| VORTEXRAG: 7-Layer RAG — Causal Drift Filtering + Context Poison Guard [paper + code + demo] | vigneshwar234 | open | 0 | disc |
| VORTEXRAG: 7-Layer RAG — Causal Drift Filtering + Context Poison Guard [paper + code + demo] | vigneshwar234 | open | 0 | disc |
| Convert model to onnx format | ekatrinaryazanova | open | 0 | disc |
| Integrate with Sentence Transformers v5.4 | tomaarsen | merged | 0 | disc |
| Add evaluation results for model jinaai/jina-embeddings-v3 revision 215a6e121fa0183376388ac6b1ae230326bfeaed | Samoed | open | 0 | disc |
| Update model to standard HF format | Sai-Suraj | open | 0 | disc |
| how to use task with ollama | ohhhchank3 | open | 0 | disc |
| how to use task in vllm | NasrFathy123 | open | 0 | disc |
| Issue comes with: "TypeError: Failed to fetch" in the web page: "https://jina.ai/api-dashboard/embedding" | g787796121 | closed | 0 | disc |
| LM Studio | Syams | open | 0 | disc |
| Problem loading the model in bf16 | LouisDo2108 | closed | 0 | disc |
| NotImplementedError When calling resize_token_embeddings | OSalem99 | open | 0 | disc |
| how to load the jina-clip-v2 model offline? help me plz!! | HT-NEKO | open | 0 | disc |
| Is there a way to train Jina-embeddings-v3 using Transformers Trainer API? (Encountering NameError in rotary.py) | saadaltohamy | open | 0 | disc |
| Saving and Loading Finetuned Model- Bug in JinaAI code? | nebulousest | closed | 0 | disc |
| Update config.json | vaidehiBhamare | open | 0 | disc |
| houtao | thou123 | draft | 0 | disc |
| thou123 | thou123 | draft | 0 | disc |
| Congrats! you are SOTA on The Arabic RAG Leaderboard | MohamedRashad | open | 0 | disc |
| Is it possible to set the revision of `xlm-roberta-flash-implementation`? | aciddust20 | open | 0 | disc |
| No sentence-transformers model found with name jinaai/jina-embeddings-v3. | siarez | closed | 0 | disc |
| output_attentions returns None | ymali | open | 0 | disc |
| 启动不了 | onthewayzh | open | 0 | disc |
| The process to convert this model to onnx format | dinhanhx | open | 0 | disc |
| when gguf support? | dfsafdsf | open | 0 | disc |
| File not found error | ritz2201 | open | 0 | disc |
| natural language retrieval of code blocks | Amashiro2233 | open | 0 | disc |
| feat-add-cmteb-qbqtc | nan | merged | 0 | disc |
| triton error when convert to onnx | hoailebads | open | 0 | disc |
| Unrecognized model in ./modellib/jinaai/ , Should have a `model_type` key in its config.json | NFYG | closed | 0 | disc |
| Using with vLLM | fpaupier | open | 0 | disc |
| Slow tokenizer availability | QuentinFvr | open | 0 | disc |
| Merging LoRA adapters into base weights | arianomidi | open | 0 | disc |
| how can i realize late_chunking parameter? | MASTERwei | open | 0 | disc |
| Is the tokenization and mean pooling method described in the documentation here performing "late chunking" as it is described in your paper/library "late-chunking"? | imambujang | open | 0 | disc |
| Where vocab save ? | batman9x | open | 0 | disc |
| Code examples not working with transformers or sentence-transformers | anto5040 | closed | 0 | disc |
| inference is too slow using task adapters (on cpu) | ffletcherr | open | 0 | disc |
| chore-fix-logo | bwang0911 | merged | 0 | disc |
| Openvino errors | Florianoli | open | 0 | disc |
| Start by gunicorn, model.encode() stuck forever | andrewzheng1618 | open | 0 | disc |
| how to sovle the" A new version of the following files was downloaded from https://huggingface.co/jinaai/xlm-roberta-flash-implementation:" | gauyer | open | 0 | disc |
| Hardware recomendations help | MLSDev | open | 0 | disc |
| How to set the size of the ONNX model output dimensions? | Hex2Dec | closed | 0 | disc |
