Upload 18 files

ego_vla_checkpoint/ckpt-6720/config.json

@@ -0,0 +1,581 @@
+{
+  "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4",
+  "action_output_dim": 48,
+  "action_output_ee_2d_dim": 0,
+  "action_output_ee_dim": 6,
+  "action_output_ee_rot_dim": 12,
+  "action_output_hand_dim": 30,
+  "action_token_idx": 31733,
+  "architectures": [
+    "LlavaLlamaModel"
+  ],
+  "chat_template": null,
+  "cvae_hidden_size": 256,
+  "cvae_latent_dim": 256,
+  "drop_path_rate": 0.0,
+  "ee_2d_loss_coeff": 0.0,
+  "ee_loss_coeff": 20.0,
+  "ee_movement_loss_weight": 1,
+  "ee_rot_loss_coeff": 5.0,
+  "ee_rot_representation": "rot6d",
+  "fps": 0.0,
+  "hand_kp_loss_coeff": 0.0,
+  "hand_loss_coeff": 5.0,
+  "hand_loss_dim": 6,
+  "hidden_size": 1536,
+  "image_aspect_ratio": "resize",
+  "input_placeholder_end_token_idx": 151195,
+  "input_placeholder_start_token_idx": 151375,
+  "input_placeholder_token_idx": 151375,
+  "interpolate_mode": "linear",
+  "invalid_token_idx": 151376,
+  "invalid_token_weight": 0.1,
+  "kl_weight": 0.001,
+  "llm_cfg": {
+    "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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_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": true,
+    "use_sliding_window": false,
+    "vocab_size": 151648
+  },
+  "loss_use_l1": true,
+  "merge_hand": true,
+  "mm_hidden_size": 1152,
+  "mm_projector_cfg": {
+    "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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",
+    "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": true,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "cls_patch",
+  "mm_vision_select_layer": -2,
+  "model_dtype": "torch.bfloat16",
+  "model_type": "llava_llama",
+  "next_token_loss_coeff": 0.0,
+  "num_time_tokens": 0,
+  "num_video_frames": 8,
+  "proprio_size": 16,
+  "resume_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4",
+  "s2": false,
+  "s2_max_split_size": 336,
+  "s2_scales": "336,672,1008",
+  "sep_proprio": true,
+  "sep_query_token": true,
+  "soft_ce_std": 1.0,
+  "time_token_format": "<t{t}>",
+  "time_token_ids": [],
+  "torch_dtype": "bfloat16",
+  "traj_decoder_cfg": {
+    "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlavaLlamaModel"
+    ],
+    "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,
+    "llm_cfg": {
+      "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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_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": true,
+      "use_sliding_window": false,
+      "vocab_size": 151648
+    },
+    "max_length": 20,
+    "min_length": 0,
+    "mm_projector_cfg": {
+      "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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",
+      "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
+    },
+    "model_type": "llava_llama",
+    "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,
+    "vision_tower_cfg": {
+      "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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": 384,
+      "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_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,
+      "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
+    }
+  },
+  "traj_decoder_type": "transformer_split_action_v2",
+  "transformers_version": "4.44.2",
+  "tune_language_model": true,
+  "tune_mm_projector": true,
+  "tune_vision_tower": true,
+  "use_movement_mask": false,
+  "use_proprio": true,
+  "vision_resolution": -1,
+  "vision_tower_cfg": {
+    "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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": 384,
+    "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_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,
+    "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
+  }
+}

ego_vla_checkpoint/ckpt-6720/llm/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "[BOS]": 151646,
+  "[PAD]": 151647
+}

ego_vla_checkpoint/ckpt-6720/llm/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/llm",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "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_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 4096,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151648
+}

ego_vla_checkpoint/ckpt-6720/llm/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": "4.44.2"
+}

ego_vla_checkpoint/ckpt-6720/llm/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f3dcf899d2a35a1fb229af0cbbe5fd27843938a4968679a9e5b0e55367802cf
+size 3086582408

ego_vla_checkpoint/ckpt-6720/llm/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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
+  }
+}

ego_vla_checkpoint/ckpt-6720/llm/tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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' }}{% endif %}{% 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
+}

ego_vla_checkpoint/ckpt-6720/mm_projector/config.json

@@ -0,0 +1,10 @@
+{
+  "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/mm_projector",
+  "architectures": [
+    "MultimodalProjector"
+  ],
+  "mm_projector_type": "mlp_downsample",
+  "model_type": "v2l_projector",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2"
+}

ego_vla_checkpoint/ckpt-6720/mm_projector/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498ea96407600c15553fceebddaf0d4aa3728e1af89674ed85deeaab82349591
+size 18899472

