Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Octen
/
Octen-Embedding-8B-INT8
like
0
Follow
Octen-Team
1
Sentence Similarity
sentence-transformers
Safetensors
English
Chinese
multilingual
qwen3
feature-extraction
embedding
text-embedding
retrieval
quantization
int8
8-bit precision
bitsandbytes
arxiv:
2506.05176
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Octen-Embedding-8B-INT8
8.21 GB
1 contributor
History:
2 commits
bflhc
init model
358b1e5
verified
3 days ago
1_Pooling
init model
3 days ago
2_Normalize
init model
3 days ago
.gitattributes
1.57 kB
init model
3 days ago
README.md
4.44 kB
init model
3 days ago
added_tokens.json
605 Bytes
init model
3 days ago
chat_template.jinja
2.43 kB
init model
3 days ago
config.json
2.01 kB
init model
3 days ago
config_sentence_transformers.json
217 Bytes
init model
3 days ago
merges.txt
1.67 MB
init model
3 days ago
model-00001-of-00002.safetensors
4.95 GB
xet
init model
3 days ago
model-00002-of-00002.safetensors
3.24 GB
xet
init model
3 days ago
model.safetensors.index.json
69.4 kB
init model
3 days ago
modules.json
350 Bytes
init model
3 days ago
special_tokens_map.json
613 Bytes
init model
3 days ago
tokenizer.json
11.4 MB
xet
init model
3 days ago
tokenizer_config.json
4.69 kB
init model
3 days ago
vocab.json
2.78 MB
init model
3 days ago
