Upload trained RFM model checkpoint
Browse files- README.md +27 -0
- config.json +68 -0
- metrics.json +341 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +745 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen3-VL-4B-Instruct
|
| 4 |
+
tags:
|
| 5 |
+
- reward_model
|
| 6 |
+
- rfm
|
| 7 |
+
- preference_comparisons
|
| 8 |
+
library_name: transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# aliangdw/qwen4b_pref_prog_succ_8_frames_all
|
| 12 |
+
|
| 13 |
+
## Model Details
|
| 14 |
+
|
| 15 |
+
- **Base Model**: Qwen/Qwen3-VL-4B-Instruct
|
| 16 |
+
- **Model Type**: qwen3_vl
|
| 17 |
+
|
| 18 |
+
## Training Run
|
| 19 |
+
|
| 20 |
+
- **Wandb Run**: [ant_rfm_qwen4b_4gpu_bs64_pref_prog_succ_8_frames_all_discrete](https://wandb.ai/clvr/rfm/runs/d6f6r6g4)
|
| 21 |
+
- **Wandb ID**: `d6f6r6g4`
|
| 22 |
+
- **Project**: rfm
|
| 23 |
+
- **Notes**: all run with prog_token per frame, qwen 4b, discrete progress, 32 bins
|
| 24 |
+
|
| 25 |
+
## Citation
|
| 26 |
+
|
| 27 |
+
If you use this model, please cite:
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RFM"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 151655,
|
| 7 |
+
"model_type": "qwen3_vl",
|
| 8 |
+
"pad_token_id": 151654,
|
| 9 |
+
"text_config": {
|
| 10 |
+
"attention_bias": false,
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 151643,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
+
"eos_token_id": 151645,
|
| 15 |
+
"head_dim": 128,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 2560,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 9728,
|
| 20 |
+
"max_position_embeddings": 262144,
|
| 21 |
+
"model_type": "qwen3_vl_text",
|
| 22 |
+
"num_attention_heads": 32,
|
| 23 |
+
"num_hidden_layers": 36,
|
| 24 |
+
"num_key_value_heads": 8,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_scaling": {
|
| 27 |
+
"mrope_interleaved": true,
|
| 28 |
+
"mrope_section": [
|
| 29 |
+
24,
|
| 30 |
+
20,
|
| 31 |
+
20
|
| 32 |
+
],
|
| 33 |
+
"rope_type": "default"
|
| 34 |
+
},
|
| 35 |
+
"rope_theta": 5000000,
|
| 36 |
+
"tie_word_embeddings": true,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 151674
|
| 39 |
+
},
|
| 40 |
+
"tie_word_embeddings": true,
|
| 41 |
+
"transformers_version": "4.57.2",
|
| 42 |
+
"unsloth_fixed": true,
|
| 43 |
+
"unsloth_version": "2025.10.11",
|
| 44 |
+
"video_token_id": 151656,
|
| 45 |
+
"vision_config": {
|
| 46 |
+
"deepstack_visual_indexes": [
|
| 47 |
+
5,
|
| 48 |
+
11,
|
| 49 |
+
17
|
| 50 |
+
],
|
| 51 |
+
"depth": 24,
|
| 52 |
+
"dtype": "bfloat16",
|
| 53 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 54 |
+
"hidden_size": 1024,
|
| 55 |
+
"in_channels": 3,
|
| 56 |
+
"initializer_range": 0.02,
|
| 57 |
+
"intermediate_size": 4096,
|
| 58 |
+
"model_type": "qwen3_vl",
|
| 59 |
+
"num_heads": 16,
|
| 60 |
+
"num_position_embeddings": 2304,
|
| 61 |
+
"out_hidden_size": 2560,
|
| 62 |
+
"patch_size": 16,
|
| 63 |
+
"spatial_merge_size": 2,
|
| 64 |
+
"temporal_patch_size": 2
|
| 65 |
+
},
|
| 66 |
+
"vision_end_token_id": 151653,
|
| 67 |
+
"vision_start_token_id": 151652
|
| 68 |
+
}
|
metrics.json
ADDED
|
@@ -0,0 +1,341 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 3750,
|
| 3 |
+
"metrics": {
|
| 4 |
+
"eval_rew_align/success_auprc_racer_val": 0.9376447934151143,
|
| 5 |
+
"eval_rew_align/positive_success_acc_racer_val": 0.8571428571428571,
|
| 6 |
+
"eval_rew_align/negative_success_acc_racer_val": 0.9903069466882067,
|
| 7 |
+
"eval_rew_align/loss_racer_val": 0.35368644297122953,
|
| 8 |
+
"eval_rew_align/pearson_racer_val": 0.9948247579804939,
|
| 9 |
+
"eval_rew_align/success_auprc_oxe_bc_z_eval": 0.026519403655989423,
|
| 10 |
+
"eval_rew_align/positive_success_acc_oxe_bc_z_eval": 0.6,
|
| 11 |
+
"eval_rew_align/negative_success_acc_oxe_bc_z_eval": 0.9541484716157205,
|
| 12 |
+
"eval_rew_align/loss_oxe_bc_z_eval": 0.5597681343555451,
|
| 13 |
+
"eval_rew_align/pearson_oxe_bc_z_eval": 0.46721908929736056,
|
| 14 |
+
"eval_rew_align/success_auprc_oxe_berkeley_cable_eval": 0.1358030057191131,
|
| 15 |
+
"eval_rew_align/positive_success_acc_oxe_berkeley_cable_eval": 0.8,
|
| 16 |
+
"eval_rew_align/negative_success_acc_oxe_berkeley_cable_eval": 0.942064264849075,
|
| 17 |
+
"eval_rew_align/loss_oxe_berkeley_cable_eval": 0.5649995774030685,
|
| 18 |
+
"eval_rew_align/pearson_oxe_berkeley_cable_eval": 0.8633005921944719,
|
| 19 |
+
"eval_rew_align/success_auprc_oxe_bridge_v2_eval": 0.17762318550763395,
|
| 20 |
+
"eval_rew_align/positive_success_acc_oxe_bridge_v2_eval": 0.6,
