Skip to content

Issues: FlagOpen/FlagEmbedding

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

701 Open 386 Closed
701 Open 386 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

How to use finetune result?
#1247 opened Nov 20, 2024 by dviettu134
Separate the compress module out of LLM in Activation Beacon
#1246 opened Nov 19, 2024 by toilaluan
Evaluation Pipeline for BGE-EN-ICL
#1244 opened Nov 19, 2024 by ShirleyTY
加载本地的数据，对嵌入模型进行测评，报错
#1243 opened Nov 19, 2024 by chaoStart
1
The Ascend 310 P chip is very slow in embedding for the first time, and fast in the second and later.
#1242 opened Nov 18, 2024 by zhaowenbin
Clarification on train_group_size and GPU Utilization for Negative Samples in Latest Version
#1240 opened Nov 18, 2024 by zhongxifang
Finetune stop with error after some iterations
#1239 opened Nov 18, 2024 by dviettu134
No sentence-transformers model found with name /home/FlagEmbedding/QA_finetune_bge-large-zh-v1.5. Creating a new one with mean pooling
#1238 opened Nov 18, 2024 by sanilyli
1
Simple code causes max_length warning
#1237 opened Nov 18, 2024 by ssamt
llm tokenizer padding size问题
#1236 opened Nov 17, 2024 by Kang9779
Embedding dimension when using BGEM3FlagModel
#1234 opened Nov 15, 2024 by shriram1998
1
inference time cost gap for FlagEmbedding 1.2 and 1.3
#1233 opened Nov 15, 2024 by Atlantic8
2
supported language list of BGE-M3
#1228 opened Nov 15, 2024 by yanfan0531
1
Error occurred when running hard negative mining
#1226 opened Nov 15, 2024 by wongbokhe1
1
unhashable type: 'list'. 在gpu机器上运行时报错，cpu环境运行正常
#1225 opened Nov 14, 2024 by lizhaoan123
1
问一个小白的问题，我就是想让一些句子与另一些句子向量更接近，还有一些句子向量更远，是组织成有query，pos和neg的训练数据，微调就可以吗？
#1224 opened Nov 14, 2024 by czhcc
2
请问训练数据中pos_scores和neg_scores的值如何确定？
#1223 opened Nov 14, 2024 by czhcc
1
微调后的模型
#1222 opened Nov 14, 2024 by yzc111
1
contrasting if condition with data_type='symmetric_sts'
#1220 opened Nov 13, 2024 by rohitkumargupta1000
1
[多语种embedding和reranke] 更多语种支持的模型
#1214 opened Nov 12, 2024 by Tian14267
Question about bge-en-icl paper
#1213 opened Nov 12, 2024 by whybe-choi
bge-m3模型蒸馏压缩
#1212 opened Nov 12, 2024 by Martine307
/Users/shiallen/PycharmProjects/FlagEmbedding/FlagEmbedding/abc/finetune/embedder/AbsDataset.py 这里是不是有个bug?
#1210 opened Nov 12, 2024 by Allenxiaoshi
1
why there isn't a sep token between query and passage for encoder reranker
#1208 opened Nov 12, 2024 by Atlantic8
2
在decoder_only的embedder训练，是否有将deepspeed转为hf格式的脚本，想测试中间checkpoint的效果
#1206 opened Nov 10, 2024 by tfka
1
ProTip! Add no:assignee to see everything that’s not assigned.