Upload 47 files

action_model/added_tokens.json

@@ -0,0 +1,15 @@
+{
+  "<act>": 151649,
+  "<generated_image>": 151652,
+  "<his>": 151650,
+  "<image>": 151654,
+  "<nav>": 151648,
+  "<obs>": 151651,
+  "<vila/sentinel>": 151653,
+  "<vila/video>": 151655,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "[BOS]": 151646,
+  "[PAD]": 151647
+}

action_model/chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{% for message in messages if message['content'] is not none %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}

action_model/config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "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"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_max_length": 4096,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 4096,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "4.56.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151656
+}

action_model/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.56.1"
+}

action_model/inference.config.json

@@ -0,0 +1,13 @@
+{
+    "__config_type__": "robo_orchard_lab.inference.basic:InferencePipelineCfg",
+    "class_type": "robo_orchard_lab.inference.basic:InferencePipeline",
+    "model_cfg": null,
+    "processor": {
+        "__config_type__": "robo_orchard_lab.models.mapdream.action_processor:ActionModelProcessorCfg",
+        "class_type": "robo_orchard_lab.models.mapdream.action_processor:ActionModelProcessor",
+        "load_image": true,
+        "transforms": null
+    },
+    "collate_fn": null,
+    "batch_size": 1
+}