|
| 21 |
+
"eval_rew_align/negative_success_acc_oxe_bridge_v2_eval": 0.9788546255506608,
|
| 22 |
+
"eval_rew_align/loss_oxe_bridge_v2_eval": 0.41510086953639985,
|
| 23 |
+
"eval_rew_align/pearson_oxe_bridge_v2_eval": 0.7667845251611323,
|
| 24 |
+
"eval_rew_align/success_auprc_oxe_jaco_eval": 0.15210700346788117,
|
| 25 |
+
"eval_rew_align/positive_success_acc_oxe_jaco_eval": 0.9,
|
| 26 |
+
"eval_rew_align/negative_success_acc_oxe_jaco_eval": 0.967741935483871,
|
| 27 |
+
"eval_rew_align/loss_oxe_jaco_eval": 0.4722878307104111,
|
| 28 |
+
"eval_rew_align/pearson_oxe_jaco_eval": 0.9441080863019213,
|
| 29 |
+
"eval_rew_align/success_auprc_oxe_toto_eval": 0.2292818383028527,
|
| 30 |
+
"eval_rew_align/positive_success_acc_oxe_toto_eval": 1.0,
|
| 31 |
+
"eval_rew_align/negative_success_acc_oxe_toto_eval": 0.9677103718199609,
|
| 32 |
+
"eval_rew_align/loss_oxe_toto_eval": 0.38560630977153776,
|
| 33 |
+
"eval_rew_align/pearson_oxe_toto_eval": 0.9688754656056376,
|
| 34 |
+
"eval_rew_align/success_auprc_oxe_viola_eval": 0.3176319797262127,
|
| 35 |
+
"eval_rew_align/positive_success_acc_oxe_viola_eval": 0.8,
|
| 36 |
+
"eval_rew_align/negative_success_acc_oxe_viola_eval": 0.9545988258317025,
|
| 37 |
+
"eval_rew_align/loss_oxe_viola_eval": 0.5993496894836425,
|
| 38 |
+
"eval_rew_align/pearson_oxe_viola_eval": 0.7651143714599564,
|
| 39 |
+
"eval_rew_align/success_auprc_mw_eval": 0.043298193843462215,
|
| 40 |
+
"eval_rew_align/positive_success_acc_mw_eval": 0.4,
|
| 41 |
+
"eval_rew_align/negative_success_acc_mw_eval": 0.9588235294117647,
|
| 42 |
+
"eval_rew_align/loss_mw_eval": 0.4465502738952637,
|
| 43 |
+
"eval_rew_align/pearson_mw_eval": 0.8184557354192725,
|
| 44 |
+
"eval_rew_align/success_auprc_libero_90": 0.22434648603555674,
|
| 45 |
+
"eval_rew_align/positive_success_acc_libero_90": 0.6,
|
| 46 |
+
"eval_rew_align/negative_success_acc_libero_90": 0.9835294117647059,
|
| 47 |
+
"eval_rew_align/loss_libero_90": 0.2993748769164085,
|
| 48 |
+
"eval_rew_align/pearson_libero_90": 0.9552000160772302,
|
| 49 |
+
"eval_rew_align/success_auprc_roboarena_eval": 0.29124862451432043,
|
| 50 |
+
"eval_rew_align/positive_success_acc_roboarena_eval": 0.625,
|
| 51 |
+
"eval_rew_align/negative_success_acc_roboarena_eval": 0.969047619047619,
|
| 52 |
+
"eval_rew_align/loss_roboarena_eval": 0.4861627906560898,
|
| 53 |
+
"eval_rew_align/pearson_roboarena_eval": 0.9148732808310944,
|
| 54 |
+
"eval_rew_align/partial_success_abs_delta_roboarena_eval": 0.19062090516090394,
|
| 55 |
+
"eval_p_rank/ranking_acc_rba_last_roboarena_eval": 0.6953316953316954,
|
| 56 |
+
"eval_p_rank/kendall_rewind_rba_last_roboarena_eval": 0.5757575757575758,
|
| 57 |
+
"eval_p_rank/ranking_acc_rba_avg_roboarena_eval": 0.6953316953316954,
|
| 58 |
+
"eval_p_rank/kendall_rewind_rba_avg_roboarena_eval": 0.5757575757575758,
|
| 59 |
+
"eval_p_rank/ranking_acc_rba_sum_roboarena_eval": 0.6953316953316954,
|
| 60 |
+
"eval_p_rank/kendall_rewind_rba_sum_roboarena_eval": 0.5757575757575758,
|
| 61 |
+
"eval_rew_align/success_auprc_jesbu1_roboreward_rfm_roboreward_test": 0.6770716091317883,
|
| 62 |
+
"eval_rew_align/positive_success_acc_jesbu1_roboreward_rfm_roboreward_test": 0.7666666666666667,
|
| 63 |
+
"eval_rew_align/negative_success_acc_jesbu1_roboreward_rfm_roboreward_test": 0.98300395256917,
|
| 64 |
+
"eval_rew_align/loss_jesbu1_roboreward_rfm_roboreward_test": 0.4755001962184906,
|
| 65 |
+
"eval_rew_align/pearson_jesbu1_roboreward_rfm_roboreward_test": 0.6494258442525024,
|
| 66 |
+
"eval_rew_align/partial_success_abs_delta_jesbu1_roboreward_rfm_roboreward_test": 0.3232084229588509,
|
| 67 |
+
"eval_rew_align/mae_jesbu1_roboreward_rfm_roboreward_test": 1.1,
|
| 68 |
+
"eval_p_rank/ranking_acc_rba_last_jesbu1_roboreward_rfm_roboreward_test": 0.8081395348837209,
|
| 69 |
+
"eval_p_rank/kendall_rewind_rba_last_jesbu1_roboreward_rfm_roboreward_test": 0.7552742616033756,
|
| 70 |
+
"eval_p_rank/ranking_acc_rba_avg_jesbu1_roboreward_rfm_roboreward_test": 0.8081395348837209,
|
| 71 |
+
"eval_p_rank/kendall_rewind_rba_avg_jesbu1_roboreward_rfm_roboreward_test": 0.7552742616033756,
|
| 72 |
+
"eval_p_rank/ranking_acc_rba_sum_jesbu1_roboreward_rfm_roboreward_test": 0.8081395348837209,
|
| 73 |
+
"eval_p_rank/kendall_rewind_rba_sum_jesbu1_roboreward_rfm_roboreward_test": 0.7552742616033756,
|
| 74 |
+
"eval_rew_align/success_auprc_mit_franka": 0.023537414965986395,
|
| 75 |
+
"eval_rew_align/positive_success_acc_mit_franka": 0.5,
|
| 76 |
+
