google/siglip2-base-patch16-224 Zero-Shot Image Classification β’ 0.4B β’ Updated Feb 21, 2025 β’ 1.2M β’ 164
view post Post 4,166 Google releases EmbeddingGemma 2, a new open embedding model that runs locally on 0.5GB RAM.The 740M parameter Apache 2.0 model combines a 270M text model with vision (170M) + audio (300M).Run & train the model via Unsloth.GGUF: unsloth/embeddinggemma-2-GGUFGuide: https://unsloth.ai/docs/models/embeddinggemma-2 See translation β€οΈ 8 8 π 7 7 π₯ 4 4 π 4 4 π 3 3 + Reply
Running on Zero MCP 294 ImageGen πΌ 294 Multi-task image generator with dynamic, chainable workflows
Running Featured 951 Jev Decision Index π¬ 951 Benchmarks and news on various repros of TypeSafe's Jev
convaiinnovations/laya Text Classification β’ 0.4B β’ Updated about 23 hours ago β’ 15.8k β’ β’ 5.99k
prism-ml/Ternary-Bonsai-2-27B-gguf Text Generation β’ 27B β’ Updated 16 days ago β’ 1.35M β’ 3.08k
Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed Text Generation β’ 27B β’ Updated Sep 24 β’ 19.8k β’ 171
DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 Image-Text-to-Text β’ 28B β’ Updated 11 days ago β’ 641 β’ 145
view post Post 23,010 Qwen3.8 - 27B - COLD FUSION Reduction in thinking tokens to 1/10 to 1/2 "normal Qwen" across all three modes of thinking without loss of detail in thinking or output.Increase in general intelligence too (all 7 critical benches); bench marks posted.Trained using the COLD FUSION method (GAIN + UNSLOTH).NOTE: This is NOT a heretic / uncensored version.MTP and GGUF NEO MAX quants: DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUFSOURCE: DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 See translation 7 replies Β· π 18 18 π₯ 14 14 π€ 6 6 π§ 4 4 π 3 3 π 1 1 + Reply