action_model/model.config.json

@@ -0,0 +1,447 @@
+{
+    "__config_type__": "robo_orchard_lab.models.mapdream.action_model:ActionModelConfig",
+    "class_type": "robo_orchard_lab.models.mapdream.action_model:ActionModel",
+    "model_dtype": "torch.float16",
+    "llava_llama_config": {
+        "Ubit": 100,
+        "architectures": [
+            "LlavaLlamaModel"
+        ],
+        "babit": "E5M2",
+        "bobit": "E5M2",
+        "bos_token_id": 151646,
+        "bwbit": "E5M2",
+        "chat_template": null,
+        "col_blocksize": -1,
+        "col_blocksize_optimizer": 128,
+        "draw_distribution_backward": false,
+        "draw_distribution_forward": false,
+        "drop_path_rate": 0.0,
+        "dynamic_s2": false,
+        "eos_token_id": 151645,
+        "epsilon": 1e-10,
+        "epsilon_optimizer": 1e-15,
+        "fabit": "E4M3",
+        "first_order_bit": null,
+        "first_order_quant_type": null,
+        "fobit": "E4M3",
+        "fps": 0.0,
+        "fwbit": "E4M3",
+        "group_size": -1,
+        "hidden_size": 1536,
+        "image_aspect_ratio": "dynamic",
+        "image_encoder": {
+            "_target_": "llava.model.encoders.BasicImageEncoder"
+        },
+        "interpolate_mode": "linear",
+        "llm_cfg": {
+            "_name_or_path": "/horizon-bucket/robot_lab/users/guoxin.lian/icml2026/mapdream/train/mapdream_stage3/mapdream_stage2_all_l20_batch64_v1/checkpoint-40000_1e-6/tmp-checkpoint-2000/llm",
+            "add_cross_attention": false,
+            "architectures": [
+                "Qwen2ForCausalLM"
+            ],
+            "attention_dropout": 0.0,
+            "bad_words_ids": null,
+            "begin_suppress_tokens": null,
+            "bos_token_id": 151643,
+            "chunk_size_feed_forward": 0,
+            "cross_attention_hidden_size": null,
+            "decoder_start_token_id": null,
+            "diversity_penalty": 0.0,
+            "do_sample": false,
+            "dtype": "bfloat16",
+            "early_stopping": false,
+            "encoder_no_repeat_ngram_size": 0,
+            "eos_token_id": 151645,
+            "exponential_decay_length_penalty": null,
+            "finetuning_task": null,
+            "forced_bos_token_id": null,
+            "forced_eos_token_id": null,
+            "hidden_act": "silu",
+            "hidden_size": 1536,
+            "id2label": {
+                "0": "LABEL_0",
+                "1": "LABEL_1"
+            },
+            "initializer_range": 0.02,
+            "intermediate_size": 8960,
+            "is_decoder": false,
+            "is_encoder_decoder": false,
+            "label2id": {
+                "LABEL_0": 0,
+                "LABEL_1": 1
+            },
+            "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"
+            ],
+            "length_penalty": 1.0,
+            "max_length": 20,
+            "max_position_embeddings": 32768,
+            "max_window_layers": 28,
+            "min_length": 0,
+            "model_max_length": 4096,
+            "model_type": "qwen2",
+            "no_repeat_ngram_size": 0,
+            "num_attention_heads": 12,
+            "num_beam_groups": 1,
+            "num_beams": 1,
+            "num_hidden_layers": 28,
+            "num_key_value_heads": 2,
+            "num_return_sequences": 1,
+            "output_attentions": false,
+            "output_hidden_states": false,
+            "output_scores": false,
+            "pad_token_id": null,
+            "prefix": null,
+            "problem_type": null,
+            "pruned_heads": {},
+            "remove_invalid_values": false,
+            "repetition_penalty": 1.0,
+            "return_dict": true,
+            "return_dict_in_generate": false,
+            "rms_norm_eps": 1e-6,
+            "rope_scaling": null,
+            "rope_theta": 1000000.0,
+            "sep_token_id": null,
+            "sliding_window": null,
+            "suppress_tokens": null,
+            "task_specific_params": null,
+            "temperature": 1.0,
+            "tf_legacy_loss": false,
+            "tie_encoder_decoder": false,
+            "tie_word_embeddings": true,
+            "tokenizer_class": null,
+            "tokenizer_model_max_length": 4096,
+            "tokenizer_padding_side": "right",
+            "top_k": 50,
+            "top_p": 1.0,
+            "torchscript": false,
+            "typical_p": 1.0,
+            "use_bfloat16": false,
+            "use_cache": false,
+            "use_sliding_window": false,
+            "vocab_size": 151656
+        },
+        "max_tiles": 12,
+        "min_blockunit_col": 4,
+        "min_blockunit_row": 4,
+        "min_tiles": 1,
+        "mlp_path": null,
+        "mm_hidden_size": 1152,
+        "mm_projector": "mlp_downsample_3x3_fix",
+        "mm_projector_cfg": {
+            "_name_or_path": "/horizon-bucket/robot_lab/users/guoxin.lian/icml2026/mapdream/train/mapdream_stage3/mapdream_stage2_all_l20_batch64_v1/checkpoint-40000_1e-6/tmp-checkpoint-2000/mm_projector",
+            "add_cross_attention": false,
+            "architectures": [
+                "MultimodalProjector"
+            ],
+            "bad_words_ids": null,
+            "begin_suppress_tokens": null,
+            "bos_token_id": null,
+            "chunk_size_feed_forward": 0,
+            "cross_attention_hidden_size": null,
+            "decoder_start_token_id": null,
+            "diversity_penalty": 0.0,
+            "do_sample": false,
+            "dtype": "bfloat16",
+            "early_stopping": false,
+            "encoder_no_repeat_ngram_size": 0,
+            "eos_token_id": null,
+            "exponential_decay_length_penalty": null,
+            "finetuning_task": null,
+            "forced_bos_token_id": null,
+            "forced_eos_token_id": null,
+            "id2label": {
+                "0": "LABEL_0",
+                "1": "LABEL_1"
+            },
+            "is_decoder": false,
+            "is_encoder_decoder": false,
+            "label2id": {
+                "LABEL_0": 0,
+                "LABEL_1": 1
+            },
+            "length_penalty": 1.0,
+            "max_length": 20,
+            "min_length": 0,
+            "mm_projector_type": "mlp_downsample_3x3_fix",
+            "model_type": "v2l_projector",
+            "no_repeat_ngram_size": 0,
+            "num_beam_groups": 1,
+            "num_beams": 1,
+            "num_return_sequences": 1,
+            "output_attentions": false,
+            "output_hidden_states": false,
+            "output_scores": false,
+            "pad_token_id": null,
+            "prefix": null,
+            "problem_type": null,
+            "pruned_heads": {},
+            "remove_invalid_values": false,
+            "repetition_penalty": 1.0,
+            "return_dict": true,
+            "return_dict_in_generate": false,
+            "sep_token_id": null,
+            "suppress_tokens": null,
+            "task_specific_params": null,
+            "temperature": 1.0,
+            "tf_legacy_loss": false,
+            "tie_encoder_decoder": false,
+            "tie_word_embeddings": true,
+            "tokenizer_class": null,
+            "top_k": 50,
+            "top_p": 1.0,
+            "torchscript": false,