"eval_rew_align/negative_success_acc_mit_franka": 0.8666666666666667,
|
| 77 |
+
"eval_rew_align/loss_mit_franka": 0.6293959319591522,
|
| 78 |
+
"eval_rew_align/pearson_mit_franka": 0.4890771669214309,
|
| 79 |
+
"eval_p_rank/kendall_last_mit_franka": 0.125,
|
| 80 |
+
"eval_p_rank/kendall_rewind_last_mit_franka": 0.0,
|
| 81 |
+
"eval_p_rank/avg_succ_subopt_diff_last_mit_franka": -0.10331523418426514,
|
| 82 |
+
"eval_p_rank/min_succ_subopt_diff_last_mit_franka": -0.10331523418426514,
|
| 83 |
+
"eval_p_rank/max_succ_subopt_diff_last_mit_franka": -0.10331523418426514,
|
| 84 |
+
"eval_p_rank/avg_subopt_fail_diff_last_mit_franka": 0.16976976891358692,
|
| 85 |
+
"eval_p_rank/min_subopt_fail_diff_last_mit_franka": -0.06174012025197351,
|
| 86 |
+
"eval_p_rank/max_subopt_fail_diff_last_mit_franka": 0.40127965807914734,
|
| 87 |
+
"eval_p_rank/avg_succ_fail_diff_last_mit_franka": -0.16505535443623864,
|
| 88 |
+
"eval_p_rank/min_succ_fail_diff_last_mit_franka": -0.16505535443623864,
|
| 89 |
+
"eval_p_rank/max_succ_fail_diff_last_mit_franka": -0.16505535443623864,
|
| 90 |
+
"eval_p_rank/ranking_acc_last_mit_franka": 0.3125,
|
| 91 |
+
"eval_p_rank/ranking_acc_all_pairs_last_mit_franka": 0.3125,
|
| 92 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_last_mit_franka": 0.5,
|
| 93 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_last_mit_franka": 0.125,
|
| 94 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_last_mit_franka": 0.0,
|
| 95 |
+
"eval_p_rank/kendall_avg_mit_franka": 0.125,
|
| 96 |
+
"eval_p_rank/kendall_rewind_avg_mit_franka": 0.0,
|
| 97 |
+
"eval_p_rank/avg_succ_subopt_diff_avg_mit_franka": -0.10331523418426514,
|
| 98 |
+
"eval_p_rank/min_succ_subopt_diff_avg_mit_franka": -0.10331523418426514,
|
| 99 |
+
"eval_p_rank/max_succ_subopt_diff_avg_mit_franka": -0.10331523418426514,
|
| 100 |
+
"eval_p_rank/avg_subopt_fail_diff_avg_mit_franka": 0.16976976891358692,
|
| 101 |
+
"eval_p_rank/min_subopt_fail_diff_avg_mit_franka": -0.06174012025197351,
|
| 102 |
+
"eval_p_rank/max_subopt_fail_diff_avg_mit_franka": 0.40127965807914734,
|
| 103 |
+
"eval_p_rank/avg_succ_fail_diff_avg_mit_franka": -0.16505535443623864,
|
| 104 |
+
"eval_p_rank/min_succ_fail_diff_avg_mit_franka": -0.16505535443623864,
|
| 105 |
+
"eval_p_rank/max_succ_fail_diff_avg_mit_franka": -0.16505535443623864,
|
| 106 |
+
"eval_p_rank/ranking_acc_avg_mit_franka": 0.3125,
|
| 107 |
+
"eval_p_rank/ranking_acc_all_pairs_avg_mit_franka": 0.3125,
|
| 108 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_avg_mit_franka": 0.5,
|
| 109 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_avg_mit_franka": 0.125,
|
| 110 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_avg_mit_franka": 0.0,
|
| 111 |
+
"eval_p_rank/kendall_sum_mit_franka": 0.125,
|
| 112 |
+
"eval_p_rank/kendall_rewind_sum_mit_franka": 0.0,
|
| 113 |
+
"eval_p_rank/avg_succ_subopt_diff_sum_mit_franka": -0.10331523418426514,
|
| 114 |
+
"eval_p_rank/min_succ_subopt_diff_sum_mit_franka": -0.10331523418426514,
|
| 115 |
+
"eval_p_rank/max_succ_subopt_diff_sum_mit_franka": -0.10331523418426514,
|
| 116 |
+
"eval_p_rank/avg_subopt_fail_diff_sum_mit_franka": 0.16976976891358692,
|
| 117 |
+
"eval_p_rank/min_subopt_fail_diff_sum_mit_franka": -0.06174012025197351,
|
| 118 |
+
"eval_p_rank/max_subopt_fail_diff_sum_mit_franka": 0.40127965807914734,
|
| 119 |
+
"eval_p_rank/avg_succ_fail_diff_sum_mit_franka": -0.16505535443623864,
|
| 120 |
+
"eval_p_rank/min_succ_fail_diff_sum_mit_franka": -0.16505535443623864,
|
| 121 |
+
"eval_p_rank/max_succ_fail_diff_sum_mit_franka": -0.16505535443623864,
|
| 122 |
+
"eval_p_rank/ranking_acc_sum_mit_franka": 0.3125,
|
| 123 |
+
"eval_p_rank/ranking_acc_all_pairs_sum_mit_franka": 0.3125,
|
| 124 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_sum_mit_franka": 0.5,
|
| 125 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_sum_mit_franka": 0.125,
|
| 126 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_sum_mit_franka": 0.0,
|
| 127 |
+
"eval_rew_align/success_auprc_utd_so101_clean_top": 0.22822130815268687,
|
| 128 |
+
"eval_rew_align/positive_success_acc_utd_so101_clean_top": 0.9,
|
| 129 |
+
"eval_rew_align/negative_success_acc_utd_so101_clean_top": 0.9780392156862745,
|
| 130 |
+
"eval_rew_align/loss_utd_so101_clean_top": 0.36203444600105283,
|
| 131 |
+
"eval_rew_align/pearson_utd_so101_clean_top": 0.9612813372731248,
|
| 132 |
+
"eval_p_rank/kendall_last_utd_so101_clean_top": 0.9333333333333332,
|
| 133 |
+
