Resources

View closed (13)

What instruct to use Qwen as a free text encoder?

#32 opened 11 days ago by

raphbrl-bbc

default prompt vs business-related prompts

#31 opened 22 days ago by

andrewdeeplearning

update config on right class

#30 opened about 1 month ago by

michaelfeil

Question about MTEB Benchmark Settings : 'max_seq_length'😭

#25 opened 3 months ago by

george31

Different tokenizer silently being loaded based on `trust_remote_code`

#24 opened 4 months ago by

DarkLight1337

is there possible get the sparse embedding？

#23 opened 4 months ago by

weiminw

How to change the embedding dimision?

#19 opened 5 months ago by

storm2008

用eval_mteb.py算出来的mteb指标和Leaderboard展示的差距很大，不清楚为什么？

#16 opened 5 months ago by

YangGuang30

Customized Further Fine-Tuning by Users

#15 opened 6 months ago by

fwj

Model keeps cache of generation in Transformers (fixed using torch.no_grad())

#14 opened 6 months ago by

Pietroferr

gte-Qwen2-1.5B-instruct模型半精度推理时，模型输出结果NAN

#13 opened 6 months ago by

Erin

Qwen 2.5 1.5B retrain?

#12 opened 6 months ago by

tomaarsen

mteb 测试速度问题

#10 opened 6 months ago by

xiaopli11

Support of Xformer and FlashAttnention

#9 opened 7 months ago by

le723z

ONNX.data

#8 opened 7 months ago by

Saugatkafley

Fine-tunning

#5 opened 8 months ago by deleted

sequence classification

#3 opened 8 months ago by

prudant

score mteb french

#2 opened 8 months ago by

abhamadi

"Bidirectional attention"

#1 opened 9 months ago by

olivierdehaene