Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
TheBloke
/
Qwen-7B-Chat-AWQ
like
9
Text Generation
Transformers
Safetensors
Chinese
English
qwen
custom_code
4-bit precision
awq
arxiv:
5 papers
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
Qwen-7B-Chat-AWQ
5.86 GB
1 contributor
History:
5 commits
TheBloke
Fix config.json, disabling Flash Attention
9be754f
about 2 years ago
.gitattributes
1.52 kB
initial commit
about 2 years ago
LICENSE
6.9 kB
AWQ model commit
about 2 years ago
NOTICE
2.7 kB
AWQ model commit
about 2 years ago
README.md
48.4 kB
Upload README.md
about 2 years ago
config.json
1.28 kB
Fix config.json, disabling Flash Attention
about 2 years ago
configuration_qwen.py
2.35 kB
AWQ model commit
about 2 years ago
cpp_kernels.py
1.92 kB
AWQ model commit
about 2 years ago
generation_config.json
249 Bytes
AWQ model commit
about 2 years ago
model.safetensors
5.86 GB
xet
AWQ model commit
about 2 years ago
modeling_qwen.py
55.8 kB
AWQ model commit
about 2 years ago
quant_config.json
90 Bytes
AWQ model commit
about 2 years ago
qwen.tiktoken
2.56 MB
AWQ model commit
about 2 years ago
qwen_generation_utils.py
14.6 kB
AWQ model commit
about 2 years ago
special_tokens_map.json
3 Bytes
AWQ model commit
about 2 years ago
tokenization_qwen.py
9.62 kB
AWQ model commit
about 2 years ago
tokenizer_config.json
173 Bytes
AWQ model commit
about 2 years ago