"eval_p_rank/kendall_rewind_last_utd_so101_clean_top": 0.9333333333333332,
|
| 134 |
+
"eval_p_rank/avg_succ_subopt_diff_last_utd_so101_clean_top": 0.17610676288604737,
|
| 135 |
+
"eval_p_rank/min_succ_subopt_diff_last_utd_so101_clean_top": -0.01307380199432373,
|
| 136 |
+
"eval_p_rank/max_succ_subopt_diff_last_utd_so101_clean_top": 0.3211899995803833,
|
| 137 |
+
"eval_p_rank/avg_subopt_fail_diff_last_utd_so101_clean_top": 0.2608294665813446,
|
| 138 |
+
"eval_p_rank/min_subopt_fail_diff_last_utd_so101_clean_top": 0.02811431884765625,
|
| 139 |
+
"eval_p_rank/max_subopt_fail_diff_last_utd_so101_clean_top": 0.6011301577091217,
|
| 140 |
+
"eval_p_rank/avg_succ_fail_diff_last_utd_so101_clean_top": 0.43693622946739197,
|
| 141 |
+
"eval_p_rank/min_succ_fail_diff_last_utd_so101_clean_top": 0.17964929342269897,
|
| 142 |
+
"eval_p_rank/max_succ_fail_diff_last_utd_so101_clean_top": 0.588056355714798,
|
| 143 |
+
"eval_p_rank/ranking_acc_last_utd_so101_clean_top": 0.9666666666666667,
|
| 144 |
+
"eval_p_rank/ranking_acc_all_pairs_last_utd_so101_clean_top": 0.9666666666666667,
|
| 145 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_last_utd_so101_clean_top": 1.0,
|
| 146 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_last_utd_so101_clean_top": 1.0,
|
| 147 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_last_utd_so101_clean_top": 0.9,
|
| 148 |
+
"eval_p_rank/kendall_avg_utd_so101_clean_top": 0.9333333333333332,
|
| 149 |
+
"eval_p_rank/kendall_rewind_avg_utd_so101_clean_top": 0.9333333333333332,
|
| 150 |
+
"eval_p_rank/avg_succ_subopt_diff_avg_utd_so101_clean_top": 0.17610676288604737,
|
| 151 |
+
"eval_p_rank/min_succ_subopt_diff_avg_utd_so101_clean_top": -0.01307380199432373,
|
| 152 |
+
"eval_p_rank/max_succ_subopt_diff_avg_utd_so101_clean_top": 0.3211899995803833,
|
| 153 |
+
"eval_p_rank/avg_subopt_fail_diff_avg_utd_so101_clean_top": 0.2608294665813446,
|
| 154 |
+
"eval_p_rank/min_subopt_fail_diff_avg_utd_so101_clean_top": 0.02811431884765625,
|
| 155 |
+
"eval_p_rank/max_subopt_fail_diff_avg_utd_so101_clean_top": 0.6011301577091217,
|
| 156 |
+
"eval_p_rank/avg_succ_fail_diff_avg_utd_so101_clean_top": 0.43693622946739197,
|
| 157 |
+
"eval_p_rank/min_succ_fail_diff_avg_utd_so101_clean_top": 0.17964929342269897,
|
| 158 |
+
"eval_p_rank/max_succ_fail_diff_avg_utd_so101_clean_top": 0.588056355714798,
|
| 159 |
+
"eval_p_rank/ranking_acc_avg_utd_so101_clean_top": 0.9666666666666667,
|
| 160 |
+
"eval_p_rank/ranking_acc_all_pairs_avg_utd_so101_clean_top": 0.9666666666666667,
|
| 161 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_avg_utd_so101_clean_top": 1.0,
|
| 162 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_avg_utd_so101_clean_top": 1.0,
|
| 163 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_avg_utd_so101_clean_top": 0.9,
|
| 164 |
+
"eval_p_rank/kendall_sum_utd_so101_clean_top": 0.9333333333333332,
|
| 165 |
+
"eval_p_rank/kendall_rewind_sum_utd_so101_clean_top": 0.9333333333333332,
|
| 166 |
+
"eval_p_rank/avg_succ_subopt_diff_sum_utd_so101_clean_top": 0.17610676288604737,
|
| 167 |
+
"eval_p_rank/min_succ_subopt_diff_sum_utd_so101_clean_top": -0.01307380199432373,
|
| 168 |
+
"eval_p_rank/max_succ_subopt_diff_sum_utd_so101_clean_top": 0.3211899995803833,
|
| 169 |
+
"eval_p_rank/avg_subopt_fail_diff_sum_utd_so101_clean_top": 0.2608294665813446,
|
| 170 |
+
"eval_p_rank/min_subopt_fail_diff_sum_utd_so101_clean_top": 0.02811431884765625,
|
| 171 |
+
"eval_p_rank/max_subopt_fail_diff_sum_utd_so101_clean_top": 0.6011301577091217,
|
| 172 |
+
"eval_p_rank/avg_succ_fail_diff_sum_utd_so101_clean_top": 0.43693622946739197,
|
| 173 |
+
"eval_p_rank/min_succ_fail_diff_sum_utd_so101_clean_top": 0.17964929342269897,
|
| 174 |
+
"eval_p_rank/max_succ_fail_diff_sum_utd_so101_clean_top": 0.588056355714798,
|
| 175 |
+
"eval_p_rank/ranking_acc_sum_utd_so101_clean_top": 0.9666666666666667,
|
| 176 |
+
"eval_p_rank/ranking_acc_all_pairs_sum_utd_so101_clean_top": 0.9666666666666667,
|
| 177 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_sum_utd_so101_clean_top": 1.0,
|
| 178 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_sum_utd_so101_clean_top": 1.0,
|
| 179 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_sum_utd_so101_clean_top": 0.9,
|
| 180 |
+
"eval_rew_align/success_auprc_usc_xarm": 0.539363079419024,
|
| 181 |
+
"eval_rew_align/positive_success_acc_usc_xarm": 1.0,
|
| 182 |
+
"eval_rew_align/negative_success_acc_usc_xarm": 0.98,
|
| 183 |
+
"eval_rew_align/loss_usc_xarm": 0.36170981377363204,
|
