guofangandClaude Sonnet 5.5 0cb17d6638 Add Qwen3-Embedding-8B and last-token pooling ...

Qwen3-Embedding is a decoder model: it pools the last token, so add a
"last" pooling mode, pad on the left, and load the weights in bfloat16.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

2026-11-10 22:16:50 +08:00

.gitignore

Initial commit

2026-11-10 11:07:18 +08:00

embedlab.py

Add Qwen3-Embedding-8B and last-token pooling

2026-11-10 22:16:50 +08:00

requirements.txt

Complete while typing with prompt_toolkit

2026-11-10 22:16:50 +08:00

setup.sh

Initial commit

2026-11-10 11:07:18 +08:00

S

Description

No description provided

91 KiB

0 Stars 1 Watchers 0 Forks

Languages

Python 98.5%

Shell 1.5%