AI가 움직이고 미래가 업데이트됩니다.embeddinggemma-2-8bit
MLX conversion of Google EmbeddingGemma 2 in **8-bit affine** format, retaining text, image, audio, and video encoders. The model produces normalized 768-dimensional embeddings. See the original model card for intended use, training information, evaluation, and limitations. Quantization mode: `affine`, 8 bits, group size 64. The standard MLX-VLM policy quantizes the text encoder and audio projection. The vision and audio towers and vision projection remain BF16. Weight storage: 1.234 GB (decimal). Source revision: `914f7f89142e33e77833254d9c9b90c3cef7303b`. Converted with MLX-VLM revision `3d87e884`, from branch `pc/embeddinggemma-2`, and MLX 0.32.3.
번역 준비 중입니다. 원문을 표시합니다.
MLX conversion of Google EmbeddingGemma 2 in **8-bit affine** format, retaining text, image, audio, and video encoders. The model produces normalized 768-dimensional embeddings. See the original model card for intended use, training information, evaluation, and limitations. Quantization mode: `affine`, 8 bits, group size 64. The standard MLX-VLM policy quantizes the text encoder and audio projection. The vision and audio towers and vision projection remain BF16. Weight storage: 1.234 GB (decimal). Source revision: `914f7f89142e33e77833254d9c9b90c3cef7303b`. Converted with MLX-VLM revision `3d87e884`, from branch `pc/embeddinggemma-2`, and MLX 0.32.3.