| 184 |
+
"eval_rew_align/pearson_usc_xarm": 0.9217780460777897,
|
| 185 |
+
"eval_p_rank/kendall_last_usc_xarm": 0.611111111111111,
|
| 186 |
+
"eval_p_rank/kendall_rewind_last_usc_xarm": 0.7777777777777777,
|
| 187 |
+
"eval_p_rank/avg_succ_subopt_diff_last_usc_xarm": 0.10237312068541844,
|
| 188 |
+
"eval_p_rank/min_succ_subopt_diff_last_usc_xarm": 0.01844966411590576,
|
| 189 |
+
"eval_p_rank/max_succ_subopt_diff_last_usc_xarm": 0.25467729568481445,
|
| 190 |
+
"eval_p_rank/avg_subopt_fail_diff_last_usc_xarm": 0.242702662323912,
|
| 191 |
+
"eval_p_rank/min_subopt_fail_diff_last_usc_xarm": -0.046282678842544556,
|
| 192 |
+
"eval_p_rank/max_subopt_fail_diff_last_usc_xarm": 0.5925045646727085,
|
| 193 |
+
"eval_p_rank/avg_succ_fail_diff_last_usc_xarm": 0.34507578300933045,
|
| 194 |
+
"eval_p_rank/min_succ_fail_diff_last_usc_xarm": -0.011230170726776123,
|
| 195 |
+
"eval_p_rank/max_succ_fail_diff_last_usc_xarm": 0.762145359069109,
|
| 196 |
+
"eval_p_rank/ranking_acc_last_usc_xarm": 0.8055555555555556,
|
| 197 |
+
"eval_p_rank/ranking_acc_all_pairs_last_usc_xarm": 0.8055555555555556,
|
| 198 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_last_usc_xarm": 0.75,
|
| 199 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_last_usc_xarm": 0.9166666666666666,
|
| 200 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_last_usc_xarm": 0.75,
|
| 201 |
+
"eval_p_rank/kendall_avg_usc_xarm": 0.611111111111111,
|
| 202 |
+
"eval_p_rank/kendall_rewind_avg_usc_xarm": 0.7777777777777777,
|
| 203 |
+
"eval_p_rank/avg_succ_subopt_diff_avg_usc_xarm": 0.10237312068541844,
|
| 204 |
+
"eval_p_rank/min_succ_subopt_diff_avg_usc_xarm": 0.01844966411590576,
|
| 205 |
+
"eval_p_rank/max_succ_subopt_diff_avg_usc_xarm": 0.25467729568481445,
|
| 206 |
+
"eval_p_rank/avg_subopt_fail_diff_avg_usc_xarm": 0.242702662323912,
|
| 207 |
+
"eval_p_rank/min_subopt_fail_diff_avg_usc_xarm": -0.046282678842544556,
|
| 208 |
+
"eval_p_rank/max_subopt_fail_diff_avg_usc_xarm": 0.5925045646727085,
|
| 209 |
+
"eval_p_rank/avg_succ_fail_diff_avg_usc_xarm": 0.34507578300933045,
|
| 210 |
+
"eval_p_rank/min_succ_fail_diff_avg_usc_xarm": -0.011230170726776123,
|
| 211 |
+
"eval_p_rank/max_succ_fail_diff_avg_usc_xarm": 0.762145359069109,
|
| 212 |
+
"eval_p_rank/ranking_acc_avg_usc_xarm": 0.8055555555555556,
|
| 213 |
+
"eval_p_rank/ranking_acc_all_pairs_avg_usc_xarm": 0.8055555555555556,
|
| 214 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_avg_usc_xarm": 0.75,
|
| 215 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_avg_usc_xarm": 0.9166666666666666,
|
| 216 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_avg_usc_xarm": 0.75,
|
| 217 |
+
"eval_p_rank/kendall_sum_usc_xarm": 0.611111111111111,
|
| 218 |
+
"eval_p_rank/kendall_rewind_sum_usc_xarm": 0.7777777777777777,
|
| 219 |
+
"eval_p_rank/avg_succ_subopt_diff_sum_usc_xarm": 0.10237312068541844,
|
| 220 |
+
"eval_p_rank/min_succ_subopt_diff_sum_usc_xarm": 0.01844966411590576,
|
| 221 |
+
"eval_p_rank/max_succ_subopt_diff_sum_usc_xarm": 0.25467729568481445,
|
| 222 |
+
"eval_p_rank/avg_subopt_fail_diff_sum_usc_xarm": 0.242702662323912,
|
| 223 |
+
"eval_p_rank/min_subopt_fail_diff_sum_usc_xarm": -0.046282678842544556,
|
| 224 |
+
"eval_p_rank/max_subopt_fail_diff_sum_usc_xarm": 0.5925045646727085,
|
| 225 |
+
"eval_p_rank/avg_succ_fail_diff_sum_usc_xarm": 0.34507578300933045,
|
| 226 |
+
"eval_p_rank/min_succ_fail_diff_sum_usc_xarm": -0.011230170726776123,
|
| 227 |
+
"eval_p_rank/max_succ_fail_diff_sum_usc_xarm": 0.762145359069109,
|
| 228 |
+
"eval_p_rank/ranking_acc_sum_usc_xarm": 0.8055555555555556,
|
| 229 |
+
"eval_p_rank/ranking_acc_all_pairs_sum_usc_xarm": 0.8055555555555556,
|
| 230 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_sum_usc_xarm": 0.75,
|
| 231 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_sum_usc_xarm": 0.9166666666666666,
|
| 232 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_sum_usc_xarm": 0.75,
|
| 233 |
+
"eval_rew_align/success_auprc_usc_franka": 0.29096379055054516,
|
| 234 |
+
"eval_rew_align/positive_success_acc_usc_franka": 0.875,
|
| 235 |
+
"eval_rew_align/negative_success_acc_usc_franka": 0.9789215686274509,
|
| 236 |
+
"eval_rew_align/loss_usc_franka": 0.40182506293058395,
|
| 237 |
+
"eval_rew_align/pearson_usc_franka": 0.9151358031143331,
|
| 238 |
+
"eval_p_rank/kendall_last_usc_franka": 0.5416666666666666,
|
| 239 |
+
"eval_p_rank/kendall_rewind_last_usc_franka": 0.5,
|
| 240 |
+
"eval_p_rank/avg_succ_subopt_diff_last_usc_franka": 0.04985911399126053,
