Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
decompute
/
Nebula-S-v1-4bit
like
0
Follow
Decompute Inc.
11
Text Generation
Transformers
Safetensors
qwen3
nebula-s
svms
math-reasoning
competition-math
4bit
quantized
bitsandbytes
conversational
4-bit precision
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Nebula-S-v1-4bit
3.51 GB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
punitdecomp
Upload folder using huggingface_hub
03674d1
verified
about 13 hours ago
.gitattributes
Safe
1.57 kB
Upload folder using huggingface_hub
about 13 hours ago
README.md
1.99 kB
Upload folder using huggingface_hub
about 13 hours ago
chat_template.jinja
Safe
4.05 kB
Upload folder using huggingface_hub
about 13 hours ago
config.json
2.15 kB
Upload folder using huggingface_hub
about 13 hours ago
generation_config.json
251 Bytes
Upload folder using huggingface_hub
about 13 hours ago
model.safetensors
2.65 GB
xet
Upload folder using huggingface_hub
about 13 hours ago
nebula_s.py
7.03 kB
Upload folder using huggingface_hub
about 13 hours ago
nebula_s_adapter.pt
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.BFloat16Storage"
What is a pickle import?
842 MB
xet
Upload folder using huggingface_hub
about 13 hours ago
tokenizer.json
Safe
11.4 MB
xet
Upload folder using huggingface_hub
about 13 hours ago
tokenizer_config.json
741 Bytes
Upload folder using huggingface_hub
about 13 hours ago
