Repository Issue Activity (beta)

#1579 Silent `trust_remote_code=True` enable in `FlagAutoModel.from_finetuned` via basename-only registry lookup

#1515 Colbert Interaction correct?

#1582 Consider using pre-built Flash Attention kernels via `kernels`

#1581 bge-reranker-v2-minicpm-layerwise微调报错

#1578 mac上使用omlx部署报错

#1577 Embedder for m3-memory

#1576 rerank微调数据格式

#296 bge模型深入使用后思考与疑问

#1569 unable to use with transformers==5.2.0

#375 关于bge-reranker-large，文本长度的问题

#1565 Activation Beacon，关于Loss定义的疑问：平均 token loss 是否会稀释真正依赖 beacon memory 的位置？

#1309 如何提升passage_max_len到8192来Finetune BGE-M3？

#1561 huggingface transformers has removed the `is_torch_fx_available` function

#1564 这行注释掉会导致微调模型时flashattention2报错(fla2只支持fp16、bf16，关还关不掉)，赶紧修复了吧。

#1266 Can flagembedding dependancy on transformers upgrade to newer ones?

#1455 Flagembedding 1.3.4 incompatible with transformers 4.52.

#1562 📋 Documentation Enhancement Suggestion

#1548 Activation beacon输出乱码

#1559 question: calculate input_tokens about bge-reranker-v2-gemma

#1555 [Question] Seeking Spring Boot Starter or Best Practice for BGE Models in a RAG Project

#1554 Reproducing Llara on MSMARCO

#1552 多模态/知识图谱等技能什么时候可以融入进去

#1550 啥时候开源bge-vl的微调方法

#1542 微调后bge-m3每次测试结果都不相同

#1536 flagEmbedding做向量化是否自带支持高并发