Qdrant
/

constella-zero

Feature Extraction

zero-lookup-table

asymmetric-dual-encoder

research-preview

Model card Files Files and versions

189 MB

Ctrl+K

Ctrl+K

2 contributors

History: 25 commits

DylanCouzon's picture

Ship int8 safetensors with per-row scales for FastEmbed

8312f3f verified 6 days ago

scripts
Ship int8 safetensors with per-row scales for FastEmbed 6 days ago
.gitattributes

1.52 kB
initial commit about 2 months ago
README.md

7.93 kB
update fastembed installation instructions 18 days ago
config.json

1.61 kB
zero v1 — M7 lookup table, run p35w-2m-s2500 about 2 months ago
model.npz

93.9 MB
xet

zero v1 — M7 lookup table, run p35w-2m-s2500 about 2 months ago
model.onnx

31.4 MB
xet

zero v1 — M7 lookup table, run p35w-2m-s2500 about 2 months ago
model.safetensors

31.4 MB
xet

Ship int8 safetensors with per-row scales for FastEmbed 6 days ago
model_tokens.onnx

31.4 MB
xet

zero v1 — M7 lookup table, run p35w-2m-s2500 about 2 months ago
special_tokens_map.json

695 Bytes
zero v1 — M7 lookup table, run p35w-2m-s2500 about 2 months ago
tokenizer.json

619 kB
zero v1 — M7 lookup table, run p35w-2m-s2500 about 2 months ago
tokenizer_config.json

1.25 kB
zero v1 — M7 lookup table, run p35w-2m-s2500 about 2 months ago
vocab.txt

232 kB
zero v1 — M7 lookup table, run p35w-2m-s2500 about 2 months ago
zero_encoder.py

4.19 kB
Ship int8 safetensors with per-row scales for FastEmbed 6 days ago