{ "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "head_dim": 128, "hidden_act": "silu", "hidden_size": 5120, "image_token_index": 10, "initializer_range": 0.02, "intermediate_size": 32768, "max_position_embeddings": 131072, "model_type": "mistral", "multimodal_projector_bias": false, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "projector_hidden_act": "gelu", "quantization": { "group_size": 64, "bits": 8 }, "quantization_config": { "group_size": 64, "bits": 8 }, "rms_norm_eps": 1e-05, "rope_theta": 1000000000.0, "sliding_window": null, "spatial_merge_size": 2, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.50.0.dev0", "use_cache": true, "vision_feature_layer": -1, "vocab_size": 131072 }