diff --git a/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/config.json b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/config.json new file mode 100644 index 0000000000000000000000000000000000000000..b3f5df6278a4a13ed38965d1fda3418493b3e8e8 --- /dev/null +++ b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/config.json @@ -0,0 +1,93 @@ +{ + "action_horizon": 30, + "add_pos_embed": true, + "apply_sincos_state_encoding": false, + "architectures": [ + "Gr00tN1d7" + ], + "attn_dropout": 0.2, + "attn_implementation": null, + "backbone_embedding_dim": 2048, + "backbone_model_path": "/mnt/data/nieshen/models/Cosmos-Reason2-2B", + "backbone_trainable_params_fp32": true, + "color_jitter_params": { + "brightness": 0.3, + "contrast": 0.4, + "hue": 0.08, + "saturation": 0.5 + }, + "crop_fraction": 0.95, + "diffusion_model_cfg": { + "attention_head_dim": 48, + "dropout": 0.2, + "final_dropout": true, + "interleave_self_attention": true, + "norm_type": "ada_norm", + "num_attention_heads": 32, + "num_layers": 32, + "output_dim": 1024, + "positional_embeddings": null + }, + "dtype": "bfloat16", + "exclude_state": false, + "formalize_language": true, + "hidden_size": 1024, + "image_crop_size": [ + 230, + 230 + ], + "image_target_size": [ + 256, + 256 + ], + "letter_box_transform": false, + "load_bf16": false, + "max_action_dim": 40, + "max_num_embodiments": 32, + "max_seq_len": 1024, + "max_state_dim": 29, + "model_dtype": "bfloat16", + "model_name": "nvidia/Cosmos-Reason2-2B", + "model_type": "Gr00tN1d7", + "noise_beta_alpha": 1.5, + "noise_beta_beta": 1.0, + "noise_s": 0.999, + "num_inference_timesteps": 4, + "num_timestep_buckets": 1000, + "random_history_crop": true, + "random_rotation_angle": 0, + "reinitialize_action_io": true, + "reproject_vision": false, + "rtc_enabled": true, + "rtc_max_delay_steps": 6, + "rtc_ramp_rate": 6.0, + "select_layer": 16, + "shortest_image_edge": 256, + "state_dropout_prob": 0.2, + "state_gaussian_noise_std": 0.0, + "transformers_version": "4.57.3", + "tune_diffusion_model": true, + "tune_linear": true, + "tune_llm": false, + "tune_projector": true, + "tune_top_llm_layers": 0, + "tune_visual": false, + "tune_vlln": true, + "use_albumentations": true, + "use_alternate_vl_dit": true, + "use_flash_attention": true, + "use_future_tokens": false, + "use_mean_std": false, + "use_percentiles": true, + "use_relative_action": false, + "use_vl_self_attention": true, + "use_vlln": true, + "vl_self_attention_cfg": { + "attention_head_dim": 64, + "dropout": 0.2, + "final_dropout": true, + "num_attention_heads": 32, + "num_layers": 4, + "positional_embeddings": null + } +} diff --git a/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/embodiment_id.json b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/embodiment_id.json new file mode 100644 index 0000000000000000000000000000000000000000..51aecc1d296972eced4ae634d0e95ad4e9d5d30a --- /dev/null +++ b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/embodiment_id.json @@ -0,0 +1,58 @@ +{ + "robocasa_panda_omron": 13, + "oxe_droid": 17, + "oxe_fractal": 18, + "oxe_language_table": 19, + "oxe_bridge": 20, + "unknown": 22, + "gr1_unified": 20, + "agibot": 26, + "sim_behavior_r1_pro": 23, + "xdof": 24, + "xdof_oss_data": 25, + "unitree_g1_full_body_with_waist_height_nav_cmd": 25, + "real_r1_pro_sharpa": 27, + "real_r1_pro_sharpa_add_view": 27, + "real_r1_pro_sharpa_relative_arm_joint": 26, + "real_r1_pro_sharpa_delta_eef": 26, + "real_r1_pro_sharpa_absolute_eef": 26, + "real_r1_pro_sharpa_meanstd": 26, + "real_r1_pro_sharpa_relative_eef": 26, + "real_r1_pro_sharpa_relative_eef_add_view": 26, + "real_r1_pro_sharpa_relative_eef_relative_hand": 26, + "real_r1_pro_sharpa_relative_eef_human": 26, + "real_r1_pro_sharpa_relative_eef_human_add_view": 26, + "real_r1_pro_sharpa_relative_eef_human_relative_hand": 26, + "real_r1_pro_sharpa_relative_eef_egodex": 26, + "real_r1_pro_sharpa_relative_eef_egodex_relative_hand": 26, + "real_r1_pro_sharpa_relative_eef_egodex_wrist_only": 26, + "real_r1_pro_sharpa_relative_eef_maxinsights": 26, + "real_r1_pro_sharpa_relative_eef_maxinsights_relative_hand": 26, + "real_r1_pro_sharpa_relative_eef_mecka": 