+            "typical_p": 1.0,
+            "use_bfloat16": false
+        },
+        "mm_projector_lr": null,
+        "mm_use_im_patch_token": false,
+        "mm_use_im_start_end": false,
+        "mm_vision_select_feature": "cls_patch",
+        "mm_vision_select_layer": -2,
+        "model_dtype": "torch.bfloat16",
+        "model_name_or_path": "/horizon-bucket/robot_lab/users/guoxin.lian/icml2026/mapdream/train/mapdream_stage2_all_l20_batch64_v1/checkpoint-40000",
+        "model_type": "llava_llama",
+        "num_time_tokens": 0,
+        "num_video_frames": 8,
+        "pad_block": false,
+        "pad_to_multiple_of": 0,
+        "pad_token_id": 151647,
+        "qchoice": "none",
+        "quantize_model": false,
+        "refine_attn_blocksize": false,
+        "refine_col_blocksize": 4,
+        "refine_ln_blocksize": false,
+        "refine_ln_blocksize_but_only_backward": false,
+        "refine_ln_blocksize_but_only_forward": false,
+        "refine_ln_pertoken": false,
+        "refine_mlp_blocksize": false,
+        "refine_residual_fp": false,
+        "refine_row_blocksize": 4,
+        "resume_path": "/horizon-bucket/robot_lab/users/guoxin.lian/icml2026/mapdream/train/mapdream_stage2_all_l20_batch64_v1/checkpoint-40000",
+        "row_blocksize": -1,
+        "row_blocksize_optimizer": 1,
+        "s2": false,
+        "s2_max_split_size": 336,
+        "s2_resize_output_to_scale_idx": 0,
+        "s2_scales": "336,672,1008",
+        "second_order_bit": null,
+        "second_order_quant_type": null,
+        "soft_ce_std": 1.0,
+        "symm": true,
+        "time_token_format": "<t{t}>",
+        "time_token_ids": [],
+        "transformers_version": "4.56.1",
+        "tune_language_model": true,
+        "tune_mm_projector": false,
+        "tune_vision_tower": false,
+        "use_quantize_optimizer": false,
+        "version": "auto",
+        "video_encoder": {
+            "_target_": "llava.model.encoders.BasicVideoEncoder"
+        },
+        "vision_resolution": -1,
+        "vision_tower": "Efficient-Large-Model/paligemma-siglip-so400m-patch14-448",
+        "vision_tower_cfg": {
+            "_name_or_path": "/horizon-bucket/robot_lab/users/guoxin.lian/icml2026/mapdream/train/mapdream_stage3/mapdream_stage2_all_l20_batch64_v1/checkpoint-40000_1e-6/tmp-checkpoint-2000/vision_tower",
+            "add_cross_attention": false,
+            "architectures": [
+                "SiglipVisionModel"
+            ],
+            "attention_dropout": 0.0,
+            "bad_words_ids": null,
+            "begin_suppress_tokens": null,
+            "bos_token_id": null,
+            "chunk_size_feed_forward": 0,
+            "cross_attention_hidden_size": null,
+            "decoder_start_token_id": null,
+            "diversity_penalty": 0.0,
+            "do_sample": false,
+            "dtype": "bfloat16",
+            "early_stopping": false,
+            "encoder_no_repeat_ngram_size": 0,
+            "eos_token_id": null,
+            "exponential_decay_length_penalty": null,
+            "finetuning_task": null,
+            "forced_bos_token_id": null,
+            "forced_eos_token_id": null,
+            "hidden_act": "gelu_pytorch_tanh",
+            "hidden_size": 1152,
+            "id2label": {
+                "0": "LABEL_0",
+                "1": "LABEL_1"
+            },
+            "image_size": 448,
+            "intermediate_size": 4304,
+            "is_decoder": false,
+            "is_encoder_decoder": false,
+            "label2id": {
+                "LABEL_0": 0,
+                "LABEL_1": 1
+            },
+            "layer_norm_eps": 1e-6,
+            "length_penalty": 1.0,
+            "max_length": 20,
+            "min_length": 0,
+            "model_type": "siglip_vision_model",
+            "no_repeat_ngram_size": 0,
+            "num_attention_heads": 16,
+            "num_beam_groups": 1,
+            "num_beams": 1,
+            "num_channels": 3,
+            "num_hidden_layers": 27,
+            "num_image_tokens": 256,
+            "num_return_sequences": 1,
+            "output_attentions": false,
+            "output_hidden_states": false,
+            "output_scores": false,
+            "pad_token_id": null,
+            "patch_size": 14,
+            "prefix": null,
+            "problem_type": null,
+            "projection_dim": 2048,
+            "projector_hidden_act": "gelu_fast",
+            "pruned_heads": {},
+            "remove_invalid_values": false,
+            "repetition_penalty": 1.0,
+            "return_dict": true,
+            "return_dict_in_generate": false,
+            "sep_token_id": null,
+            "suppress_tokens": null,
+            "task_specific_params": null,
+            "temperature": 1.0,
+            "tf_legacy_loss": false,
+            "tie_encoder_decoder": false,
+            "tie_word_embeddings": true,
+            "tokenizer_class": null,
+            "top_k": 50,
+            "top_p": 1.0,
+            "torchscript": false,
+            "typical_p": 1.0,
+            "use_bfloat16": false,
+            "vision_use_head": false
+        },
+        "vision_tower_lr": null,
+        "weight_memory_efficient": true
+    },
+    "projector_config": {
+        "architectures": [
+            "MultimodalProjector"
+        ],
+        "dtype": "bfloat16",
+        "mm_projector_type": "mlp_downsample_3x3_fix",
+        "model_type": "v2l_projector",
+        "transformers_version": "4.56.1"
+    },
+    "vision_config": {
+        "architectures": [
+            "SiglipVisionModel"
+        ],
+        "attention_dropout": 0.0,
+        "dtype": "bfloat16",
+        "hidden_act": "gelu_pytorch_tanh",
+        "hidden_size": 1152,
+        "image_size": 448,
+        "intermediate_size": 4304,
+        "layer_norm_eps": 1e-6,
+        "model_type": "siglip_vision_model",
+        "num_attention_heads": 16,
+        "num_channels": 3,
+        "num_hidden_layers": 27,
+        "num_image_tokens": 256,
+        "patch_size": 14,
+        "projection_dim": 2048,
+        "projector_hidden_act": "gelu_fast",
+        "transformers_version": "4.56.1",
+        "vision_use_head": false
+    },
+    "llm_config": {
+        "architectures": [
+            "Qwen2ForCausalLM"
+        ],
+        "attention_dropout": 0.0,
+        "bos_token_id": 151643,
+        "dtype": "bfloat16",
+        "eos_token_id": 151645,
+        "hidden_act": "silu",
+        "hidden_size": 1536,
+        "initializer_range": 0.02,
+        "intermediate_size": 8960,
+        "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"
+        ],
+        "max_position_embeddings": 32768,
+        "max_window_layers": 28,
+        "model_max_length": 4096,
+        "model_type": "qwen2",
+        "num_attention_heads": 12,
+        "num_hidden_layers": 28,
+        "num_key_value_heads": 2,
+        "rms_norm_eps": 1e-6,
+        "rope_scaling": null,
+        "rope_theta": 1000000.0,
+        "sliding_window": null,
+        "tie_word_embeddings": true,
+        "tokenizer_model_max_length": 4096,
+        "tokenizer_padding_side": "right",
+        "transformers_version": "4.56.1",
+        "use_cache": false,
+        "use_sliding_window": false,
+        "vocab_size": 151656
+    }
+}

