| { | |
| "architectures": [ | |
| "TPUGemma3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "auto_map": { | |
| "FlaxAutoModelForCausalLM": "modelling_flax_tpu_gemma3.FlaxTPUGemma3ForCausalLM" | |
| }, | |
| "bos_token_id": 2, | |
| "cache_implementation": "hybrid", | |
| "eos_token_id": 1, | |
| "expand_input_ids": false, | |
| "expand_input_ids_dict": null, | |
| "expand_input_ids_maxlen": null, | |
| "expand_input_ids_vocab_size": null, | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6912, | |
| "max_position_embeddings": 8192, | |
| "model_type": "tpu_gemma3", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 26, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": 0, | |
| "previous_hidden_size": null, | |
| "project_mode": null, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_local_base_freq": 10000, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "skip_out_norm": false, | |
| "sliding_window": 512, | |
| "sliding_window_pattern": 6, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.52.3", | |
| "use_cache": true, | |
| "vocab_size": 262144 | |
| } | |