HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Qwen-14B-Chat-AWQ

TheBloke/Qwen-14B-Chat-AWQ

kind
awq
quant
awq
family
qwen
modality
text-generation
root model
Qwen/Qwen-14B-Chat
provider
TheBloke
license
—
language
zh, en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
53
likes
11
created
—
last modified
2023-11-21T11:10:51+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Qwen-14B-Chat-AWQ
tags
transformerssafetensorsqwentext-generationcustom_codezhenarxiv:2309.16609arxiv:2305.08322arxiv:2009.03300arxiv:2305.05280arxiv:2210.03629base_model:Qwen/Qwen-14B-Chatbase_model:quantized:Qwen/Qwen-14B-Chat4-bitawqregion:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
C-Evalknowledge69.8low| BF16 | 64.6 | 69.8 | 60.1 | 43.9 |
MMLUknowledge64.6low| BF16 | 64.6 | 69.8 | 60.1 | 43.9 |
GSM8Kmath60.1low| BF16 | 64.6 | 69.8 | 60.1 | 43.9 |
HumanEvalcoding43.9low| BF16 | 64.6 | 69.8 | 60.1 | 43.9 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.