action_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe13b45c42d29d98c10394887668bcb38e14355ede267eefede710d6caa6467
+size 4000400976

action_model/preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 448,
+    "width": 448
+  }
+}

action_model/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<generated_image>",
+    "<vila/sentinel>",
+    "<image>",
+    "<vila/video>"
+  ],
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

action_model/tokenizer_config.json

@@ -0,0 +1,129 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<nav>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<act>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<his>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<obs>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<generated_image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<vila/sentinel>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<vila/video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<generated_image>",
+    "<vila/sentinel>",
+    "<image>",
+    "<vila/video>"
+  ],
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

progress_model/.cache/huggingface/.gitignore

@@ -0,0 +1 @@
+*

progress_model/.cache/huggingface/download/.gitattributes.metadata

@@ -0,0 +1,3 @@
+960ab33191f61342a4c60ae74d8dc356a39fafcb
+a6344aac8c09253b3b630fb776ae94478aa0275b
+1765879013.3574634

progress_model/.cache/huggingface/download/README.md.metadata

@@ -0,0 +1,3 @@
+960ab33191f61342a4c60ae74d8dc356a39fafcb
+7fa45bdfc73e212a88ad977ded48a44e9d576dad
+1765879013.409681

progress_model/.cache/huggingface/download/config.json.metadata

@@ -0,0 +1,3 @@
+960ab33191f61342a4c60ae74d8dc356a39fafcb
+5112d8fb1d821bc100343b6e035f16bf0f2eec9d
+1765879013.5021608

