upload

config.json

@@ -0,0 +1,319 @@
+{
+  "action_chunk_length": 16,
+  "action_dim": 13,
+  "enable_robot_alignment": false,
+  "gen_action_type": "prop_hidden",
+  "loss_func": "l1",
+  "model_type": "beingvla",
+  "motion_config": [
+    {
+      "activate": "relu",
+      "cache_path": null,
+      "chunk_size": 10,
+      "code_dim": 512,
+      "commit_weight": 0.02,
+      "depth": 3,
+      "depth_first": true,
+      "dilation_growth_rate": 1,
+      "down_t": 2,
+      "eval_window_size": 15,
+      "fps": 20,
+      "frame_interval": 2,
+      "instruction": null,
+      "is_hm3d_old": false,
+      "max_eval_motion_len": 80,
+      "max_motion_len": 200,
+      "max_text_len": 20,
+      "min_motion_len": 40,
+      "motion_code_path": "/share/dataset/Being-H0/vq_code_augv2/wrist_mano162_grvq_shared_w15_f2_c4096",
+      "motion_feat": "mano162",
+      "motion_feat_dir": null,
+      "motion_resume_pth": null,
+      "motion_unit_length": 4,
+      "mu": 0.99,
+      "multi_coords": true,
+      "nb_code": 4096,
+      "nb_joints": 22,
+      "new_token_type": "insert",
+      "norm": null,
+      "normalize": true,
+      "num_conv_layers": 3,
+      "num_quant_groups": 2,
+      "num_quantizers": 8,
+      "output_emb_width": 512,
+      "quantbeta": 1.0,
+      "quantizer_name": "group_residualvq",
+      "recons_loss": "l1_smooth",
+      "relative": true,
+      "seq_len": 64,
+      "shared_codebook": true,
+      "stride_t": 2,
+      "tmr_model_path": "",
+      "unit_length": 4,
+      "use_part": "wrist",
+      "val_split_file": "val/test.txt",
+      "vel_weight": 1.0,
+      "width": 512,
+      "window_size": 15
+    },
+    {
+      "activate": "relu",
+      "cache_path": null,
+      "chunk_size": 10,
+      "code_dim": 512,
+      "commit_weight": 0.02,
+      "depth": 3,
+      "depth_first": true,
+      "dilation_growth_rate": 1,
+      "down_t": 2,
+      "eval_window_size": 15,
+      "fps": 20,
+      "frame_interval": 2,
+      "instruction": null,
+      "is_hm3d_old": false,
+      "max_eval_motion_len": 80,
+      "max_motion_len": 200,
+      "max_text_len": 20,
+      "min_motion_len": 40,
+      "motion_code_path": "/share/dataset/Being-H0/vq_code_augv2/finger_mano162_grvq_shared_w15_f2_c4096",
+      "motion_feat": "mano162",
+      "motion_feat_dir": null,
+      "motion_resume_pth": null,
+      "motion_unit_length": 4,
+      "mu": 0.99,
+      "multi_coords": true,
+      "nb_code": 4096,
+      "nb_joints": 22,
+      "new_token_type": "insert",
+      "norm": null,
+      "normalize": true,
+      "num_conv_layers": 3,
+      "num_quant_groups": 2,
+      "num_quantizers": 8,
+      "output_emb_width": 512,
+      "quantbeta": 1.0,
+      "quantizer_name": "group_residualvq",
+      "recons_loss": "l1_smooth",
+      "relative": true,
+      "seq_len": 64,
+      "shared_codebook": true,
+      "stride_t": 2,
+      "tmr_model_path": "",
+      "unit_length": 4,
+      "use_part": "finger",
+      "val_split_file": "val/test.txt",
+      "vel_weight": 1.0,
+      "width": 512,
+      "window_size": 15
+    }
+  ],
+  "motion_type": "mano",
+  "proprio_dim": 13,
+  "transformers_version": null,
+  "vlm_config": {
+    "downsample_ratio": 0.5,
+    "force_image_size": 448,
+    "llm_config": {
+      "_attn_implementation_autoset": true,
+      "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
+      "add_cross_attention": false,
+      "architectures": [
+        "Qwen2ForCausalLM"
+      ],
+      "attention_dropout": 0.0,
+      "attn_implementation": "flash_attention_2",
+      "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": 151643,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "silu",
+      "hidden_size": 896,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 4864,
+      "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": 70,
+      "min_length": 0,
+      "model_type": "qwen2",
+      "moe_config": null,
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 14,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 24,
+      "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": {
+        "factor": 2.0,
+        "rope_type": "dynamic",
+        "type": "dynamic"
+      },
+      "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": false,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": "bfloat16",
+      "torchscript": false,
+      "transformers_version": "4.43.4",
+      "typical_p": 1.0,
+      "use_bfloat16": true,
+      "use_cache": false,
+      "use_sliding_window": false,
+      "vocab_size": 159869
+    },
+    "ps_version": "v2",
+    "select_layer": -1,
+    "system_message": null,
+    "template": "internvl2_5",
+    "use_backbone_lora": 0,
+    "use_llm_lora": 0,
+    "use_thumbnail": true,
+    "vision_config": {
+      "_attn_implementation_autoset": true,
+      "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
+      "add_cross_attention": false,
+      "architectures": [
+        "InternVisionModel"
+      ],
+      "attention_dropout": 0.0,
+      "auto_map": {
+        "AutoConfig": "configuration_intern_vit.InternVisionConfig",
+        "AutoModel": "modeling_intern_vit.InternVisionModel"
+      },
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "capacity_factor": 1.2,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "drop_path_rate": 0.0,
+      "dropout": 0.0,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "eval_capacity_factor": 1.4,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "gelu",
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 448,
+      "initializer_factor": 0.1,
+      "initializer_range": 1e-10,
+      "intermediate_size": 4096,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "laux_allreduce": "all_nodes",
+      "layer_norm_eps": 1e-06,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "intern_vit_6b",
+      "moe_coeff_ratio": 0.5,
+      "moe_intermediate_size": 768,
+      "moe_output_scale": 4.0,
+      "no_repeat_ngram_size": 0,
+      "noisy_gate_policy": "RSample_before",
+      "norm_type": "layer_norm",
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_channels": 3,
+      "num_experts": 8,
+      "num_hidden_layers": 24,
+      "num_return_sequences": 1,
+      "num_routed_experts": 4,
+      "num_shared_experts": 4,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "qk_normalization": false,
+      "qkv_bias": true,
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "shared_expert_intermediate_size": 3072,
+      "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,
+      "transformers_version": "4.43.4",
+      "typical_p": 1.0,
+      "use_bfloat16": true,
+      "use_flash_attn": true,
+      "use_moe": false,
+      "use_residual": true,
+      "use_rts": false,
+      "use_weighted_residual": false
+    }
+  },
+  "vlm_type": "internvl"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d496e08898a547469d3b1283d82eac2b5a33a279c87ced2376b9c21988f0bd43
+size 2351010300