Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +51 -0
- added_tokens.json +0 -0
- all_results.json +9 -0
- assets/teaser.jpg +3 -0
- config.json +206 -0
- generation_config.json +8 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +908 -0
- special_tokens_map.json +0 -0
- tokenization_internlm2.py +235 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
assets/teaser.jpg filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<h1 align="center"><strong>ARGenSeg: Image Segmentation with Autoregressive Image Generation Model</strong></h1>
|
| 2 |
+
|
| 3 |
+
<p align="center">
|
| 4 |
+
<a href="https://arxiv.org/abs/2510.20803" target='_blank'>
|
| 5 |
+
<img src="https://img.shields.io/badge/arXiv-2510.20803-red?">
|
| 6 |
+
</a>
|
| 7 |
+
<a href="https://arxiv.org/pdf/2510.20803.pdf" target='_blank'>
|
| 8 |
+
<img src="https://img.shields.io/badge/Paper-📖-blue?">
|
| 9 |
+
</a>
|
| 10 |
+
<a href="https://xlwangdev.github.io/ARGenSeg/" target='_blank'>
|
| 11 |
+
<img src="https://img.shields.io/badge/Project-Page-green?">
|
| 12 |
+
</a>
|
| 13 |
+
</p>
|
| 14 |
+
|
| 15 |
+
<p align="center">
|
| 16 |
+
<a href="https://xlwang.site" target='_blank'>Xiaolong Wang</a><sup>1</sup> ·
|
| 17 |
+
<a href="https://rulixiang.github.io/" target='_blank'>Lixiang Ru</a><sup>1</sup> ·
|
| 18 |
+
<a href="https://huang-ziyuan.github.io/" target='_blank'>Ziyuan Huang</a><sup>1</sup> ·
|
| 19 |
+
<a href="https://scholar.google.com/citations?user=PNTIf4gAAAAJ" target='_blank'>Kaixiang Ji</a><sup>1</sup><br>
|
| 20 |
+
<a href="https://openreview.net/profile?id=~DanDan_Zheng1" target='_blank'>Dandan Zheng</a><sup>1</sup> ·
|
| 21 |
+
<a href="https://scholar.google.com/citations?user=8SCEv-YAAAAJ&hl=en" target='_blank'>Jingdong Chen</a><sup>1</sup> ·
|
| 22 |
+
<a href="https://scholar.google.com/citations?user=mCVvloEAAAAJ&hl=en" target='_blank'>Jun Zhou</a><sup>1</sup>
|
| 23 |
+
</p>
|
| 24 |
+
|
| 25 |
+
<p align="center"><sup>1</sup>Ant Group · NeurIPS 2025</p>
|
| 26 |
+
|
| 27 |
+
## 🏠 About
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
We propose a novel AutoRegressive Generation-based paradigm for image Segmentation (ARGenSeg), **achieving multimodal understanding and pixel-level perception within a unified framework.** Prior works integrating image segmentation into multimodal large language models (MLLMs) typically employ either boundary points representation or dedicated segmentation heads. These methods rely on discrete representations or semantic prompts fed into task-specific decoders, which limits the ability of the MLLM to capture fine-grained visual details. To address these challenges, we introduce **a segmentation framework for MLLM based on image generation**, which naturally produces dense masks for target objects. We leverage MLLM to output visual tokens and detokenize them into images using an universal VQ-VAE, making the segmentation fully dependent on the pixel-level understanding of the MLLM. To reduce inference latency, we **employ a next-scale-prediction strategy to generate required visual tokens in parallel**. Extensive experiments demonstrate that our method surpasses prior state-of-the-art approaches on multiple segmentation datasets with a remarkable boost in inference speed, while maintaining strong understanding capabilities.
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
## 🔗 Citation
|
| 35 |
+
|
| 36 |
+
If you find this work useful, please cite:
|
| 37 |
+
|
| 38 |
+
```bibtex
|
| 39 |
+
@article{wang2025argenseg,
|
| 40 |
+
title={ARGenSeg: Image Segmentation with Autoregressive Image Generation Model},
|
| 41 |
+
author={Wang, Xiaolong and Ru, Lixiang and Huang, Ziyuan and Ji, Kaixiang and Zheng, Dandan and Chen, Jingdong and Zhou, Jun},
|
| 42 |
+
journal={arXiv preprint arXiv:2510.20803},
|
| 43 |
+
year={2025}
|
| 44 |
+
}
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
---
|
| 48 |
+
|
| 49 |
+
## 👏 Acknowledgements
|
| 50 |
+
|
| 51 |
+
We sincerely thank the contributors of [InternVL](https://github.com/OpenGVLab/InternVL), [VAR](https://github.com/FoundationVision/VAR), and [PSALM](https://github.com/zamling/PSALM) for their foundational work and open-source spirit.
