413 7 months ago

General Text Embedding model

7 months ago

9df7ed75fb1b · 4.7GB ·

qwen2
·
7.61B
·
Q4_K_M
{{ .Prompt }}
{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

Readme

Quant type File Size Description
Q4_K_M 4.7GB balanced quality
Q8_0 8.1GB best quality

gte-Qwen2-7B-instruct

gte-Qwen2-7B-instruct is the latest model in the gte (General Text Embedding) model family that ranks No.1 in both English and Chinese evaluations on the Massive Text Embedding Benchmark MTEB benchmark (as of June 16, 2024).

https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct

MTEB Leaderboard

MTEB is a massive benchmark for measuring the performance of text embedding models on diverse embedding tasks.

https://huggingface.co/spaces/mteb/leaderboard