progress_model/.cache/huggingface/download/janus_pro_teaser1.png.metadata

@@ -0,0 +1,3 @@
+960ab33191f61342a4c60ae74d8dc356a39fafcb
+c203a0a58d8bb83714b5ea6ed196f032e18794f2
+1765879013.467131

progress_model/.cache/huggingface/download/janus_pro_teaser2.png.metadata

@@ -0,0 +1,3 @@
+960ab33191f61342a4c60ae74d8dc356a39fafcb
+d23c3a7f78efe0dd5b925b913e8ead3119e99581
+1765879013.5437665

progress_model/.cache/huggingface/download/preprocessor_config.json.metadata

@@ -0,0 +1,3 @@
+960ab33191f61342a4c60ae74d8dc356a39fafcb
+e325669f58049a8df9c94cc6ece12ee328e51345
+1765879013.5825741

progress_model/.cache/huggingface/download/processor_config.json.metadata

@@ -0,0 +1,3 @@
+960ab33191f61342a4c60ae74d8dc356a39fafcb
+e4a9c19ea470f825a18c6064c9e2bf16b515e946
+1765879013.215889

progress_model/.cache/huggingface/download/pytorch_model.bin.metadata

@@ -0,0 +1,3 @@
+960ab33191f61342a4c60ae74d8dc356a39fafcb
+ea7cf164cbed272be2a9999bc4c314da6a6f23ef51871ddef3afc2c0c430cc3f
+1765880492.9973273

progress_model/.cache/huggingface/download/special_tokens_map.json.metadata

@@ -0,0 +1,3 @@
+960ab33191f61342a4c60ae74d8dc356a39fafcb
+7b9a4071b211902617eef7c5d0c8be81a0433759
+1765879013.582345

progress_model/.cache/huggingface/download/tokenizer.json.metadata

@@ -0,0 +1,3 @@
+960ab33191f61342a4c60ae74d8dc356a39fafcb
+bfec23b547afea669da464bced65f75bc9e62895
+1765879013.7275553

progress_model/.cache/huggingface/download/tokenizer_config.json.metadata

@@ -0,0 +1,3 @@
+960ab33191f61342a4c60ae74d8dc356a39fafcb
+c0925edbbc626cff16c785d54959bac10548d959
+1765879013.825062

progress_model/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

progress_model/README.md

@@ -0,0 +1,61 @@
+---
+license: mit
+license_name: deepseek
+license_link: LICENSE
+pipeline_tag: any-to-any
+library_name: transformers
+tags:
+- muiltimodal
+- text-to-image
+- unified-model
+---
+
+## 1. Introduction
+
+Janus-Pro is a novel autoregressive framework that unifies multimodal understanding and generation. 
+It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing. The decoupling not only alleviates the conflict between the visual encoder’s roles in understanding and generation, but also enhances the framework’s flexibility. 
+Janus-Pro surpasses previous unified model and matches or exceeds the performance of task-specific models. 
+The simplicity, high flexibility, and effectiveness of Janus-Pro make it a strong candidate for next-generation unified multimodal models.
+
+[**Github Repository**](https://github.com/deepseek-ai/Janus)
+
+<div align="center">
+<img alt="image" src="janus_pro_teaser1.png" style="width:90%;">
+</div>
+
+<div align="center">
+<img alt="image" src="janus_pro_teaser2.png" style="width:90%;">
+</div>
+
+
+### 2. Model Summary
+
+Janus-Pro is a unified understanding and generation MLLM, which decouples visual encoding for multimodal understanding and generation. 
+Janus-Pro is constructed based on the DeepSeek-LLM-1.5b-base/DeepSeek-LLM-7b-base.
+
+For multimodal understanding, it uses the [SigLIP-L](https://huggingface.co/timm/ViT-L-16-SigLIP-384) as the vision encoder, which supports 384 x 384 image input. For image generation, Janus-Pro uses the tokenizer from [here](https://github.com/FoundationVision/LlamaGen) with a downsample rate of 16.
+
+
+
+## 3. Quick Start
+
+Please refer to [**Github Repository**](https://github.com/deepseek-ai/Janus)
+
+
+## 4. License
+
+This code repository is licensed under [the MIT License](https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-CODE). The use of Janus-Pro models is subject to [DeepSeek Model License](https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL).
+## 5. Citation
+
+```
+@article{chen2025janus,
+  title={Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling},
+  author={Chen, Xiaokang and Wu, Zhiyu and Liu, Xingchao and Pan, Zizheng and Liu, Wen and Xie, Zhenda and Yu, Xingkai and Ruan, Chong},
+  journal={arXiv preprint arXiv:2501.17811},
+  year={2025}
+}
+```
+
+## 6. Contact
+
+If you have any questions, please raise an issue or contact us at [service@deepseek.com](mailto:service@deepseek.com).

