307.11088license:other8-bitgptqregion:us

benchmark	category	score	conf	evidence
C-Eval	knowledge	80.1	high	`\| Int8 \| 73.5 \| 80.1 \| 73.5 \| 62.2 \|`
MMLU	knowledge	73.5	high	`\| Int8 \| 73.5 \| 80.1 \| 73.5 \| 62.2 \|`
GSM8K	math	73.5	high	`\| Int8 \| 73.5 \| 80.1 \| 73.5 \| 62.2 \|`
HumanEval	coding	62.2	high	`\| Int8 \| 73.5 \| 80.1 \| 73.5 \| 62.2 \|`
QuALITY	knowledge	61.38	low	`\| ChatGPT-3.5-16k \| 60.73 \| 63.51 \| 84.00 \| 61.38 \| 78.43 \| 12.22 \| 64.84 \|`

none scraped.