Hugging Face's logo
yanzhao's picture
39 1

yanzhao

zyznull
sigridjineth's profile picture rjmalagon's profile picture sudongpo's profile picture
·

AI & ML interests

None yet

Recent Activity

New activity about 1 month ago
Alibaba-NLP/gte-large-en-v1.5:Recommended tokenizer max_length
View all activity

Organizations

Alibaba-NLP's profile picture

zyznull's activity

New activity in Alibaba-NLP/gte-large-en-v1.5 about 1 month ago

Recommended tokenizer max_length

1
#21 opened about 1 month ago by rcland12
New activity in Alibaba-NLP/gte-Qwen2-1.5B-instruct 3 months ago

Support of Xformer and FlashAttnention

1
#9 opened 4 months ago by le723z

mteb 测试速度问题

2
#10 opened 3 months ago by xiaopli11
New activity in Alibaba-NLP/gte-Qwen2-7B-instruct 4 months ago

Retrieval 效果一般，仅和bm25持平

8
#26 opened 4 months ago by Stefan8

关于bidirectional attention的问题

1
#30 opened 4 months ago by JoeBlack18

测试效果一般

3
#22 opened 4 months ago by dhajshdkajs

请问支持fp16推理吗？

2
#23 opened 4 months ago by DJCan
New activity in Alibaba-NLP/gte-Qwen2-1.5B-instruct 4 months ago

fix parameter name in eval_mteb
#6 opened 4 months ago by Jeol
New activity in Alibaba-NLP/gte-Qwen2-7B-instruct 4 months ago

config_sentence_transformers.json does not include the prompt to embeddings mappings

1
#19 opened 5 months ago by Tonic
New activity in Alibaba-NLP/gte-Qwen2-7B-instruct 5 months ago

Only one Instruct Prompt Available , is this Correct ?

2
#15 opened 5 months ago by Tonic
New activity in Alibaba-NLP/gte-Qwen2-1.5B-instruct 5 months ago

sequence classification

1
#3 opened 5 months ago by prudant

"Bidirectional attention"

2
#1 opened 5 months ago by olivierdehaene
New activity in Alibaba-NLP/gte-Qwen2-7B-instruct 5 months ago

Training embadding Issues.

2
#8 opened 6 months ago by Imran1
New activity in mteb/leaderboard 6 months ago

New GTE model, Apply for refreshing the results

4
#126 opened 6 months ago by thenlper
New activity in Alibaba-NLP/gte-Qwen2-7B-instruct 6 months ago

输出的embedding size是多少

3
#6 opened 6 months ago by seleven11

Upload ./model-00001-of-00007.safetensors with huggingface_hub
#1 opened 6 months ago by zyznull
New activity in Alibaba-NLP/gte-Qwen1.5-7B-instruct 6 months ago

how to load this model to multiple gpus?

1
#18 opened 6 months ago by yijiu

Architecture should be Qwen2ForCausalLM or Qwen2Model?

1
#19 opened 6 months ago by ultraxyz

infer speed so slow and mutil-gpu infer bug

1
#17 opened 6 months ago by YuYuyanzu

使用官方代码报错 ，Failed to import transformers.models.auto because of the following error

1
#15 opened 7 months ago by haaaaaaaa1