{ "source": "MoonViT tower from moonshotai/Kimi-K2.6 (via exolabs extract) + trained projector from baseten/GLM-5.2-Vision-NVFP4", "component": "vision_tower + mm_projector", "model_type": "kimi_k25", "vision_config": { "patch_size": 14, "init_pos_emb_height": 64, "init_pos_emb_width": 64, "init_pos_emb_time": 4, "pos_emb_type": "divided_fixed", "num_attention_heads": 16, "num_hidden_layers": 27, "hidden_size": 1152, "intermediate_size": 4304, "vt_num_attention_heads": 16, "vt_num_hidden_layers": 27, "vt_hidden_size": 1152, "vt_intermediate_size": 4304, "merge_kernel_size": [ 2, 2 ], "video_attn_type": "spatial_temporal", "merge_type": "sd2_tpool", "mm_projector_type": "patchmerger", "mm_hidden_size": 1152, "projector_hidden_act": "gelu", "projector_ln_eps": 1e-05, "text_hidden_size": 6144 }, "text_config": { "hidden_size": 6144 }, "media_placeholder_token_id": 154854, "original_dtype": "bfloat16", "num_tensors": 335 }