|
{ |
|
"module": "keras_hub.src.models.qwen.qwen_causal_lm", |
|
"class_name": "QwenCausalLM", |
|
"config": { |
|
"backbone": { |
|
"module": "keras_hub.src.models.qwen.qwen_backbone", |
|
"class_name": "QwenBackbone", |
|
"config": { |
|
"name": "qwen_backbone", |
|
"trainable": true, |
|
"vocabulary_size": 151936, |
|
"num_layers": 24, |
|
"num_query_heads": 14, |
|
"hidden_dim": 896, |
|
"intermediate_dim": 4864, |
|
"rope_max_wavelength": 1000000.0, |
|
"rope_scaling_factor": 1.0, |
|
"num_key_value_heads": 2, |
|
"layer_norm_epsilon": 1e-06, |
|
"dropout": 0, |
|
"tie_word_embeddings": true, |
|
"use_sliding_window_attention": [ |
|
false |
|
], |
|
"sliding_window_size": 32768 |
|
}, |
|
"registered_name": "keras_hub>QwenBackbone" |
|
}, |
|
"preprocessor": { |
|
"module": "keras_hub.src.models.qwen.qwen_causal_lm_preprocessor", |
|
"class_name": "QwenCausalLMPreprocessor", |
|
"config": { |
|
"name": "qwen_causal_lm_preprocessor_2", |
|
"trainable": true, |
|
"dtype": { |
|
"module": "keras", |
|
"class_name": "DTypePolicy", |
|
"config": { |
|
"name": "float32" |
|
}, |
|
"registered_name": null |
|
}, |
|
"tokenizer": { |
|
"module": "keras_hub.src.models.qwen.qwen_tokenizer", |
|
"class_name": "QwenTokenizer", |
|
"config": { |
|
"name": "qwen_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": [ |
|
"<|object_ref_start|>", |
|
"<|endoftext|>", |
|
"<|im_start|>", |
|
"<|im_end|>", |
|
"<|fim_middle|>", |
|
"<|vision_start|>", |
|
"</tool_call>", |
|
"<|vision_pad|>", |
|
"<|fim_prefix|>", |
|
"<|box_start|>", |
|
"<|object_ref_end|>", |
|
"<|box_end|>", |
|
"<|fim_suffix|>", |
|
"<|quad_end|>", |
|
"<|vision_end|>", |
|
"<|video_pad|>", |
|
"<tool_call>", |
|
"<|file_sep|>", |
|
"<|repo_name|>", |
|
"<|image_pad|>", |
|
"<|fim_pad|>", |
|
"<|quad_start|>" |
|
] |
|
}, |
|
"registered_name": "keras_hub>QwenTokenizer" |
|
}, |
|
"config_file": "preprocessor.json", |
|
"sequence_length": 1024, |
|
"add_start_token": true, |
|
"add_end_token": true |
|
}, |
|
"registered_name": "keras_hub>QwenCausalLMPreprocessor" |
|
}, |
|
"name": "qwen_causal_lm" |
|
}, |
|
"registered_name": "keras_hub>QwenCausalLM" |
|
} |