Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
manu02
/
Nanbeige4.1-3B-bnb-4bit-nf4-dq
like
0
Text Generation
Transformers
Safetensors
English
llama
quantized
4bit
bnb
conversational
text-generation-inference
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Nanbeige4.1-3B-bnb-4bit-nf4-dq
3.31 GB
1 contributor
History:
4 commits
manu02
Upload 4-bit quantized version of Nanbeige/Nanbeige4.1-3B with 58.8% memory reduction
e598854
verified
9 days ago
.gitattributes
1.57 kB
Upload 4-bit quantized version of Nanbeige/Nanbeige4.1-3B with 58.8% memory reduction
9 days ago
README.md
1.07 kB
Upload 4-bit quantized version of Nanbeige/Nanbeige4.1-3B with 58.8% memory reduction
9 days ago
chat_template.jinja
5.66 kB
Upload 4-bit quantized version of Nanbeige/Nanbeige4.1-3B with 58.8% memory reduction
9 days ago
config.json
1.32 kB
Upload 4-bit quantized version of Nanbeige/Nanbeige4.1-3B with 58.8% memory reduction
9 days ago
generation_config.json
153 Bytes
Upload 4-bit quantized version of Nanbeige/Nanbeige4.1-3B with 58.8% memory reduction
9 days ago
model.safetensors
3.29 GB
xet
Upload 4-bit quantized version of Nanbeige/Nanbeige4.1-3B with 58.8% memory reduction
9 days ago
tokenizer.json
18.5 MB
xet
Upload 4-bit quantized version of Nanbeige/Nanbeige4.1-3B with 58.8% memory reduction
9 days ago
tokenizer_config.json
464 Bytes
Upload 4-bit quantized version of Nanbeige/Nanbeige4.1-3B with 58.8% memory reduction
9 days ago
