| { |
| "module": "keras_hub.src.models.qwen3_5_moe.qwen3_5_moe_causal_lm", |
| "class_name": "Qwen3_5MoeCausalLM", |
| "config": { |
| "backbone": { |
| "module": "keras_hub.src.models.qwen3_5_moe.qwen3_5_moe_backbone", |
| "class_name": "Qwen3_5MoeBackbone", |
| "config": { |
| "name": "qwen3_5_moe_backbone", |
| "trainable": true, |
| "dtype": { |
| "module": "keras", |
| "class_name": "DTypePolicy", |
| "config": { |
| "name": "float32" |
| }, |
| "registered_name": null |
| }, |
| "vocabulary_size": 248320, |
| "num_layers": 40, |
| "num_query_heads": 16, |
| "hidden_dim": 2048, |
| "head_dim": 256, |
| "moe_intermediate_dim": 512, |
| "shared_expert_intermediate_size": 512, |
| "num_experts": 256, |
| "top_k": 8, |
| "layer_types": [ |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention" |
| ], |
| "partial_rotary_factor": 0.25, |
| "rope_max_wavelength": 10000000, |
| "rope_scaling_factor": 1.0, |
| "num_key_value_heads": 2, |
| "layer_norm_epsilon": 1e-06, |
| "dropout": 0.0, |
| "tie_word_embeddings": false, |
| "sliding_window_size": 32768, |
| "linear_num_key_heads": 16, |
| "linear_num_value_heads": 32, |
| "linear_key_head_dim": 128, |
| "linear_value_head_dim": 128, |
| "linear_conv_kernel_dim": 4, |
| "mrope_section": [ |
| 11, |
| 11, |
| 10 |
| ], |
| "router_aux_loss_coefficient": 0.001, |
| "vision_encoder": null |
| }, |
| "registered_name": "keras_hub>Qwen3_5MoeBackbone" |
| }, |
| "preprocessor": { |
| "module": "keras_hub.src.models.qwen3_5_moe.qwen3_5_moe_causal_lm_preprocessor", |
| "class_name": "Qwen3_5MoeCausalLMPreprocessor", |
| "config": { |
| "name": "qwen3_5_moe_causal_lm_preprocessor", |
| "trainable": true, |
| "dtype": { |
| "module": "keras", |
| "class_name": "DTypePolicy", |
| "config": { |
| "name": "float32" |
| }, |
| "registered_name": null |
| }, |
| "tokenizer": { |
| "module": "keras_hub.src.models.qwen3_5_moe.qwen3_5_moe_tokenizer", |
| "class_name": "Qwen3_5MoeTokenizer", |
| "config": { |
| "name": "qwen3_5_moe_tokenizer", |
| "trainable": true, |
| "dtype": { |
| "module": "keras", |
| "class_name": "DTypePolicy", |
| "config": { |
| "name": "int32" |
| }, |
| "registered_name": null |
| }, |
| "config_file": "tokenizer.json", |
| "sequence_length": null, |
| "add_prefix_space": false, |
| "unsplittable_tokens": [ |
| "<|vision_start|>", |
| "<|fim_prefix|>", |
| "<|repo_name|>", |
| "<|fim_middle|>", |
| "<|object_ref_start|>", |
| "</think>", |
| "<|fim_suffix|>", |
| "</tool_response>", |
| "<|object_ref_end|>", |
| "<|im_end|>", |
| "<think>", |
| "<|vision_pad|>", |
| "<|file_sep|>", |
| "<tool_response>", |
| "<|quad_start|>", |
| "<|im_start|>", |
| "</tool_call>", |
| "<|video_pad|>", |
| "<|fim_pad|>", |
| "<|image_pad|>", |
| "<tool_call>", |
| "<|box_end|>", |
| "<|quad_end|>", |
| "<|box_start|>", |
| "<|endoftext|>", |
| "<|vision_end|>" |
| ], |
| "has_vision_tokens": true |
| }, |
| "registered_name": "keras_hub>Qwen3_5MoeTokenizer" |
| }, |
| "config_file": "preprocessor.json", |
| "sequence_length": 1024, |
| "add_start_token": false, |
| "add_end_token": true, |
| "video_fps": 2.0 |
| }, |
| "registered_name": "keras_hub>Qwen3_5MoeCausalLMPreprocessor" |
| }, |
| "name": "qwen3_5_moe_causal_lm" |
| }, |
| "registered_name": "keras_hub>Qwen3_5MoeCausalLM" |
| } |
