| { | |
| "module": "keras_hub.src.models.qwen_moe.qwen_moe_causal_lm", | |
| "class_name": "QwenMoeCausalLM", | |
| "config": { | |
| "backbone": { | |
| "module": "keras_hub.src.models.qwen_moe.qwen_moe_backbone", | |
| "class_name": "QwenMoeBackbone", | |
| "config": { | |
| "name": "qwen_moe_backbone", | |
| "trainable": true, | |
| "vocabulary_size": 151936, | |
| "num_layers": 24, | |
| "num_query_heads": 16, | |
| "hidden_dim": 2048, | |
| "intermediate_dim": 5632, | |
| "moe_intermediate_dim": 1408, | |
| "shared_expert_intermediate_dim": 5632, | |
| "rope_max_wavelength": 1000000.0, | |
| "num_key_value_heads": 16, | |
| "rope_scaling_factor": 1.0, | |
| "layer_norm_epsilon": 1e-06, | |
| "dropout": 0, | |
| "tie_word_embeddings": false, | |
| "use_sliding_window_attention": false, | |
| "sliding_window_size": 32768, | |
| "num_experts": 60, | |
| "top_k": 4, | |
| "norm_top_k_prob": false, | |
| "decoder_sparse_step": 1, | |
| "mlp_only_layers": [], | |
| "output_router_logits": false | |
| }, | |
| "registered_name": "keras_hub>QwenMoeBackbone" | |
| }, | |
| "preprocessor": { | |
| "module": "keras_hub.src.models.qwen_moe.qwen_moe_causal_lm_preprocessor", | |
| "class_name": "QwenMoeCausalLMPreprocessor", | |
| "config": { | |
| "name": "qwen_moe_causal_lm_preprocessor_1", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "tokenizer": { | |
| "module": "keras_hub.src.models.qwen_moe.qwen_moe_tokenizer", | |
| "class_name": "QwenMoeTokenizer", | |
| "config": { | |
| "name": "qwen_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": [ | |
| "<|im_end|>", | |
| "<|endoftext|>", | |
| "<|im_start|>" | |
| ] | |
| }, | |
| "registered_name": "keras_hub>QwenMoeTokenizer" | |
| }, | |
| "config_file": "preprocessor.json", | |
| "sequence_length": 1024, | |
| "add_start_token": true, | |
| "add_end_token": true | |
| }, | |
| "registered_name": "keras_hub>QwenMoeCausalLMPreprocessor" | |
| }, | |
| "name": "qwen_moe_causal_lm_1" | |
| }, | |
| "registered_name": "keras_hub>QwenMoeCausalLM" | |
| } |