{ "architectures": [ "Sa2VAChatModel" ], "auto_map": { "AutoConfig": "configuration_earthmind_chat.Sa2VAChatConfig", "AutoModel": "modeling_earthmind_chat.Sa2VAChatModel", "AutoModelForCausalLM": "modeling_earthmind_chat.Sa2VAChatModel" }, "downsample_ratio": 0.5, "dtype": "bfloat16", "dynamic_image_size": true, "eos_token_id": 151645, "force_image_size": 448, "hidden_size": 2048, "llm_config": { "_name_or_path": "Qwen/Qwen2.5-3B-Instruct", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 11008, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "num_attention_heads": 16, "num_hidden_layers": 36, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "use_bfloat16": true, "use_cache": true, "use_sliding_window": false, "vocab_size": 151679 }, "max_dynamic_patch": 12, "min_dynamic_patch": 1, "model_type": "sa2va_chat", "output_attentions": false, "pad2square": false, "pad_token_id": 151643, "ps_version": "v2", "quantization_config": { "_load_in_4bit": true, "_load_in_8bit": false, "bnb_4bit_compute_dtype": "bfloat16", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "nf4", "bnb_4bit_use_double_quant": true, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": null, "llm_int8_threshold": 6.0, "load_in_4bit": true, "load_in_8bit": false, "quant_method": "bitsandbytes" }, "select_layer": -1, "template": "phi3_chat", "tie_word_embeddings": false, "transformers_version": null, "use_backbone_lora": 0, "use_cache": false, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "drop_path_rate": 0.0, "dropout": 0.0, "dtype": "bfloat16", "hidden_act": "gelu", "hidden_size": 1024, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-06, "model_type": "intern_vit_6b", "norm_type": "layer_norm", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 24, "patch_size": 14, "qk_normalization": false, "qkv_bias": true, "use_bfloat16": true, "use_flash_attn": true } }