| { |
| "architectures": [ |
| "GemmaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 2, |
| "eos_token_id": 1, |
| "head_dim": 256, |
| "hidden_act": "gelu", |
| "hidden_size": 2048, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "initializer_range": 0.02, |
| "intermediate_size": 16384, |
| "max_position_embeddings": 8192, |
| "model_type": "gemma", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 18, |
| "num_key_value_heads": 1, |
| "pad_token_id": 0, |
| "query_pre_attn_scalar": 256, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.38.0.dev0", |
| "use_cache": true, |
| "vocab_size": 256000 |
| } |
|
|