ego_vla_checkpoint/ckpt-6720/traj_decoder/config.json

@@ -0,0 +1,581 @@
+{
+  "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/traj_decoder",
+  "action_output_dim": 48,
+  "action_output_ee_2d_dim": 0,
+  "action_output_ee_dim": 6,
+  "action_output_ee_rot_dim": 12,
+  "action_output_hand_dim": 30,
+  "action_token_idx": 31733,
+  "architectures": [
+    "TrajDecoder"
+  ],
+  "chat_template": null,
+  "cvae_hidden_size": 256,
+  "cvae_latent_dim": 256,
+  "drop_path_rate": 0.0,
+  "ee_2d_loss_coeff": 0.0,
+  "ee_loss_coeff": 20.0,
+  "ee_movement_loss_weight": 1,
+  "ee_rot_loss_coeff": 5.0,
+  "ee_rot_representation": "rot6d",
+  "fps": 0.0,
+  "hand_kp_loss_coeff": 0.0,
+  "hand_loss_coeff": 5.0,
+  "hand_loss_dim": 6,
+  "hidden_size": 1536,
+  "image_aspect_ratio": "resize",
+  "input_placeholder_end_token_idx": 151195,
+  "input_placeholder_start_token_idx": 151375,
+  "input_placeholder_token_idx": 151375,
+  "interpolate_mode": "linear",
+  "invalid_token_idx": 151376,
+  "invalid_token_weight": 0.1,
+  "kl_weight": 0.001,
+  "llm_cfg": {
+    "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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_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": true,
+    "use_sliding_window": false,
+    "vocab_size": 151648
+  },
+  "loss_use_l1": true,
+  "merge_hand": true,
+  "mm_hidden_size": 1152,
+  "mm_projector_cfg": {
+    "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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",
+    "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": true,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "cls_patch",
+  "mm_vision_select_layer": -2,
+  "model_dtype": "torch.bfloat16",
+  "model_type": "llava_llama",
+  "next_token_loss_coeff": 0.0,
+  "num_time_tokens": 0,
+  "num_video_frames": 8,
+  "proprio_size": 16,
+  "resume_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4",
+  "s2": false,
+  "s2_max_split_size": 336,
+  "s2_scales": "336,672,1008",
+  "sep_proprio": true,
+  "sep_query_token": true,
+  "soft_ce_std": 1.0,
+  "time_token_format": "<t{t}>",
+  "time_token_ids": [],
+  "torch_dtype": "bfloat16",
+  "traj_decoder_cfg": {
+    "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/traj_decoder",
+    "add_cross_attention": false,
+    "architectures": [
+      "TrajDecoder"
+    ],
+    "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,
+    "llm_cfg": {
+      "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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_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": true,
+      "use_sliding_window": false,
+      "vocab_size": 151648
+    },
+    "max_length": 20,
+    "min_length": 0,
+    "mm_projector_cfg": {
+      "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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",
+      "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
+    },
+    "model_type": "llava_llama",
+    "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,
+    "vision_tower_cfg": {
+      "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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": 384,
+      "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_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,
+      "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
+    }
+  },
+  "traj_decoder_type": "transformer_split_action_v2",
+  "transformers_version": "4.44.2",
+  "tune_language_model": true,
+  "tune_mm_projector": true,
+  "tune_vision_tower": true,
+  "use_movement_mask": false,
+  "use_proprio": true,
+  "vision_resolution": -1,
+  "vision_tower_cfg": {
+    "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/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": 384,
+    "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_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,
+    "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
+  }
+}

ego_vla_checkpoint/ckpt-6720/traj_decoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2dee51fa74138f70a54b6bb81cb1a7f27ee64e464c69b91d5c7fb260cf7ab2
+size 217554240

ego_vla_checkpoint/ckpt-6720/vision_tower/config.json

@@ -0,0 +1,19 @@
+{
+  "_name_or_path": "pretrain_transv2update2_diffdata/otv-fixed-set-aug-room1table1-fixorder-30hz-hoi4dhot3dholotaco-transv2-100e-h5-3d20-rot5-lr2e-6-const-h5p30f1skip6-manoloss6l1-kp0-b16-4/vision_tower",
+  "architectures": [
+    "SiglipVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "image_size": 384,
+  "intermediate_size": 4304,
+  "layer_norm_eps": 1e-06,
+  "model_type": "siglip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 27,
+  "patch_size": 14,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2"
+}

ego_vla_checkpoint/ckpt-6720/vision_tower/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de8670a93e897dbfcba37c8b3e155be019eeee72eff077cdf79b1c5b016f17cc
+size 856506120

ego_vla_checkpoint/ckpt-6720/vision_tower/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": 384,
+    "width": 384
+  }
+}