Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
matatonic
/
QwQ-32B-6.5bpw-h8-exl2
like
0
Text Generation
Safetensors
13 languages
qwen2
chat
conversational
exl2
arxiv:
2309.00071
arxiv:
2407.10671
License:
apache-2.0
Model card
Files
Files and versions
Community
1
main
QwQ-32B-6.5bpw-h8-exl2
Ctrl+K
Ctrl+K
2 contributors
History:
4 commits
matatonic
lbourdois
Improve language tag (
#1
)
e9b9e70
verified
about 2 months ago
.gitattributes
Safe
1.52 kB
initial commit
3 months ago
LICENSE
Safe
11.3 kB
initial
3 months ago
README.md
6.97 kB
Improve language tag (#1)
about 2 months ago
added_tokens.json
Safe
707 Bytes
initial
3 months ago
config.json
Safe
978 Bytes
initial
3 months ago
generation_config.json
Safe
243 Bytes
initial
3 months ago
measurement.json
Safe
3.57 MB
initial
3 months ago
merges.txt
Safe
1.67 MB
initial
3 months ago
model.safetensors.index.json
Safe
63.2 kB
initial
3 months ago
output-00001-of-00003.safetensors
Safe
10.7 GB
LFS
initial
3 months ago
output-00002-of-00003.safetensors
Safe
10.6 GB
LFS
initial
3 months ago
output-00003-of-00003.safetensors
Safe
6.33 GB
LFS
initial
3 months ago
special_tokens_map.json
Safe
613 Bytes
initial
3 months ago
tokenizer.json
Safe
7.03 MB
initial
3 months ago
tokenizer_config.json
Safe
8.07 kB
remove the "<think>\n" prefix from generation so open-webui does it's "Thinking..." thing
3 months ago
vocab.json
Safe
2.78 MB
initial
3 months ago