| request fp8 quantized model | brotherb74939 | open | 0 | disc |
| Integrate with Sentence Transformers v5.4 | tomaarsen | merged | 0 | disc |
| Add `id2label` and `label2id` configs | kozistr | open | 0 | disc |
| Working GGUF for llama.cpp (native Windows/Linux, no WSL needed) | Voodisss | open | 0 | disc |
| Qwen/Qwen3-Reranker-0.6B compatibility question | dqdw | open | 0 | disc |
| Performance Optimization recommendations for Qwen3 Reranker 0.6B on A100/H100 GPUs | rajshah14 | open | 0 | disc |
| testing | weiseng188 | draft | 0 | disc |
| Update README.md | aynot | open | 0 | disc |
| Error loading model weights | napaull | closed | 0 | disc |
| Working 0.6B-Reranker Quants | JonathanMiddleton | open | 0 | disc |
| which inference service can run qwen3-reranker-0.6B now? | wangruiai2023 | open | 0 | disc |
| 06b_reranker | linlxiu | draft | 0 | disc |
| Why using prefix and suffix as input? | FrankQ | open | 0 | disc |
| Training supported | russwest404 | open | 0 | disc |
| Why in my test data 0.6B model not better than v2-m3 | hookzeng | open | 0 | disc |
| max_len_tokens | mansurealism | open | 0 | disc |
| 有没有计划给他转换成CrossEncoder 用SentenceTransfomrer调用？ | oaksharks | open | 0 | disc |
| ValueError: Cannot handle batch sizes > 1 if no padding token is defined. Raised when running `query_engine.query(query)` in llamaindex | theforgehermit | open | 0 | disc |
| vllm online serving | aperez900907 | open | 0 | disc |
| reranker0.6b and embedding0.6b are the same model weights？ | chaochaoli | open | 0 | disc |
| update model type and add paper link | thenlper | merged | 0 | disc |
| Add pipeline tag, link to paper and project page | nielsr | open | 0 | disc |
| Converting a reranker model to a single label classification model | ccdv | open | 0 | disc |
| TypeError: argument of type 'NoneType' is not iterable | galabala | open | 0 | disc |
| vllm open ai api | prudant | open | 0 | disc |