Search FoxAI

AI Models 84759

• CLIP-convnext_base_w_320-laion_aesthetic-s13B-b82K↗

  laion

• Hermes-3-Llama-3.1-70B-IMat-GGUF↗

  legraphista

• EXAONE 4.5 33B (Reasoning)↗

  LG AI Research

• LTX-2.5-22b-LoRA-Slow-Motion-Control↗

  Lightricks

• Llama-3-Open-Ko-8B-Instruct-preview-GGUF↗

  LiteLLMs

• Llama-3.2-1B-Instruct-TOFU-forget10-GradDiff-SAM↗

  Lordvarun23

• vietlegal-harrier-0.6b↗

  mainguyen9

• gemma-3-1b-it-abliterated-GGUF↗

  MaziyarPanahi

• LLM2Vec-Meta-Llama-3-8B-Instruct-mntp↗

  McGill-NLP

  > LLM2Vec is a simple recipe to convert decoder-only LLMs into text encoders. It consists of 3 simple steps: 1) enabling bidirectional attention, 2) masked next token prediction, and 3) unsupervised contrastive learning. The model can be further fine-tuned to achieve state-of-the-art performance. - **Repository:** https://github.com/McGill-NLP/llm2vec - **Paper:** https://arxiv.org/abs/2404.05961 If you have any question about the code, feel free to email Parishad (`parishad.behnamghader@mila.quebec`) and Vaibhav (`vaibhav.adlakha@mila.quebec`).

• kanana-1.5-8b-instruct-2505-Safe-DPO↗

  mgmbykai