| { | |
| "architectures": [ | |
| "Gemma3Model" | |
| ], | |
| "model_type": "gemma3", | |
| "vocab_size": 50257, | |
| "max_position_embeddings": 32768, | |
| "hidden_size": 640, | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 18, | |
| "intermediate_size": 2048, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.36.0", | |
| "head_dim": 256, | |
| "n_kv_groups": 1, | |
| "qk_norm": true, | |
| "rope_local_base": 10000.0, | |
| "rope_base": 1000000.0, | |
| "sliding_window": 512, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "query_pre_attn_scalar": 256 | |
| } |