| { | |
| "model_type": "embernet_vlm", | |
| "architecture": "BitNet b1.58 MoE VLM", | |
| "vision_encoder": { | |
| "model_name": "google/siglip-base-patch16-224", | |
| "num_image_tokens": 64, | |
| "freeze_vision": true | |
| }, | |
| "language_decoder": { | |
| "vocab_size": 32002, | |
| "hidden_size": 768, | |
| "intermediate_size": 2048, | |
| "num_layers": 16, | |
| "num_attention_heads": 12, | |
| "num_kv_heads": 6, | |
| "max_position_embeddings": 4096, | |
| "num_experts": 8, | |
| "num_experts_per_tok": 2, | |
| "use_shared_expert": true, | |
| "expert_domains": [ | |
| "vision_ocr", | |
| "vision_diagram", | |
| "code_math_chart", | |
| "code_math_formula", | |
| "spatial_scene", | |
| "spatial_reasoning", | |
| "agentic_knowledge", | |
| "agentic_reasoning" | |
| ], | |
| "quantisation": "BitNet b1.58 (ternary)", | |
| "activation_bits": 4 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": ">=4.36.0" | |
| } |