| Example for Fine-Tuning Models on Asymmetric Semantic Search with Hard Negatives. | wilfoderek | open | 0 | disc |
| Returning all hidden states | carolinmschuster | closed | 0 | disc |
| Error loading model using AutoModel.from_pretrained | sjoshi-wm | open | 0 | disc |
| Help decoding retrieved vector values to "see" what a chunk looks like in natural language | k0rruptt | closed | 0 | disc |
| Ollama drop? | kagevazquez | open | 0 | disc |
| readme: azure link | jupyterjazz | merged | 0 | disc |
| can I use task = "retrieval.query" with transformers library? | k0rruptt | closed | 0 | disc |
| Finetuning for assymetric semantic similarity? | shensmobile | open | 0 | disc |
| Finetune for document retrieval task | truong1301 | open | 0 | disc |
| Minor Recommendations | zboyles | closed | 0 | disc |
| Finetuning The Model with Custom Dataset | eneSadi | open | 0 | disc |
| `FlashAttention is not installed` error on Windows 11 | ocean11 | closed | 0 | disc |
| Using jina-embeddings-v3 for zero-shot-classification task | yrayegan | open | 0 | disc |
| Troubleshooting RuntimeError in Sentence Transformers with Multi-Process Pool | SamMaggioli | open | 0 | disc |
| code_revision problem with ST | jupyterjazz | closed | 0 | disc |
| fix: normalization after truncation | jupyterjazz | merged | 0 | disc |
| readme: add onnx mean pool function | knysfh | merged | 0 | disc |
| How can I use this model offline? | BenWan | open | 0 | disc |
| No model found error | huggit0000 | open | 0 | disc |
| Resolved-please delete this post | huggit0000 | closed | 0 | disc |
| ONNX model 13049 outputs | here4data | open | 0 | disc |
| Fine Tuning Jina Embedding V3 for classification task | mumeranwaar | closed | 0 | disc |
| add onnx model mean pooling code | knysfh | closed | 0 | disc |
| ModuleNotFoundError: No module named 'custom_st' | LeMoussel | closed | 0 | disc |
| fine tuning adapter take longer than fine tuning whole model | hail75 | open | 0 | disc |
| Pros and cons of finetuning only adapters | hail75 | closed | 0 | disc |
| Can this model upload a model_quantized.onnx file, similar to jina-embeddings-v2-base-zh? | JoeZhang | open | 0 | disc |
| Adapter selection for training with retrieval data | hail75 | open | 0 | disc |
| retrieval finetuning and loss function used | hail75 | closed | 0 | disc |
| Update config.json | VuaCoBac | closed | 0 | disc |
| readme: onnx final outputs | jupyterjazz | merged | 0 | disc |
| How to serve a jina-embeddings-v3 classification task using onnxruntime | luozhouyang | open | 0 | disc |
| Disable tqdm | ivanstepanovftw | open | 0 | disc |
| What if I want to run xlm-roberta-flash-implementation locally? | Nucleon-17th | closed | 0 | disc |
| ONNX export | rztk-bohdanbilonoh | closed | 0 | disc |
| chore-add-mmteb | bwang0911 | draft | 0 | disc |
| chore-update-mmteb | bwang0911 | closed | 0 | disc |
| truncate_dim=N returns non-normalized embeddings | ivanstepanovftw | closed | 0 | disc |
| Sentences only? What is the best way to create sentences from documents? | turian | open | 0 | disc |
| Can this be used as a reranker ? | pepoo20 | closed | 0 | disc |
| StopIteration: Caught StopIteration in replica 0 on device 0. | seregadgl | open | 0 | disc |
| How to finetune this model with transformers? | xianf | closed | 0 | disc |
| Update custom_st.py to be compatible with Python 3.8 | pewh | merged | 0 | disc |
| Update custom_st.py to be compatible with Python 3.8 | pewh | closed | 0 | disc |
| remove-st-prompt-length | jupyterjazz | merged | 0 | disc |
| FileNotFoundError | Samoed | closed | 0 | disc |
| custom_pt dict error only visible in sentence transformers and not in normal transformers why? | sleeping4cat | closed | 0 | disc |