|
| 241 |
+
"eval_p_rank/min_succ_subopt_diff_last_usc_franka": -0.08763229846954346,
|
| 242 |
+
"eval_p_rank/max_succ_subopt_diff_last_usc_franka": 0.2255823016166687,
|
| 243 |
+
"eval_p_rank/avg_subopt_fail_diff_last_usc_franka": 0.27740854187868536,
|
| 244 |
+
"eval_p_rank/min_subopt_fail_diff_last_usc_franka": -0.06445235013961792,
|
| 245 |
+
"eval_p_rank/max_subopt_fail_diff_last_usc_franka": 0.6084701782092452,
|
| 246 |
+
"eval_p_rank/avg_succ_fail_diff_last_usc_franka": 0.3272676558699459,
|
| 247 |
+
"eval_p_rank/min_succ_fail_diff_last_usc_franka": -0.019217491149902344,
|
| 248 |
+
"eval_p_rank/max_succ_fail_diff_last_usc_franka": 0.6527606612071395,
|
| 249 |
+
"eval_p_rank/ranking_acc_last_usc_franka": 0.7708333333333334,
|
| 250 |
+
"eval_p_rank/ranking_acc_all_pairs_last_usc_franka": 0.7708333333333334,
|
| 251 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_last_usc_franka": 0.5625,
|
| 252 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_last_usc_franka": 0.875,
|
| 253 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_last_usc_franka": 0.875,
|
| 254 |
+
"eval_p_rank/kendall_avg_usc_franka": 0.5416666666666666,
|
| 255 |
+
"eval_p_rank/kendall_rewind_avg_usc_franka": 0.5,
|
| 256 |
+
"eval_p_rank/avg_succ_subopt_diff_avg_usc_franka": 0.04985911399126053,
|
| 257 |
+
"eval_p_rank/min_succ_subopt_diff_avg_usc_franka": -0.08763229846954346,
|
| 258 |
+
"eval_p_rank/max_succ_subopt_diff_avg_usc_franka": 0.2255823016166687,
|
| 259 |
+
"eval_p_rank/avg_subopt_fail_diff_avg_usc_franka": 0.27740854187868536,
|
| 260 |
+
"eval_p_rank/min_subopt_fail_diff_avg_usc_franka": -0.06445235013961792,
|
| 261 |
+
"eval_p_rank/max_subopt_fail_diff_avg_usc_franka": 0.6084701782092452,
|
| 262 |
+
"eval_p_rank/avg_succ_fail_diff_avg_usc_franka": 0.3272676558699459,
|
| 263 |
+
"eval_p_rank/min_succ_fail_diff_avg_usc_franka": -0.019217491149902344,
|
| 264 |
+
"eval_p_rank/max_succ_fail_diff_avg_usc_franka": 0.6527606612071395,
|
| 265 |
+
"eval_p_rank/ranking_acc_avg_usc_franka": 0.7708333333333334,
|
| 266 |
+
"eval_p_rank/ranking_acc_all_pairs_avg_usc_franka": 0.7708333333333334,
|
| 267 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_avg_usc_franka": 0.5625,
|
| 268 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_avg_usc_franka": 0.875,
|
| 269 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_avg_usc_franka": 0.875,
|
| 270 |
+
"eval_p_rank/kendall_sum_usc_franka": 0.5416666666666666,
|
| 271 |
+
"eval_p_rank/kendall_rewind_sum_usc_franka": 0.5,
|
| 272 |
+
"eval_p_rank/avg_succ_subopt_diff_sum_usc_franka": 0.04985911399126053,
|
| 273 |
+
"eval_p_rank/min_succ_subopt_diff_sum_usc_franka": -0.08763229846954346,
|
| 274 |
+
"eval_p_rank/max_succ_subopt_diff_sum_usc_franka": 0.2255823016166687,
|
| 275 |
+
"eval_p_rank/avg_subopt_fail_diff_sum_usc_franka": 0.27740854187868536,
|
| 276 |
+
"eval_p_rank/min_subopt_fail_diff_sum_usc_franka": -0.06445235013961792,
|
| 277 |
+
"eval_p_rank/max_subopt_fail_diff_sum_usc_franka": 0.6084701782092452,
|
| 278 |
+
"eval_p_rank/avg_succ_fail_diff_sum_usc_franka": 0.3272676558699459,
|
| 279 |
+
"eval_p_rank/min_succ_fail_diff_sum_usc_franka": -0.019217491149902344,
|
| 280 |
+
"eval_p_rank/max_succ_fail_diff_sum_usc_franka": 0.6527606612071395,
|
| 281 |
+
"eval_p_rank/ranking_acc_sum_usc_franka": 0.7708333333333334,
|
| 282 |
+
"eval_p_rank/ranking_acc_all_pairs_sum_usc_franka": 0.7708333333333334,
|
| 283 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_sum_usc_franka": 0.5625,
|
| 284 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_sum_usc_franka": 0.875,
|
| 285 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_sum_usc_franka": 0.875,
|
| 286 |
+
"eval_rew_align/success_auprc_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.10783957095259439,
|
| 287 |
+
"eval_rew_align/positive_success_acc_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.6,
|
| 288 |
+
"eval_rew_align/negative_success_acc_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.967843137254902,
|
| 289 |
+
"eval_rew_align/loss_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.4013170063495636,
|
| 290 |
+
"eval_rew_align/pearson_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.9195934693444656,
|
| 291 |
+
"eval_p_rank/kendall_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.3626666666666666,
|
| 292 |
+
"eval_p_rank/kendall_rewind_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.7333333333333333,
|
| 293 |
+
