Qwen-14B-Chat

Home/Models/Qwen/Qwen-14B-Chat

Qwen/Qwen-14B-Chat

kind: original
quant: bf16 (16-bit)
family: qwen
modality: text-generation
root model: Qwen/Qwen-14B-Chat
provider: Qwen
license: —
language: zh, en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 3,694
likes: 373
created: —
last modified: 2023-12-13T15:44:33+00:00 (2023)
huggingface: https://huggingface.co/Qwen/Qwen-14B-Chat
tags: transformerssafetensorsqwentext-generationcustom_codezhenarxiv:2309.16609arxiv:2305.08322arxiv:2009.03300arxiv:2305.05280arxiv:2210.03629region:us

benchmark	category	score	conf	evidence
C-Eval	knowledge	69.8	low	`\| BF16 \| 64.6 \| 69.8 \| 60.1 \| 43.9 \|`
MMLU	knowledge	64.6	low	`\| BF16 \| 64.6 \| 69.8 \| 60.1 \| 43.9 \|`
GSM8K	math	60.1	low	`\| BF16 \| 64.6 \| 69.8 \| 60.1 \| 43.9 \|`
HumanEval	coding	43.9	low	`\| BF16 \| 64.6 \| 69.8 \| 60.1 \| 43.9 \|`

none scraped.