netease-youdao/BCEmbedding
Netease Youdao's open-source embedding and reranker models for RAG products.
PythonApache-2.0
Issues
- 1
新版 pydantic 适配
#100 opened by bzr1 - 1
使用convert_hf_to_gguf_update.py转换后得bce-reranker-base_v1得gguf文件,在ollama内使用报Error: invalid file magic?
#99 opened by lianlian1212 - 1
无法复现bce-reranker-base_v1在T2Reranking上的指标
#98 opened by HuDi2018 - 26
embedding、rerank模型加速推理
#70 opened by deku0818 - 0
提问:【中英文混合的 query】 对【中英文混合语料】召回:jina-embeddings-v2-base-zh 和 maidalun1020/bce-embedding-base_v1 哪个更好,有人对比过吗
#96 opened by jiangying000 - 1
想在私有领域使用,不支持微调吗?
#95 opened by Kang9779 - 1
Conan-embedding-v1 模型输出维度错误 由1792 变成了 1024
#94 opened by longgui0318 - 1
Mac M2加载模型段错误
#91 opened by leopeng1995 - 1
单独跑Clustering 脚本能否提供?
#93 opened by myboyliu2025 - 0
有道词典笔A6 Pro
#92 opened by wyxdlz54188 - 1
- 1
bce-reranker-base_v1 显存占用不释放,服务崩溃
#88 opened by xxx1099836595 - 1
What is the basic model structure?
#78 opened by sherlcok314159 - 1
请问 text2vec 面对 10M 条 chunk,精度如何?
#89 opened by tpoisonooo - 1
BCEmbedding何时能支持transformers4.37以上版本
#85 opened by VJJJJJJ1 - 1
- 1
请问Embedding模型是否可以扩长度?
#83 opened by Double-bear - 3
- 1
根据embedding怎么解码输出
#81 opened by Theviro1 - 2
当使用 BCERerank(**reranker_args)有 typeError:can't instantiate abstract class BCErerank with abstract method accompress_documents
#79 opened by bzr1 - 2
请问Rerank在哪设置阈值呢?
#80 opened by klayc-gzl - 1
笔记本按照demo安装,安装后运行时报错找不到指定的模块。 Error loading "C:\Users\Lenovo\anaconda3\envs\bce\lib\site-packages\torch\lib\fbgemm.dll" or one of its dependencies.
#77 opened by chuangzhidan - 1
【BUG】【P0】 不同框架数值抖动 5e-3 导致掉 3 个点
#75 opened by tpoisonooo - 1
咨询关于 Rerank Overlap 相关的问题
#74 opened by sherlcok314159 - 1
reranker模型使用时,出现在待排序的doc中添加前缀会出现排序结果更好的情况
#72 opened by windsunboyu - 4
多GPU并发调用报错:Core dumped
#71 opened by melove93 - 1
为什么匹配效果越来越差
#69 opened by wensese - 0
请问如何在特定数据集上优化这个词向量模型?
#68 opened by PeiGuijun - 2
FYI:最近测了 bce chunksize & bge 对比
#67 opened by tpoisonooo - 1
accelerate加速,微调bce模型报错:Could not find the transformer layer class to wrap in the model.
#66 opened by HuXiLiFeng - 3
query只能是一个句子吗?多轮交互下的召回或者排序,BCEEmbedding支持处理呢?
#64 opened by macomzzl - 1
- 1
请问出现这种情况:Token indices sequence length is longer than the specified maximum sequence length for this model (781 > 512),如何解决?
#62 opened by starxuh - 0
请问有没有提交到最新的mteb leaderboard的结果对比?
#61 opened by green-dalii - 1
请问有 C-MTEB (非英文)的测试结果么?
#60 opened by tpoisonooo - 1
python3.11报错
#59 opened by qiansheng2 - 4
Xinference对比手动部署
#57 opened by Lorrrrraine - 1
单独部署-用api的方式提供服务
#58 opened by kingslyChen - 1
复现 LlamaIndex RAG评测结果时的一些问题
#56 opened by Lorrrrraine - 4
RerankerModel的token数量
#55 opened by DiaQusNet - 1
Are there any optimization methods to support the optimized run of this project?
#54 opened by wencan - 1
bce-reranker-base_v1原生支持的passage长度问题
#53 opened by dmortem - 2
下载 tokenizer 时不能指定 auth token
#52 opened by SakigamiYang - 1
pydantic版本问题
#51 opened by sun-wan-ning - 2
使用 langchain 调用程序报错
#50 opened by shguan2018 - 1
关于模型微调的问题
#49 opened by sevenandseven - 4
- 2
测试“Embedding和Reranker集成常用RAG框架”中的样例代码1
#47 opened by zdm0301 - 2
可以提供一下复现llamaindex结果的数据么,
#46 opened by afalf - 2
QAnything和这个模型库的对应关系?
#45 opened by ChaofeiBu