"eval_p_rank/avg_succ_subopt_diff_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.015897962450981174,
|
| 294 |
+
"eval_p_rank/min_succ_subopt_diff_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": -0.05595738887786861,
|
| 295 |
+
"eval_p_rank/max_succ_subopt_diff_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.10355948209762578,
|
| 296 |
+
"eval_p_rank/avg_subopt_fail_diff_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.19282167583703994,
|
| 297 |
+
"eval_p_rank/min_subopt_fail_diff_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.027634358406066872,
|
| 298 |
+
"eval_p_rank/max_subopt_fail_diff_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.36386977732181547,
|
| 299 |
+
"eval_p_rank/avg_succ_fail_diff_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.20871963828802112,
|
| 300 |
+
"eval_p_rank/min_succ_fail_diff_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": -0.017108345031738303,
|
| 301 |
+
"eval_p_rank/max_succ_fail_diff_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.3345988690853119,
|
| 302 |
+
"eval_p_rank/ranking_acc_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.6813333333333333,
|
| 303 |
+
"eval_p_rank/ranking_acc_all_pairs_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.6813333333333333,
|
| 304 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.76,
|
| 305 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.552,
|
| 306 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_last_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.732,
|
| 307 |
+
"eval_p_rank/kendall_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.3626666666666666,
|
| 308 |
+
"eval_p_rank/kendall_rewind_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.7333333333333333,
|
| 309 |
+
"eval_p_rank/avg_succ_subopt_diff_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.015897962450981174,
|
| 310 |
+
"eval_p_rank/min_succ_subopt_diff_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": -0.05595738887786861,
|
| 311 |
+
"eval_p_rank/max_succ_subopt_diff_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.10355948209762578,
|
| 312 |
+
"eval_p_rank/avg_subopt_fail_diff_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.19282167583703994,
|
| 313 |
+
"eval_p_rank/min_subopt_fail_diff_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.027634358406066872,
|
| 314 |
+
"eval_p_rank/max_subopt_fail_diff_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.36386977732181547,
|
| 315 |
+
"eval_p_rank/avg_succ_fail_diff_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.20871963828802112,
|
| 316 |
+
"eval_p_rank/min_succ_fail_diff_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": -0.017108345031738303,
|
| 317 |
+
"eval_p_rank/max_succ_fail_diff_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.3345988690853119,
|
| 318 |
+
"eval_p_rank/ranking_acc_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.6813333333333333,
|
| 319 |
+
"eval_p_rank/ranking_acc_all_pairs_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.6813333333333333,
|
| 320 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.76,
|
| 321 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.552,
|
| 322 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_avg_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.732,
|
| 323 |
+
"eval_p_rank/kendall_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.3626666666666666,
|
| 324 |
+
"eval_p_rank/kendall_rewind_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.7333333333333333,
|
| 325 |
+
"eval_p_rank/avg_succ_subopt_diff_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.015897962450981174,
|
| 326 |
+
"eval_p_rank/min_succ_subopt_diff_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": -0.05595738887786861,
|
| 327 |
+
"eval_p_rank/max_succ_subopt_diff_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.10355948209762578,
|
| 328 |
+
"eval_p_rank/avg_subopt_fail_diff_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.19282167583703994,
|
| 329 |
+
"eval_p_rank/min_subopt_fail_diff_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.027634358406066872,
|
| 330 |
+
"eval_p_rank/max_subopt_fail_diff_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.36386977732181547,
|
| 331 |
+
"eval_p_rank/avg_succ_fail_diff_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.20871963828802112,
|
| 332 |
+
"eval_p_rank/min_succ_fail_diff_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": -0.017108345031738303,
|
