Qwen-7B

Qwen/Qwen-7B

kind: original
quant: bf16 (16-bit)
family: qwen
modality: text-generation
root model: Qwen/Qwen-7B
provider: Qwen
license: other
language: zh, en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 22,560
likes: 399
created: —
last modified: 2024-01-04T06:42:50+00:00 (2024)
huggingface: https://huggingface.co/Qwen/Qwen-7B
tags: transformerssafetensorsqwentext-generationcustom_codezhenarxiv:2309.16609license:otherregion:us

benchmark	category	score	conf	evidence
MMLU	knowledge	46.8	low	`\| LLaMA2-7B \| 46.8 \| 32.5 \| 16.7 \| 3.3 \| 12.8 \| 20.8 \| 38.2 \| 31.8 \|`
BBH	reasoning	38.2	low	`\| LLaMA2-7B \| 46.8 \| 32.5 \| 16.7 \| 3.3 \| 12.8 \| 20.8 \| 38.2 \| 31.8 \|`
C-Eval	knowledge	32.5	low	`\| LLaMA2-7B \| 46.8 \| 32.5 \| 16.7 \| 3.3 \| 12.8 \| 20.8 \| 38.2 \| 31.8 \|`
CMMLU	knowledge	31.8	low	`\| LLaMA2-7B \| 46.8 \| 32.5 \| 16.7 \| 3.3 \| 12.8 \| 20.8 \| 38.2 \| 31.8 \|`
MBPP	coding	20.8	low	`\| LLaMA2-7B \| 46.8 \| 32.5 \| 16.7 \| 3.3 \| 12.8 \| 20.8 \| 38.2 \| 31.8 \|`
GSM8K	math	16.7	low	`\| LLaMA2-7B \| 46.8 \| 32.5 \| 16.7 \| 3.3 \| 12.8 \| 20.8 \| 38.2 \| 31.8 \|`
HumanEval	coding	12.8	low	`\| LLaMA2-7B \| 46.8 \| 32.5 \| 16.7 \| 3.3 \| 12.8 \| 20.8 \| 38.2 \| 31.8 \|`
MATH	math	3.3	low	`\| LLaMA2-7B \| 46.8 \| 32.5 \| 16.7 \| 3.3 \| 12.8 \| 20.8 \| 38.2 \| 31.8 \|`

none scraped.