전체 검색
AI 모델 84759
- nsfwcaption-qwen3-vl-8b-v3-gguf↗
GitMylo
- Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-gguf↗
Goekdeniz-Guelmez
- paligemma2-3b-pt-896-keras↗
Google
- opus-mt-en-tl↗
Helsinki-NLP
- Ling-1T-GGUF↗
honda6666
- rwkv7-g1k-lora-sft-v1-merged↗
Ilikemechuri
- bioclip-2↗
imageomics
/resolve/main/ )| |:--| |**Figure #.** Image of .| --> BioCLIP 2 is a foundation model for biology organismal images. It is trained on TreeOfLife-200M on the basis of a CLIP model (ViT-14/L) pre-trained on LAION-2B. BioCLIP 2 yields state-of-the-art performance in recognizing various species. More importantly, it demonstrates emergent properties beyond species classification after extensive hierarchical contrastive training. Foundation models trained at scale exhibit emergent properties beyond their initial training objectives. BioCLIP 2 demonstrates such emergence beyond species classification by scaling up the hierarchical contrastive training proposed by BioCLIP. The model is trained on TreeOfLife-200M (the largest and most diverse available dataset of biology images). We evaluate BioCLIP 2 on a diverse set of biological tasks. Through training at scale, BioCLIP 2 improves species classification by 18.1% over BioCLIP. More importantly, we demonstrate that BioCLIP 2 generalizes to diverse biological questions beyond species classification solely through species-level supersvision. Further analysis reveals that BioCLIP 2 acquires two emergent properties through scaling up hierarchical contrastive learning: inter-species ecological alignment and intra-species variation separation.
- tiny_glm4_moe_2.8B_0.7B↗
imdatta0
- Mistral-Small-3.2-24B-Instruct-2506-int4-AutoRound↗
Intel
- Qwen3-Next-80B-A3B-moved-store↗
jalenluorion