Harrier-OSS-v1-270M โ€” ONNX INT8 (single-file)

Re-export of microsoft/harrier-oss-v1-270m as single-file ONNX INT8 for Transformers.js v4 and ONNX Runtime.

Property Value
Dimensions 640
MTEB v2 66.5
Languages 94
Max tokens 32,768
Pooling Last-token + L2 norm
Size 270 MB (INT8)
License MIT

Important: Queries must be prefixed with an instruction. See search_instructions.json.

Export by Deposium.

Downloads last month
34
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for tss-deposium/harrier-oss-v1-270m-onnx-int8

Quantized
(7)
this model