Upload 10 files

added_tokens.json

@@ -0,0 +1,10 @@
+{
+  "<image>": 151649,
+  "<vila/sentinel>": 151648,
+  "<vila/video>": 151650,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "[BOS]": 151646,
+  "[PAD]": 151647
+}

config.json

@@ -0,0 +1,322 @@
+{
+  "Ubit": 100,
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "/horizon-bucket/robot_lab/users/shuo03.wang/nips2025/sft_2B_model/step3_aux_qwen/tmp-checkpoint-25000",
+  "architectures": [
+    "LlavaLlamaModel"
+  ],
+  "babit": "E5M2",
+  "bobit": "E5M2",
+  "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,
+  "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_": "robo_orchard_lab.models.monodream.multimodal_encoder.BasicImageEncoder"
+  },
+  "interpolate_mode": "linear",
+  "llm_cfg": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "/horizon-bucket/robot_lab/users/shuo03.wang/nips2025/sft_2B_model/step3_aux_qwen/tmp-checkpoint-25000/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,
+    "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
+    },
+    "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-06,
+    "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,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151651
+  },
+  "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": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "/horizon-bucket/robot_lab/users/shuo03.wang/nips2025/sft_2B_model/step3_aux_qwen/tmp-checkpoint-25000/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,
+    "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,
+    "torch_dtype": "bfloat16",
+    "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": "/bucket/input/robot_lab/users/shuo03.wang/NVILA-Lite-2B",
+  "model_type": "llava_llama",
+  "num_time_tokens": 0,
+  "num_video_frames": 8,
+  "pad_block": false,
+  "pad_to_multiple_of": 0,
+  "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": "/bucket/input/robot_lab/users/shuo03.wang/NVILA-Lite-2B",
+  "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": "4.46.0",
+  "tune_language_model": true,
+  "tune_mm_projector": true,
+  "tune_vision_tower": true,
+  "use_quantize_optimizer": false,
+  "version": "auto",
+  "video_encoder": {
+    "_target_": "robo_orchard_lab.models.monodream.multimodal_encoder.BasicVideoEncoder"
+  },
+  "vision_resolution": -1,
+  "vision_tower": "Efficient-Large-Model/paligemma-siglip-so400m-patch14-448",
+  "vision_tower_cfg": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "/horizon-bucket/robot_lab/users/shuo03.wang/nips2025/sft_2B_model/step3_aux_qwen/tmp-checkpoint-25000/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,
+    "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-06,
+    "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,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vision_use_head": false
+  },
+  "vision_tower_lr": null,
+  "weight_memory_efficient": true
+}

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": "4.46.0"
+}

inference.config.json

@@ -0,0 +1,13 @@
+{
+    "__config_type__": "robo_orchard_lab.inference.basic:InferencePipelineCfg",
+    "class_type": "robo_orchard_lab.inference.basic:InferencePipeline",
+    "model": null,
+    "processor": {
+        "__config_type__": "robo_orchard_lab.models.monodream.processor:MonoDreamProcessorCfg",
+        "class_type": "robo_orchard_lab.models.monodream.processor:MonoDreamProcessor",
+        "load_image": true,
+        "transforms": null
+    },
+    "collate_fn": null,
+    "batch_size": 1
+}

model.config.json

@@ -29,7 +29,7 @@
         "hidden_size": 1536,
         "image_aspect_ratio": "dynamic",
         "image_encoder": {
-            "_target_": "llava.model.encoders.BasicImageEncoder"
+            "_target_": "robo_orchard_lab.models.monodream.multimodal_encoder.BasicImageEncoder"
         },
         "interpolate_mode": "linear",
         "llm_cfg": {
@@ -231,7 +231,7 @@
         "use_quantize_optimizer": false,
         "version": "auto",
         "video_encoder": {
-            "_target_": "llava.model.encoders.BasicVideoEncoder"
+            "_target_": "robo_orchard_lab.models.monodream.multimodal_encoder.BasicVideoEncoder"
         },
         "vision_resolution": -1,
         "vision_tower": "Efficient-Large-Model/paligemma-siglip-so400m-patch14-448",
@@ -378,7 +378,5 @@
         "use_cache": false,
         "use_sliding_window": false,
         "vocab_size": 151651
-    },
-    "tokenizer_path": "/mnt/data3/shuo03.wang/model/aux_think_2B/llm",
-    "image_processor_path": "/mnt/data3/shuo03.wang/model/aux_think_2B/vision_tower/preprocessor_config.json"
+    }
 }

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
+  }
+}

special_tokens_map.json

@@ -0,0 +1,48 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    {
+      "content": "<vila/sentinel>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<vila/video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,88 @@
+{
+  "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": "<vila/sentinel>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<vila/video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<vila/sentinel>",
+    "<image>",
+    "<vila/video>"
+  ],
+  "bos_token": "[BOS]",
+  "chat_template": "{% 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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}