| Save Transformer module in root when training with ST | tomaarsen | merged | 0 | disc |
| Running into "Flash attention implementation does not support kwargs: prompt_length" when using the exact example from the Readme | HotSauce7 | closed | 0 | disc |
| Bulk embedding error | aikokul | closed | 0 | disc |
| RuntimeError: FlashAttention is not installed. | seregadgl | closed | 0 | disc |
| SentenceTransformerTrainer: checkpoint saves custom_st.py in the wrong folder | botkop | closed | 0 | disc |
| Add compatibility with Sentence Transformers v3.2.0 | tomaarsen | merged | 0 | disc |
| unexpected keyword argument 'backend' when installing with sentence transformers | botkop | closed | 0 | disc |
| readme: finetuning | jupyterjazz | merged | 0 | disc |
| feat: finetuning via ST | jupyterjazz | merged | 0 | disc |
| Fine-tuning model | epishchik | closed | 0 | disc |
| jina | chengtaoo | closed | 0 | disc |
| Release Custom finetune code with torch? | CVHvn | closed | 0 | disc |
| ONNX model output | Riddler2024 | closed | 0 | disc |
| Add Sentence Transformers tag | tomaarsen | merged | 0 | disc |
| How can I fine-tune my own dataset? | liu0815 | closed | 0 | disc |
| Accept tokens instead of string and question regarding tokenizer behaviour | MH1P | open | 0 | disc |
| Model seems to be incredibly slow on CPU | adi751 | closed | 0 | disc |
| No model named 'custom_st' | RICHKEED | closed | 0 | disc |
| Enable saving in SentenceTransformers by adding get_config_dict | edwardjross | merged | 0 | disc |
| Fine-Tuning 'retrieval.query' and 'retrieval.passage' LoRA Adapters Together? | miweru | open | 0 | disc |
| ONNX ERROR: Unsupported model IR version: 10, max supported IR version: 9 | cseeeee | closed | 0 | disc |
| add polish retrieval socre | makram93 | merged | 0 | disc |
| Created the custom branch for serving using text-embedding-inference | sigridjineth | open | 0 | disc |
| Update config.json | sigridjineth | closed | 0 | disc |
| Update config.json | sigridjineth | closed | 0 | disc |
| Update config.json | sigridjineth | closed | 0 | disc |
| Update ONNX weights | Xenova | merged | 0 | disc |
| support ST for python3.8+ | jupyterjazz | merged | 0 | disc |
| Unable to load the model through sentence_transformerss | adi751 | closed | 0 | disc |
| readme-adjustments | jupyterjazz | merged | 0 | disc |
| Adding `safetensors` variant of this model | bwang0911 | merged | 0 | disc |
| onnx-checkpoint | jupyterjazz | merged | 0 | disc |
| refactor-task | bwang0911 | merged | 0 | disc |
| Update README.md | bwang0911 | merged | 0 | disc |
| refactor: define prompts in configuration | bwang0911 | merged | 0 | disc |
| refactor: improve class init | bwang0911 | closed | 0 | disc |
| refactor: clean up num_examples code | bwang0911 | merged | 0 | disc |
| readme: performance | jupyterjazz | merged | 0 | disc |
| fix: not properly reference config | bwang0911 | merged | 0 | disc |
| fix: make sure data and adapter on same device | bwang0911 | merged | 0 | disc |
| fix device and use auto model | bwang0911 | merged | 0 | disc |
| fix: add missing adaption map | bwang0911 | merged | 0 | disc |
| fix: add missing lora adaptations | bwang0911 | merged | 0 | disc |
| feat: add pooling config for sbert | bwang0911 | merged | 0 | disc |
| fix: remove config args but pass config when initi auto model | bwang0911 | merged | 0 | disc |
| fix model loading in custom_st.py | bwang0911 | merged | 0 | disc |
| support sentence-transformers | bwang0911 | merged | 0 | disc |
| readme: usage | jupyterjazz | merged | 0 | disc |
| Update README.md | jupyterjazz | merged | 0 | disc |
| Update README.md | makram93 | merged | 0 | disc |