| { | |
| "_name_or_path": "Tensoic/Cerule", | |
| "architectures": [ | |
| "CeruleGemmaForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_gemma.CeruleGemmaConfig", | |
| "AutoModelForCausalLM": "modeling_cerule_gemma.CeruleGemmaForCausalLM" | |
| }, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "freeze_mm_mlp_adapter": false, | |
| "head_dim": 256, | |
| "hidden_act": "gelu", | |
| "hidden_size": 2048, | |
| "image_aspect_ratio": "pad", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 16384, | |
| "max_position_embeddings": 8192, | |
| "mm_hidden_size": 1152, | |
| "mm_projector_lr": null, | |
| "mm_projector_type": "mlp2x_gelu", | |
| "mm_vision_tower": "google/siglip-so400m-patch14-384", | |
| "model_type": "phi-msft", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 18, | |
| "num_key_value_heads": 1, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tokenizer_model_max_length": 2048, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.39.0.dev0", | |
| "tune_mm_mlp_adapter": false, | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "vocab_size": 256000 | |
| } | |