| { |
| "architectures": [ |
| "Gemma2ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_logit_softcapping": 50.0, |
| "bos_token_id": 2, |
| "cache_implementation": "hybrid", |
| "dtype": "bfloat16", |
| "eos_token_id": 1, |
| "final_logit_softcapping": 30.0, |
| "head_dim": 256, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 2304, |
| "initializer_range": 0.02, |
| "intermediate_size": 9216, |
| "layer_types": [ |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 8192, |
| "model_type": "gemma2", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 26, |
| "num_key_value_heads": 4, |
| "pad_token_id": 0, |
| "query_pre_attn_scalar": 224, |
| "rms_norm_eps": 1e-06, |
| "rope_theta": 10000.0, |
| "sliding_window": 4096, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 256000 |
| } |
|
|