26, + "real_r1_pro_sharpa_relative_eef_mecka_relative_hand": 26, + "real_g1_relative_eef_absolute_joints": 25, + "real_g1_relative_eef_absolute_joints_wrist_cam": 25, + "real_g1_relative_eef_relative_joints": 25, + "real_r1_pro_sharpa_relative_eef_relative_hand_relative_joint": 26, + "real_r1_pro_sharpa_relative_joint": 29, + "oxe_droid_relative_eef_relative_joint": 24, + "oxe_droid_relative_eef_relative_joint_swapped": 24, + "oxe_droid_relative_eef_relative_joint_upweight_z": 24, + "oxe_droid_relative_eef_relative_joint_upweight_z_swapped": 24, + "oxe_droid_relative_eef_relative_joint_3view": 24, + "oxe_droid_relative_eef_relative_joint_3view_swapped": 24, + "oxe_droid_relative_eef": 24, + "oxe_droid_joint_position_relative": 24, + "xdof_relative_eef_relative_joint": 27, + "xdof_relative_eef_relative_joint_subtask": 27, + "xdof_relative_eef": 27, + "xdof_relative_joint": 28, + "simpler_env_google": 0, + "simpler_env_widowx": 1, + "libero_sim": 2, + "droid_sim": 3, + "new_embodiment": 10, + "robocasa_gr1_tabletop": 10, + "unitree_g1_sonic": 11, + "g1_heft": 12 +} \ No newline at end of file diff --git a/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/model-00001-of-00002.safetensors b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8da64d644adac14f63b193bd21156063b59f15e0 --- /dev/null +++ b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d336673a8e1928e7362134396ecbee0d69974b1cec3c2611e699f7b8c1200f9 +size 4990519232 diff --git a/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/model-00002-of-00002.safetensors b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2922886421f22a7d274b34e1903781f7b4db9888 --- /dev/null +++ b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1774e83b4eaad50b845d8a96905e002229b01127a4fa39b16e0232a1297efc64 +size 1898150792 diff --git a/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/model.safetensors.index.json b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..def1c74874c88e43cc67f20f5a4a34ac15d2eb5d --- /dev/null +++ b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/model.safetensors.index.json @@ -0,0 +1,1039 @@ +{ + "metadata": { + "total_parameters": 3133101312, + "total_size": 6888532480 + }, + "weight_map": { + "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.16.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.17.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.18.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.19.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.19.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.19.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.19.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.19.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.19.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.19.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.19.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.19.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.19.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.19.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.19.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.19.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.19.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.20.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.20.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.21.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.22.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.23.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.24.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.25.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.26.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.27.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.28.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.29.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.30.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.30.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.31.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.position_embedding.weight": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vlln.bias": "model-00002-of-00002.safetensors", + "action_head.vlln.weight": "model-00002-of-00002.safetensors", + "backbone.model.lm_head.