| { | |
| "module": "keras_hub.src.models.mistral.mistral_causal_lm", | |
| "class_name": "MistralCausalLM", | |
| "config": { | |
| "backbone": { | |
| "module": "keras_hub.src.models.mistral.mistral_backbone", | |
| "class_name": "MistralBackbone", | |
| "config": { | |
| "name": "mistral_backbone_1", | |
| "trainable": true, | |
| "vocabulary_size": 32000, | |
| "num_layers": 32, | |
| "num_query_heads": 32, | |
| "hidden_dim": 4096, | |
| "intermediate_dim": 14336, | |
| "rope_max_wavelength": 10000.0, | |
| "rope_scaling_factor": 1.0, | |
| "num_key_value_heads": 8, | |
| "sliding_window": 4096, | |
| "layer_norm_epsilon": 1e-05, | |
| "dropout": 0 | |
| }, | |
| "registered_name": "keras_hub>MistralBackbone" | |
| }, | |
| "preprocessor": { | |
| "module": "keras_hub.src.models.mistral.mistral_causal_lm_preprocessor", | |
| "class_name": "MistralCausalLMPreprocessor", | |
| "config": { | |
| "name": "mistral_causal_lm_preprocessor", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "bfloat16" | |
| }, | |
| "registered_name": null | |
| }, | |
| "tokenizer": { | |
| "module": "keras_hub.src.models.mistral.mistral_tokenizer", | |
| "class_name": "MistralTokenizer", | |
| "config": { | |
| "name": "mistral_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>MistralTokenizer" | |
| }, | |
| "config_file": "preprocessor.json", | |
| "sequence_length": 1024, | |
| "add_start_token": true, | |
| "add_end_token": true | |
| }, | |
| "registered_name": "keras_hub>MistralCausalLMPreprocessor" | |
| }, | |
| "name": "mistral_causal_lm" | |
| }, | |
| "registered_name": "keras_hub>MistralCausalLM" | |
| } |