| Qwen3 Embedding 0.6B — bilingual mobile RAG champion | 3morixd | open | 0 | disc |
| Embedding Vectors Drift Across Different vLLM Versions and GPUs: How to Pin Unique Values? | Donghao-1997 | open | 0 | disc |
| Urgent : Need solution for Qwen Tokenizer please reply quickly | RohitUltimate | open | 0 | disc |
| Add exported openvino model 'openvino_model.xml' | gpuman | open | 0 | disc |
| libcuda.so.1: cannot open shared object file | daylans | open | 0 | disc |
| Add exported onnx model 'model.onnx' | rexfong | open | 0 | disc |
| Update README.md | heyitsys | merged | 0 | disc |
| Fix architecture in config (Qwen3ForCausalLM -> Qwen3Model) | Xenova | open | 0 | disc |
| Add exported openvino model 'openvino_model_qint8_quantized.xml' | jingmou | open | 0 | disc |
| Add exported onnx model 'model.onnx' | lenzhao123 | closed | 0 | disc |
| Add exported onnx model 'model.onnx' | lenzhao123 | closed | 0 | disc |
| Update vLLM embedding method to `runner="pooling"` from `task="embed"` | pj-mathematician | open | 0 | disc |
| Add exported onnx model 'model.onnx' | lenzhao123 | closed | 0 | disc |
| How to increase speed when using CPU | aki0923 | open | 0 | disc |
| Pooling implementation is weird | ir2718 | open | 0 | disc |
| Update blog link in readme | maigonis | open | 0 | disc |
| Segfault on example sentencetransformers code: | marksverdhei | open | 0 | disc |
| Problems with API | artemredchych | open | 0 | disc |
| 微调的显存占用很高 | laaok | open | 0 | disc |
| Qwen3-Embedding-0.6B -> how do I pass instructions to it in llama.cpp? | bp50 | open | 0 | disc |
| any inference providers for Qwen/Qwen3-Embedding-0.6B ? | bp50 | open | 0 | disc |
| HTTP Error - Failed to perform Inference | TomBombadyl | open | 0 | disc |
| 如何定义32k的上下文 | Loki1996 | open | 0 | disc |
| Qwen-3 (0.6B) Embedding Model – High CUDA Memory Spikes with Misspelled Sentences | rgsurya | open | 0 | disc |
| Add exported onnx model 'model.onnx' | AIInnovatorX | open | 0 | disc |
| ValueError: The checkpoint you are trying to load has model type `qwen3` but Transformers does not recognize this architecture. | DaniDubi | closed | 0 | disc |
| issues downloading this model | Daemontatox | closed | 0 | disc |
| Update README.md | aari1995 | open | 0 | disc |
| task description for clustering | guishe | open | 0 | disc |
| 用vllm部署后，如何用api调用呢？ | hhy150 | open | 0 | disc |
| Adding ONNX file of this model | hackcheee | open | 0 | disc |
| Update README.md | Catsup34577 | open | 0 | disc |
| Best Practices for Query/Passage Prefixes? | timdim | open | 0 | disc |
| Update `README.md` to use TEI v1.7 instead | alvarobartt | open | 0 | disc |
| Add ONNX export from Sentence Transformers | alvarobartt | open | 0 | disc |
| Update README.md with TEI support | alvarobartt | merged | 0 | disc |
| onnx-community/Qwen3-Embedding-0.6B-ONNX | zhnagchenchne | open | 0 | disc |
| FileNotFoundError: [Errno 2] No such file or directory: 'Qwen/Qwen3-Embedding-0.6B/sentence_xlnet_config.json' | ColinZhao | open | 0 | disc |
| Qwen Embedding model used in Typescript Environment | AnushaV2002 | open | 0 | disc |
| 求教关于模型训练的问题 | Jay-v2 | open | 0 | disc |
| coreml model for the same | sriharsha4444 | open | 0 | disc |
| 本地测试用例结果与示例对不上 | kingkingofall | closed | 0 | disc |
| Embedding Model uses unsloth library instead of transformers | mahmoud-mohey | open | 0 | disc |
| ONNX conversion | shuttie | open | 0 | disc |
| ONNX version planned? | Florianoli | open | 0 | disc |
| How to use "user-defined output dimensions"？ | BigPan98 | closed | 0 | disc |
| 关于Qwen3 Embedding系列的句子表征 | Jay-v2 | open | 0 | disc |
| Reduce GPU memory usage in the runtime. | xiping | open | 0 | disc |
| Add missing `torch_dtype` in commented snippet in `README.md` | alvarobartt | open | 0 | disc |
| Add library name and project page link | nielsr | closed | 0 | disc |
| Training supported | tastelikefeet | open | 0 | disc |
| Languages list? | anto5040 | open | 0 | disc |
| Improve model card metadata | nielsr | closed | 0 | disc |
| Add sentence_bert_config.json | yjoonjang | open | 0 | disc |
| Add sentence_bert_config.json | yjoonjang | closed | 0 | disc |
| How to change the output embedding dimensions? | ly400929 | open | 0 | disc |
| add use case for vllm & modify Citation | zyznull | merged | 0 | disc |
| update README | zyznull | closed | 0 | disc |
| Embedding Dimension: Up to 1024, supports user-defined output dimensions ranging from 32 to 1024 | chaochaoli | closed | 0 | disc |
| Automatically add EOS via Tokenizer, integrate Sentence Transformers | tomaarsen | merged | 0 | disc |
| vLLM support | ccdv | open | 0 | disc |