CoolFace
16 results

text-matching

inallmodelsdatasetsappsagentspeopleprojects

Models

All models matching “text-matching”
jinaai /jina-embeddings-v5-text-small-text-matchingsentence-similarityllama.cpp12 likes91k downloads5mo agoHugging Facejinaai /jina-embeddings-v5-text-nano-text-matchingsentence-similarityllama.cpp7 likes3k downloads5mo agoHugging Facejinaai /jina-embeddings-v4-text-matching-GGUF9 likes2k downloads1y agoHugging Facejinaai /jina-embeddings-v5-omni-small-text-matching-GGUFfeature-extractionllama.cpp5 likes923 downloads4mo agoHugging Facejinaai /jina-embeddings-v5-omni-nano-text-matching-GGUFfeature-extractionllama.cpp1 likes772 downloads4mo agoHugging Facejinaai /jina-embeddings-v5-omni-small-text-matchingfeature-extractiontransformers1 likes669 downloads28d agoHugging Facejinaai /jina-embeddings-v5-text-nano-text-matching-GGUFsentence-similarityllama.cpp2 likes616 downloads7mo agoHugging Facejinaai /jina-embeddings-v5-text-small-text-matching-GGUFsentence-similarityllama.cpp3 likes610 downloads7mo agoHugging Face

Datasets

All datasets matching “text-matching”
ThatsGroes /synthetic-from-text-matching-short-tasks-danish Thanks to Arrow Denmark and Nvidia for sponsoring the compute used to generate this dataset The purpose of this dataset is to pre- or post-train embedding models for Danish text matching tasks on short texts. The dataset consists of 100,000 samples generated with gemma-2-27b-it. The column "prompt" shows the prompt given to the LLM and "response" shows the LLM output. Each sample in the dataset was generated from a seed task randomly sampled from… See the full description on the dataset page: https://huggingface.co/datasets/ThatsGroes/synthetic-from-text-matching-short-tasks-danish.texttext-retrieval100K<n<1M0 likes40 downloads2y agoHugging FaceThatsGroes /synthetic-from-text-matching-long-tasks-swedish Thanks to Arrow Denmark and Nvidia for sponsoring the compute used to generate this dataset The purpose of this dataset is to pre- or post-train embedding models for text matching tasks. The dataset consists of 100,000 samples generated with gemma-2-27b-it. The column "prompt" shows the prompt given to the LLM and "response" shows the LLM output. Each sample in the dataset was generated from a seed task randomly sampled from… See the full description on the dataset page: https://huggingface.co/datasets/ThatsGroes/synthetic-from-text-matching-long-tasks-swedish.text10K<n<100K1 likes38 downloads2y agoHugging Facekardosdrur /synthetic-nordic-text_matchingtext100K<n<1M0 likes24 downloads1y agoHugging FaceThatsGroes /synthetic-from-text-matching-long-tasks-danish Thanks to Arrow Denmark and Nvidia for sponsoring the compute used to generate this dataset The purpose of this dataset is to pre- or post-train embedding models for Danish text matching tasks. The dataset consists of 100,000 samples generated with gemma-2-27b-it. The column "prompt" shows the prompt given to the LLM and "response" shows the LLM output. Each sample in the dataset was generated from a seed task randomly sampled from… See the full description on the dataset page: https://huggingface.co/datasets/ThatsGroes/synthetic-from-text-matching-long-tasks-danish.texttext-retrieval100K<n<1M0 likes19 downloads2y agoHugging Facecatlove007 /multilingual-text-matchingtext100K<n<1M0 likes17 downloads3y agoHugging FaceThatsGroes /text-matching-long-tasks-processedtext100K<n<1M0 likes13 downloads2y agoHugging Face

Apps

All apps matching “text-matching”
lordvader31 /text-matchingstreamlit2 likes3y agoHugging FaceInf009 /image-text-matchinggradio0 likes3y agoHugging Face