{ "architectures": [ "MiniMaxVL01ForConditionalGeneration" ], "auto_map": { "AutoModelForCausalLM": "modeling_minimax_vl_01.MiniMaxVL01ForConditionalGeneration", "AutoConfig": "configuration_minimax_vl_01.MiniMaxVL01Config" }, "ignore_index": -100, "image_grid_pinpoints": [ [ 336, 336 ], [ 336, 672 ], [ 336, 1008 ], [ 336, 1344 ], [ 336, 1680 ], [ 336, 2016 ], [ 672, 336 ], [ 672, 672 ], [ 672, 1008 ], [ 672, 1344 ], [ 672, 1680 ], [ 672, 2016 ], [ 1008, 336 ], [ 1008, 672 ], [ 1008, 1008 ], [ 1008, 1344 ], [ 1008, 1680 ], [ 1008, 2016 ], [ 1344, 336 ], [ 1344, 672 ], [ 1344, 1008 ], [ 1344, 1344 ], [ 1680, 336 ], [ 1680, 672 ], [ 1680, 1008 ], [ 2016, 336 ], [ 2016, 672 ], [ 2016, 1008 ] ], "image_token_index": 200025, "model_type": "minimax_vl_01", "projector_hidden_act": "gelu", "text_config": { "architectures": [ "MiniMaxText01ForCausalLM" ], "attn_type_list": [ 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1 ], "bos_token_id": null, "eos_token_id": null, "head_dim": 128, "hidden_size": 6144, "intermediate_size": 9216, "layernorm_full_attention_alpha": 3.5565588200778455, "layernorm_full_attention_beta": 1.0, "layernorm_linear_attention_alpha": 3.5565588200778455, "layernorm_linear_attention_beta": 1.0, "layernorm_mlp_alpha": 3.5565588200778455, "layernorm_mlp_beta": 1.0, "max_position_embeddings": 8192, "model_type": "minimax_text_01", "num_attention_heads": 64, "num_experts_per_tok": 2, "num_hidden_layers": 80, "num_key_value_heads": 8, "num_local_experts": 32, "postnorm": true, "rms_norm_eps": 1e-05, "rope_theta": 10000000, "rotary_dim": 64, "shared_intermediate_size": [ 0 ], "shared_moe_mode": "sigmoid", "vocab_size": 200064 }, "transformers_version": "4.42.3", "vision_config": { "auto_map": { "AutoModel": "modeling_clip.CLIPVisionModel" }, "hidden_act": "gelu", "hidden_size": 1024, "image_size": 336, "intermediate_size": 4096, "model_type": "clip_vision_model", "num_attention_heads": 16, "num_hidden_layers": 24, "patch_size": 14, "projection_dim": 6144, "vocab_size": 32000 }, "torch_dtype": "bfloat16", "vision_feature_layer": -1, "vision_feature_select_strategy": "default" }