| 333 |
+
"eval_p_rank/max_succ_fail_diff_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.3345988690853119,
|
| 334 |
+
"eval_p_rank/ranking_acc_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.6813333333333333,
|
| 335 |
+
"eval_p_rank/ranking_acc_all_pairs_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.6813333333333333,
|
| 336 |
+
"eval_p_rank/ranking_acc_failure_vs_successful_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.76,
|
| 337 |
+
"eval_p_rank/ranking_acc_suboptimal_vs_successful_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.552,
|
| 338 |
+
"eval_p_rank/ranking_acc_failure_vs_suboptimal_sum_jesbu1_usc_koch_p_ranking_rfm_usc_koch_p_ranking_all": 0.732,
|
| 339 |
+
"time/custom_evaluations": 418.1960205519572
|
| 340 |
+
}
|
| 341 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e240836d7d80302ac0736421376a9e990a5af5347aef571ab6baaba66e4117a9
|
| 3 |
+
size 4965686062
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17091e5365a3b2f81082fb796ab997231bbba49ac9886ca1a687d578bec431f0
|
| 3 |
+
size 3935028936
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,745 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4450312483,
|
| 4 |
+
"total_size": 8900624966
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 405 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 700 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 701 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 702 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 703 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
|
| 704 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
|
| 705 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 706 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 707 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 708 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 709 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
|
| 710 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
|
| 711 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 712 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 713 |
+
"model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 714 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 715 |
+
"model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
|
| 716 |
+
"model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
|
| 717 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
|
| 718 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
|
| 719 |
+
"model.visual.pos_embed.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"preference_head.0.bias": "model-00001-of-00002.safetensors",
|
| 721 |
+
"preference_head.0.weight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"preference_head.1.bias": "model-00001-of-00002.safetensors",
|
| 723 |
+
"preference_head.1.weight": "model-00001-of-00002.safetensors",
|
| 724 |
+
"preference_head.4.bias": "model-00001-of-00002.safetensors",
|
| 725 |
+
"preference_head.4.weight": "model-00001-of-00002.safetensors",
|
| 726 |
+
"progress_head.0.bias": "model-00001-of-00002.safetensors",
|
| 727 |
+
"progress_head.0.weight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"progress_head.1.bias": "model-00001-of-00002.safetensors",
|
| 729 |
+
"progress_head.1.weight": "model-00001-of-00002.safetensors",
|
| 730 |
+
"progress_head.4.bias": "model-00001-of-00002.safetensors",
|
| 731 |
+
"progress_head.4.weight": "model-00001-of-00002.safetensors",
|
| 732 |
+
"similarity_head.0.bias": "model-00001-of-00002.safetensors",
|
| 733 |
+
"similarity_head.0.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"similarity_head.1.bias": "model-00001-of-00002.safetensors",
|
| 735 |
+
"similarity_head.1.weight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"similarity_head.4.bias": "model-00001-of-00002.safetensors",
|
| 737 |
+
"similarity_head.4.weight": "model-00001-of-00002.safetensors",
|
| 738 |
+
"success_head.0.bias": "model-00001-of-00002.safetensors",
|
| 739 |
+
"success_head.0.weight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"success_head.1.bias": "model-00001-of-00002.safetensors",
|
| 741 |
+
"success_head.1.weight": "model-00001-of-00002.safetensors",
|
| 742 |
+
"success_head.4.bias": "model-00001-of-00002.safetensors",
|
| 743 |
+
"success_head.4.weight": "model-00001-of-00002.safetensors"
|
| 744 |
+
}
|
| 745 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6cd66cd0eea42bf15877edda890a8793021e00eefdbdcc1e1bde285c3798d08
|
| 3 |
+
size 5905
|