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.language_model.norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.merger.norm.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.merger.norm.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors", + "backbone.model.model.visual.pos_embed.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/processor_config.json b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/processor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9433074f50bd57e2d3345600cc828a85f2c9aa3a --- /dev/null +++ b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/processor_config.json @@ -0,0 +1,112 @@ +{ + "processor_class": "Gr00tN1d7Processor", + "processor_kwargs": { + "modality_configs": { + "g1_heft": { + "video": { + "delta_indices": [ + 0 + ], + "modality_keys": [ + "ego_view", + "left_wrist", + "right_wrist" + ], + "sin_cos_embedding_keys": null, + "mean_std_embedding_keys": null, + "action_configs": null + }, + "state": { + "delta_indices": [ + 0 + ], + "modality_keys": [ + "joint_position" + ], + "sin_cos_embedding_keys": null, + "mean_std_embedding_keys": null, + "action_configs": null + }, + "action": { + "delta_indices": [ + 0, + 1, + 2, + 3, + 4, + 5, + 6, + 7, + 8, + 9, + 10, + 11, + 12, + 13, + 14, + 15, + 16, + 17, + 18, + 19, + 20, + 21, + 22, + 23, + 24, + 25, + 26, + 27, + 28, + 29 + ], + "modality_keys": [ + "root_local" + ], + "sin_cos_embedding_keys": null, + "mean_std_embedding_keys": null, + "action_configs": [ + { + "rep": "ABSOLUTE", + "type": "NON_EEF", + "format": "DEFAULT", + "state_key": null + } + ] + }, + "language": { + "delta_indices": [ + 0 + ], + "modality_keys": [ + "task" + ], + "sin_cos_embedding_keys": null, + "mean_std_embedding_keys": null, + "action_configs": null + } + } + }, + "image_crop_size": null, + "image_target_size": null, + "use_albumentations": true, + "random_rotation_angle": null, + "color_jitter_params": null, + "shortest_image_edge": 320, + "crop_fraction": 1.0, + "letter_box_transform": false, + "model_name": "/mnt/data/nieshen/models/Cosmos-Reason2-2B", + "model_type": "qwen", + "formalize_language": true, + "max_state_dim": 29, + "max_action_dim": 40, + "max_action_horizon": 30, + "use_percentiles": true, + "use_mean_std": false, + "clip_outliers": true, + "apply_sincos_state_encoding": false, + "use_relative_action": true, + "exclude_state": false, + "state_dropout_prob": 0.2 + } +} \ No newline at end of file diff --git a/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/statistics.json b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/statistics.json new file mode 100644 index 0000000000000000000000000000000000000000..56de56fea371f6a4b6a4cd9cca775bc96955326e --- /dev/null +++ b/groot_posttrain_ns78000_0824_new_nollmvisual_20260825_165941/checkpoint-30000/statistics.json @@ -0,0 +1,450 @@ +{ + "g1_heft": { + "state": { + "joint_position": { + "min": [ + -0.3967556059360504, + -0.39027026295661926, + -0.2537764310836792, + -0.22532473504543304, + -0.5114803314208984, + -0.17879684269428253, + -0.5037093758583069, + -1.040336012840271, + -0.06969813257455826, + -0.0010311759542673826, + 0.009178318083286285, + -0.4378916025161743, + -2.8147590160369873, + -0.36294087767601013, + -0.48336002230644226, + -0.05442036688327789, + -2.157723903656006, + -0.21120533347129822, + -0.19152714312076569, + -0.6097813248634338, + -0.8616777658462524, + -0.143511101603508, + -0.4498758316040039, + -1.2266693115234375, + -1.4626147747039795, + -0.21551232039928436, + -0.5952085256576538, + -0.6632789373397827, + -1.370072603225708 + ], + "max": [ + 0.32808440923690796, + 0.3294309079647064, + 0.39962756633758545, + 0.4155639111995697, + 0.19281286001205444, + 0.4612109959125519, + 0.6512478590011597, + 0.2290148138999939, + 0.42060738801956177, + 1.2753771543502808, + 1.1494543552398682, + 0.2449815273284912, + 0.3877735733985901, + 0.39100608229637146, + 0.42000433802604675, + 0.6817585825920105, + -0.07849667221307755, + 0.22131916880607605, + 0.21125800907611847, + 0.37587323784828186, + 2.5153090953826904, + 1.4813580513000488, + 