Alibaba-NLP
/

gte-Qwen2-1.5B-instruct

Sentence Similarity

sentence-transformers

text-generation

Eval Results (legacy)

text-embeddings-inference

Model card Files Files and versions

Resources

View closed (15)

add AIBOM

#38 opened 11 months ago by

Fine-tuning Qwen3 1.7B

#36 opened about 1 year ago by

VRAM usage

#34 opened about 1 year ago by

training code supported

#33 opened about 1 year ago by

What instruct to use Qwen as a free text encoder?

#32 opened about 1 year ago by

default prompt vs business-related prompts

#31 opened about 1 year ago by

andrewdeeplearning

update config on right class

#30 opened over 1 year ago by

Question about MTEB Benchmark Settings : 'max_seq_length'😭

#25 opened over 1 year ago by

Different tokenizer silently being loaded based on `trust_remote_code`

#24 opened over 1 year ago by

is there possible get the sparse embedding？

#23 opened over 1 year ago by

How to change the embedding dimision?

#19 opened over 1 year ago by

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 over 1 year ago by

Customized Further Fine-Tuning by Users

#15 opened over 1 year ago by

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

#14 opened over 1 year ago by

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

#13 opened over 1 year ago by

Qwen 2.5 1.5B retrain?

#12 opened over 1 year ago by

mteb 测试速度问题

#10 opened over 1 year ago by

Support of Xformer and FlashAttnention

#9 opened almost 2 years ago by

ONNX.data

#8 opened almost 2 years ago by

Fine-tunning

#5 opened almost 2 years ago by deleted

sequence classification

#3 opened almost 2 years ago by

score mteb french

#2 opened almost 2 years ago by

"Bidirectional attention"

#1 opened almost 2 years ago by