| { | |
| "module": "keras_hub.src.models.gpt_oss.gpt_oss_causal_lm", | |
| "class_name": "GptOssCausalLM", | |
| "config": { | |
| "backbone": { | |
| "module": "keras_hub.src.models.gpt_oss.gpt_oss_backbone", | |
| "class_name": "GptOssBackbone", | |
| "config": { | |
| "name": "gpt_oss_backbone", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "vocabulary_size": 201088, | |
| "num_layers": 24, | |
| "num_query_heads": 64, | |
| "hidden_dim": 2880, | |
| "intermediate_dim": 2880, | |
| "num_experts": 32, | |
| "top_k": 4, | |
| "rope_max_wavelength": 150000, | |
| "rope_scaling_factor": 32.0, | |
| "num_key_value_heads": 8, | |
| "sliding_window": 128, | |
| "layer_norm_epsilon": 1e-05, | |
| "dropout": 0, | |
| "output_router_logits": false, | |
| "head_dim": 64 | |
| }, | |
| "registered_name": "keras_hub>GptOssBackbone" | |
| }, | |
| "preprocessor": { | |
| "module": "keras_hub.src.models.gpt_oss.gpt_oss_causal_lm_preprocessor", | |
| "class_name": "GptOssCausalLMPreprocessor", | |
| "config": { | |
| "name": "gpt_oss_causal_lm_preprocessor_1", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "tokenizer": { | |
| "module": "keras_hub.src.models.gpt_oss.gpt_oss_tokenizer", | |
| "class_name": "GptOssTokenizer", | |
| "config": { | |
| "name": "gpt_oss_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": [ | |
| "<|endoftext|>" | |
| ] | |
| }, | |
| "registered_name": "keras_hub>GptOssTokenizer" | |
| }, | |
| "config_file": "preprocessor.json", | |
| "sequence_length": 1024, | |
| "add_start_token": true, | |
| "add_end_token": true | |
| }, | |
| "registered_name": "keras_hub>GptOssCausalLMPreprocessor" | |
| }, | |
| "name": "gpt_oss_causal_lm" | |
| }, | |
| "registered_name": "keras_hub>GptOssCausalLM" | |
| } |