1.634864091873169, + 0.7024433612823486, + 1.2137622833251953, + 0.6177868247032166, + 0.7384679317474365, + 0.8406094908714294, + 0.958306610584259 + ], + "mean": [ + 0.009594946149312078, + -0.012116376438927656, + 0.057138769123520346, + 0.03229605402954488, + -0.07622727432900342, + -0.02217569835426249, + 0.06405375538803833, + -0.1546009351609176, + 0.13479303224596614, + 0.12900787606476463, + 0.15996872005469823, + -0.04715825245999469, + -0.48067387765867475, + -0.07521794146599155, + -0.08188225048230424, + 0.2886074236222252, + -0.5011296664754865, + -0.02491418252015477, + 0.04148368631970046, + -0.15574503497870124, + 0.32567772917526966, + 1.2053897049156905, + 0.4959788415676994, + -0.06991282327753505, + 0.19484839659777176, + 0.13007504179544013, + 0.02261612033732995, + 0.1313856489661974, + 0.0031905261641737995 + ], + "std": [ + 0.10080513446226318, + 0.0934240638847502, + 0.08803344969025405, + 0.05870605640609433, + 0.0683006436899359, + 0.03960904790819792, + 0.10694949640087545, + 0.10967961565165027, + 0.05776945315256184, + 0.11187030619943715, + 0.12358805783878124, + 0.06027719079180399, + 0.40133862404991943, + 0.06776859460461296, + 0.07707008796587166, + 0.06366036065111734, + 0.20051451734042958, + 0.046084857256499044, + 0.05272372059503313, + 0.0975600812166384, + 0.28496930113856284, + 0.12086477923584746, + 0.5587259576618397, + 0.16868537270733358, + 0.37577923686569425, + 0.14173867588860262, + 0.1570125106236177, + 0.22153744515025206, + 0.2787217191226084 + ], + "q01": [ + -0.2548044383525848, + -0.26462021470069885, + -0.12724443078041076, + -0.0958601638674736, + -0.2831132054328918, + -0.12978269159793854, + -0.19360662996768951, + -0.57743980884552, + 0.02514094188809395, + 0.05573122575879097, + 0.06772524863481522, + -0.21014338731765747, + -1.5500204801559447, + -0.22067586779594422, + -0.25583191514015197, + 0.1734213262796402, + -1.087887215614319, + -0.11668550074100495, + -0.10671820491552353, + -0.4138272762298584, + -0.5186580777168274, + 0.8584492325782777, + -0.2733314216136932, + -0.4649687647819519, + -0.6844718217849731, + -0.14097043871879578, + -0.31990931630134584, + -0.22033717334270475, + -0.909303081035614 + ], + "q99": [ + 0.19351167976856232, + 0.20062082111835478, + 0.2887694537639618, + 0.2135454624891279, + 0.06216542273759834, + 0.07264577597379683, + 0.39122548699378934, + 0.053838100284337956, + 0.33302269577980037, + 0.6794750928878782, + 0.7596306800842278, + 0.09025319665670395, + 0.0890212193131443, + 0.12188822627067551, + 0.12868857681751242, + 0.4733169674873352, + -0.19857381582260156, + 0.11358110904693576, + 0.13834015130996705, + 0.08084558695554733, + 0.9407880425453186, + 1.3726563930511473, + 1.3655545234680173, + 0.28083594441413867, + 0.9974974274635298, + 0.4210777282714844, + 0.4214324593543998, + 0.7369340062141418, + 0.6251499295234676 + ] + } + }, + "action": { + "root_local": { + "min": [ + -0.43101248145103455, + -0.24202874302864075, + -0.31924086809158325, + -0.08726700395345688, + -0.3745346963405609, + -0.26179999113082886, + -0.45998284220695496, + -0.5664225816726685, + -0.7763651013374329, + -0.08726737648248672, + -0.34316450357437134, + -0.08738861978054047, + -0.2791321873664856, + -0.2586599588394165, + -0.1832597255706787, + -0.4437520503997803, + -0.4895506501197815, + -0.6624303460121155, + -0.25071612000465393, + -1.4249913692474365, + -0.2939627766609192, + -0.7711055874824524, + -3.089200019836426, + -2.251500129699707, + -0.9062362313270569, + -0.47939687967300415, + -1.5984599590301514, + -0.692857563495636, + -1.4311563968658447, + -0.48704424500465393, + -0.4427714943885803, + -0.04230743646621704, + -0.19477154314517975, + -0.9998215436935425, + -0.23059462010860443, + -0.7636915445327759, + -0.19353483617305756, + -0.22201953828334808, + 0.0, + 0.0 + ], + "max": [ + 0.3716237545013428, + 0.4680149555206299, + 0.6677578091621399, + 1.1967136859893799, + 0.36097007989883423, + 0.13692378997802734, + 0.36524322628974915, + 0.14338967204093933, + 0.23810553550720215, + 1.041733741760254, + 0.3616960942745209, + 0.2617999315261841, + 0.4703235924243927, + 0.5199999809265137, + 0.5199999809265137, + 