mixedbread-ai/mxbai-embed-large-v1
29 derivatives checked
- ChristianAzinn/mxbai-embed-large-v1-gguf: Same weights, converted
- mlx-community/mxbai-embed-large-v1: Same weights, repacked
- s3dev-ai/mxbai-embed-large-v1-gguf: Same weights, converted
- cstr/mxbai-embed-large-v1-GGUF: Quantization
- blobbybob/potion-mxbai-256d-v2: Different architecture
- blobbybob/potion-mxbai-micro: Different architecture
- njw9722/tech-tuned-mxbai-embed-large: Full fine-tune
- aloobun/d-mxbai-L8-embed: Full fine-tune (fewer layers)
- tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-20-gamma-1: Same weights, converted
- Mollel/MultiLinguSwahili-mxbai-embed-large-v1-nli-matryoshka: Full fine-tune
- tomaarsen/csr-mxbai-embed-large-v1-nq-no-reconstruction: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-gooaq-2e-4: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-5-gamma-1-detach-2: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq-og: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq-no-base-loss: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-5-gamma-0.1: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq-nanobeir: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-20-gamma-1-detach-2: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-gooaq-1e-5-512bs: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq-original: Same weights, converted
- Gurveer05/mxbai-embed-large-v1-eedi-2024: Full fine-tune
- tomaarsen/csr-mxbai-embed-large-v1-nq-2: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-20-gamma-0.5-detach-2: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-50-gamma-0.1-detach-2: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-5-gamma-0.1-detach-2: Same weights, converted
- tomaarsen/csr-mxbai-embed-large-v1-nq-updated-reconstruction-2: Same weights, converted
- mrm8488/mxbai-embed-large-v1-ft-webinstruct: Full fine-tune
- lorelaiassistant/mxbai-embed-large-v1-mlx-int6: Quantization
6 other repos hold byte-for-byte identical weight files.