Yesterday
-
LFM3 MLX: re-export with RNE runtime MLX schema
-
LFM3: tokenizer config variant with thinking off by default
-
Add LFM3-1.7B MLX build (int4, Apple GPU) and update the notice
-
Add LFM3-1.7B for react-native-executorch (XNNPACK 8da4w, 2048 tokens/call, 8192 context) with LFM license and notice
5 days ago
-
README: add SAM 3 section (shapes, timings, SAM License)
-
Add SAM 3 (672px, Core ML: 4 vision chunks, head, text encoder, tokenizer) with the SAM License
-
Upload da3-scanner/vulkan/da3_small_8v_560x420_vulkan.pte with huggingface_hub
-
Upload README.md with huggingface_hub
-
Upload README.md with huggingface_hub
-
Upload da3-scanner/xnnpack/da3_small_8v_560x420_xnnpack.pte with huggingface_hub
-
Upload da3-scanner/xnnpack/da3_base_8v_560x420_xnnpack.pte with huggingface_hub
-
Upload da3-scanner/coreml/da3_small_8v_560x420_coreml_fp32.pte with huggingface_hub
-
Upload da3-scanner/coreml/da3_base_8v_560x420_coreml_fp16_gpu.pte with huggingface_hub
-
Add moebius-eraser/xnnpack/moebius_unet.pte
-
Add moebius-eraser/xnnpack/moebius_vae_decoder.pte
-
Add moebius-eraser/xnnpack/moebius_vae_encoder.pte
-
Add moebius-eraser/coreml/moebius_unet.pte
-
Add moebius-eraser/coreml/moebius_vae_decoder.pte
-
Add moebius-eraser/coreml/moebius_vae_encoder.pte
-
Add README.md
-
initial commit