0.28550344705581665, + 0.7132689952850342, + 0.4458114206790924, + 1.4491417407989502, + 0.7996933460235596, + 0.6984569430351257, + 0.8922561407089233, + 0.37872326374053955, + -0.025211533531546593, + 2.618000030517578, + 1.5551677942276, + 1.4216184616088867, + 0.7958832383155823, + 1.0879156589508057, + 0.46385449171066284, + 0.3810043931007385, + 0.052625954151153564, + 1.0, + 0.7610474228858948, + 0.19089250266551971, + 0.9999997019767761, + 1.0, + 0.21314860880374908, + 0.0, + 1.0 + ], + "mean": [ + 0.033418054112852355, + 0.06093141585368822, + 0.07604293499664416, + 0.04823992985210164, + -0.029572420185776008, + -0.049318248104679614, + 0.03611997432717123, + -0.13536218194426455, + -0.14671583161096693, + 0.07207994676743039, + -0.0050877052106775775, + 0.10907373722604839, + 0.05986379810412769, + -0.04216510584322933, + 0.12311100036760585, + -0.008603244909718703, + 0.3323985378730199, + -0.16377466312179803, + 1.1700422041266574, + -0.06205802701068457, + 0.1367432637914551, + 0.1393716988241412, + -0.5128994936130736, + -0.5190786808315715, + 0.30404734793558746, + 0.46762409816355294, + 0.2069603403862259, + 0.01142668508213328, + 0.018450203764979748, + 0.0146242941810799, + -0.0050468862445729465, + 2.4551900083116766e-05, + 0.9886026131804971, + -0.02530680704975805, + 0.0010313411322433613, + 0.02519064255522762, + 0.9882763009437876, + -0.0007321909620623349, + 0.0, + 0.553455541559122 + ], + "std": [ + 0.12121049141137677, + 0.06562073856698679, + 0.11394895256280393, + 0.16145097849267664, + 0.08014186694055811, + 0.052536300606900864, + 0.10493302892678395, + 0.07749559489808323, + 0.11884001821299497, + 0.1458377611909016, + 0.08105453031987048, + 0.05418728959286906, + 0.11216751965915694, + 0.048478530640962386, + 0.08117084001496357, + 0.065353581473645, + 0.06557216650389341, + 0.10276863593679987, + 0.13054574761989993, + 0.17454818278671222, + 0.16292884675170322, + 0.23094271555190346, + 0.42650224110817997, + 0.21645975619898106, + 0.2915346843553718, + 0.5734675832977589, + 0.3918108955959333, + 0.177371402859481, + 0.29577235687292247, + 0.0705046688282154, + 0.05559094524139535, + 0.005646773923291314, + 0.05069514346113761, + 0.13691858062161166, + 0.026583449177049932, + 0.1370945568617717, + 0.050829567869312337, + 0.03600397167166051, + 0.0, + 0.49663334105090784 + ], + "q01": [ + -0.2668549120426178, + -0.08257932960987091, + -0.18781167268753052, + -0.08726699650287628, + -0.2168368399143219, + -0.1645175814628601, + -0.2493157982826233, + -0.34941190481185913, + -0.5326669216156006, + -0.08726699650287628, + -0.20860007405281067, + -0.0251467265188694, + -0.15802119672298431, + -0.18679259717464447, + -0.02215815894305706, + -0.1964767873287201, + 0.2205345183610916, + -0.41870754957199097, + 0.8184259533882141, + -0.47792068123817444, + -0.1904497742652893, + -0.23051393032073975, + -1.612612247467041, + -1.1628139019012451, + -0.5469273328781128, + -0.3279397785663605, + -0.7031332850456238, + -0.35553136467933655, + -0.9186270236968994, + -0.18939056172966956, + -0.17961656272411347, + -0.015675301551818847, + 0.725578961968422, + -0.6848118299245834, + -0.07573490627110004, + -0.21586443543434142, + 0.7241324102878571, + -0.10451267905533312, + 0.0, + 0.0 + ], + "q99": [ + 0.2602812349796295, + 0.25048398703335445, + 0.4175134301185608, + 0.6998357772827148, + 0.19159191846847534, + 0.08805429503320861, + 0.2644321620464325, + 0.023861616849899292, + 0.0921102911233902, + 0.679039716720581, + 0.2287910282611847, + 0.21824665367603302, + 0.37526631355285645, + 0.07916446030139923, + 0.402423620223999, + 0.13834910094738007, + 0.5487155318260193, + 0.07719717174768448, + 1.3513909578323364, + 0.2988387942314148, + 0.462659547924995, + 0.7767245769500732, + 0.10471570491790771, + -0.15158554911613464, + 0.9215548634529114, + 1.3577766418457031, + 1.0861786603927612, + 0.4642687439918518, + 0.706809401512146, + 0.25981940448284113, + 0.15967351391911494, + 0.01773762583732602, + 0.999999463558197, + 0.2160452067852018, + 0.08312424182891844, + 0.6863480919599528, + 0.9999997019767761, + 0.10185461908578865, + 0.0, + 1.0 + ] + } + } + } +} \ No newline at end of file