|
{ |
|
"module": "keras_hub.src.models.mixtral.mixtral_causal_lm", |
|
"class_name": "MixtralCausalLM", |
|
"config": { |
|
"backbone": { |
|
"module": "keras_hub.src.models.mixtral.mixtral_backbone", |
|
"class_name": "MixtralBackbone", |
|
"config": { |
|
"name": "mixtral_backbone", |
|
"trainable": true, |
|
"vocabulary_size": 32000, |
|
"num_layers": 32, |
|
"num_query_heads": 32, |
|
"hidden_dim": 4096, |
|
"intermediate_dim": 14336, |
|
"num_experts": 8, |
|
"top_k": 2, |
|
"router_jitter_noise": 0.0, |
|
"rope_max_wavelength": 1000000.0, |
|
"rope_scaling_factor": 1.0, |
|
"num_key_value_heads": 8, |
|
"router_aux_loss_coef": 0.02, |
|
"sliding_window": null, |
|
"layer_norm_epsilon": 1e-05, |
|
"dropout": 0 |
|
}, |
|
"registered_name": "keras_hub>MixtralBackbone" |
|
}, |
|
"preprocessor": { |
|
"module": "keras_hub.src.models.mixtral.mixtral_causal_lm_preprocessor", |
|
"class_name": "MixtralCausalLMPreprocessor", |
|
"config": { |
|
"name": "mixtral_causal_lm_preprocessor_2", |
|
"trainable": true, |
|
"dtype": { |
|
"module": "keras", |
|
"class_name": "DTypePolicy", |
|
"config": { |
|
"name": "float32" |
|
}, |
|
"registered_name": null |
|
}, |
|
"tokenizer": { |
|
"module": "keras_hub.src.models.mixtral.mixtral_tokenizer", |
|
"class_name": "MixtralTokenizer", |
|
"config": { |
|
"name": "mixtral_tokenizer", |
|
"trainable": true, |
|
"dtype": { |
|
"module": "keras", |
|
"class_name": "DTypePolicy", |
|
"config": { |
|
"name": "int32" |
|
}, |
|
"registered_name": null |
|
}, |
|
"config_file": "tokenizer.json", |
|
"proto": null, |
|
"sequence_length": null, |
|
"add_bos": false, |
|
"add_eos": false |
|
}, |
|
"registered_name": "keras_hub>MixtralTokenizer" |
|
}, |
|
"config_file": "preprocessor.json", |
|
"sequence_length": 1024, |
|
"add_start_token": true, |
|
"add_end_token": true |
|
}, |
|
"registered_name": "keras_hub>MixtralCausalLMPreprocessor" |
|
}, |
|
"name": "mixtral_causal_lm" |
|
}, |
|
"registered_name": "keras_hub>MixtralCausalLM" |
|
} |