progress_model/config.json

@@ -0,0 +1,66 @@
+{
+  "aligner_config": {
+    "cls": "MlpProjector",
+    "model_type": "aligner",
+    "params": {
+      "depth": 2,
+      "input_dim": 1024,
+      "n_embed": 2048,
+      "projector_type": "mlp_gelu"
+    }
+  },
+  "architectures": [
+    "MultiModalityCausalLM"
+  ],
+  "gen_aligner_config": {
+    "cls": "MlpProjector",
+    "model_type": "gen_aligner",
+    "params": {
+      "depth": 2,
+      "input_dim": 8,
+      "n_embed": 2048,
+      "projector_type": "mlp_gelu"
+    }
+  },
+  "gen_head_config": {
+    "cls": "vision_head",
+    "model_type": "gen_head",
+    "params": {
+      "image_token_embed": 2048,
+      "image_token_size": 16384,
+      "n_embed": 2048
+    }
+  },
+  "gen_vision_config": {
+    "cls": "VQ-16",
+    "model_type": "gen_vision",
+    "params": {
+      "image_token_size": 16384,
+      "n_embed": 8
+    }
+  },
+  "language_config": {
+    "hidden_size": 2048,
+    "intermediate_size": 5632,
+    "max_position_embeddings": 16384,
+    "model_type": "llama",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 16,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 102400
+  },
+  "model_type": "multi_modality",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.1",
+  "vision_config": {
+    "cls": "CLIPVisionTower",
+    "model_type": "vision",
+    "params": {
+      "image_size": 384,
+      "model_name": "siglip_large_patch16_384",
+      "select_feature": "same",
+      "select_layer": -1
+    }
+  }
+}

progress_model/inference.config.json

@@ -0,0 +1,13 @@
+{
+    "__config_type__": "robo_orchard_lab.inference.basic:InferencePipelineCfg",
+    "class_type": "robo_orchard_lab.inference.basic:InferencePipeline",
+    "model_cfg": null,
+    "processor": {
+        "__config_type__": "robo_orchard_lab.models.mapdream.progress_processor:ProgressModelProcessorCfg",
+        "class_type": "robo_orchard_lab.models.mapdream.progress_processor:ProgressModelProcessor",
+        "load_image": true,
+        "transforms": null
+    },
+    "collate_fn": null,
+    "batch_size": 1
+}

progress_model/iter_3699.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd2b659c5a8a0c5ff86f5ef7778d464e698d85a93d8f43e8e97d4cdac2b3260
+size 4178905914

progress_model/model.config.json

@@ -0,0 +1,4 @@
+{
+    "__config_type__": "robo_orchard_lab.models.mapdream.progress_model:ProgressModelConfig",
+    "class_type": "robo_orchard_lab.models.mapdream.progress_model:ProgressModel"
+}

progress_model/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "background_color": [
+    127,
+    127,
+    127
+  ],
+  "do_normalize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "VLMImageProcessor",
+  "image_size": 384,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "min_size": 14,
+  "processor_class": "VLChatProcessor",
+  "rescale_factor": 0.00392156862745098
+}

progress_model/processor_config.json

@@ -0,0 +1,9 @@
+{
+  "add_special_token": false,
+  "ignore_id": -100,
+  "image_tag": "<image_placeholder>",
+  "mask_prompt": true,
+  "num_image_tokens": 576,
+  "processor_class": "VLChatProcessor",
+  "sft_format": "deepseek"
+}

progress_model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7cf164cbed272be2a9999bc4c314da6a6f23ef51871ddef3afc2c0c430cc3f
+size 4178890389

progress_model/special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [
+    "<image_placeholder>",
+    "<patch_placeholder>",
+    "<|ref|>",
+    "<|/ref|>",
+    "<|det|>",
+    "<|/det|>",
+    "<|grounding|>",
+    "<|User|>",
+    "<|Assistant|>"
+  ],
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "pad_token": "<｜▁pad▁｜>"
+}

progress_model/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "model_max_length": 16384,
+  "pad_token": null,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": true
+}