|
added_tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 1.4209298644409839e+23,
|
| 4 |
+
"train_loss": 1.6960658713700907,
|
| 5 |
+
"train_runtime": 112688.7442,
|
| 6 |
+
"train_samples": 2513191,
|
| 7 |
+
"train_samples_per_second": 44.604,
|
| 8 |
+
"train_steps_per_second": 0.348
|
| 9 |
+
}
|
assets/teaser.jpg
ADDED
|
Git LFS Details
|
config.json
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_commit_hash": null,
|
| 3 |
+
"_name_or_path": "./work_dirs/internvl_chat_v2_5_mix/internvl2_5_8b_20250504-18-openseg_6_usd_ctn",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"InternVLGenSeg"
|
| 6 |
+
],
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
|
| 9 |
+
"AutoModel": "modeling_internvl_chat.InternVLChatModel",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
|
| 11 |
+
},
|
| 12 |
+
"downsample_ratio": 0.5,
|
| 13 |
+
"dynamic_image_size": false,
|
| 14 |
+
"force_image_size": 448,
|
| 15 |
+
"hidden_size": 4096,
|
| 16 |
+
"llm_config": {
|
| 17 |
+
"_attn_implementation_autoset": true,
|
| 18 |
+
"_name_or_path": "internlm/internlm2_5-7b-chat",
|
| 19 |
+
"add_cross_attention": false,
|
| 20 |
+
"architectures": [
|
| 21 |
+
"InternLM2ForCausalLM"
|
| 22 |
+
],
|
| 23 |
+
"attn_implementation": "flash_attention_2",
|
| 24 |
+
"auto_map": {
|
| 25 |
+
"AutoConfig": "configuration_internlm2.InternLM2Config",
|
| 26 |
+
"AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
|
| 27 |
+
"AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
|
| 28 |
+
"AutoModelForSequenceClassification": "modeling_internlm2.InternLM2ForSequenceClassification"
|
| 29 |
+
},
|
| 30 |
+
"bad_words_ids": null,
|
| 31 |
+
"begin_suppress_tokens": null,
|
| 32 |
+
"bias": false,
|
| 33 |
+
"bos_token_id": 1,
|
| 34 |
+
"chunk_size_feed_forward": 0,
|
| 35 |
+
"cross_attention_hidden_size": null,
|
| 36 |
+
"decoder_start_token_id": null,
|
| 37 |
+
"diversity_penalty": 0.0,
|
| 38 |
+
"do_sample": false,
|
| 39 |
+
"early_stopping": false,
|
| 40 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 41 |
+
"eos_token_id": 2,
|
| 42 |
+
"exponential_decay_length_penalty": null,
|
| 43 |
+
"finetuning_task": null,
|
| 44 |
+
"forced_bos_token_id": null,
|
| 45 |
+
"forced_eos_token_id": null,
|
| 46 |
+
"hidden_act": "silu",
|
| 47 |
+
"hidden_size": 4096,
|
| 48 |
+
"id2label": {
|
| 49 |
+
"0": "LABEL_0",
|
| 50 |
+
"1": "LABEL_1"
|
| 51 |
+
},
|
| 52 |
+
"initializer_range": 0.02,
|
| 53 |
+
"intermediate_size": 14336,
|
| 54 |
+
"is_decoder": false,
|
| 55 |
+
"is_encoder_decoder": false,
|
| 56 |
+
"label2id": {
|
| 57 |
+
"LABEL_0": 0,
|
| 58 |
+
"LABEL_1": 1
|
| 59 |
+
},
|
| 60 |
+
"length_penalty": 1.0,
|
| 61 |
+
"max_length": 20,
|
| 62 |
+
"max_position_embeddings": 32768,
|
| 63 |
+
"min_length": 0,
|
| 64 |
+
"model_type": "internlm2",
|
| 65 |
+
"no_repeat_ngram_size": 0,
|
| 66 |
+
"num_attention_heads": 32,
|
| 67 |
+
"num_beam_groups": 1,
|
| 68 |
+
"num_beams": 1,
|
| 69 |
+
"num_hidden_layers": 32,
|
| 70 |
+
"num_key_value_heads": 8,
|
| 71 |
+
"num_return_sequences": 1,
|
| 72 |
+
"output_attentions": false,
|
| 73 |
+
"output_hidden_states": false,
|
| 74 |
+
"output_scores": false,
|
| 75 |
+
"pad_token_id": 2,
|
| 76 |
+
"prefix": null,
|
| 77 |
+
"pretraining_tp": 1,
|
| 78 |
+
"problem_type": null,
|
| 79 |
+
"pruned_heads": {},
|
| 80 |
+
"remove_invalid_values": false,
|
| 81 |
+
"repetition_penalty": 1.0,
|
| 82 |
+
"return_dict": true,
|
| 83 |
+
"return_dict_in_generate": false,
|
| 84 |
+
"rms_norm_eps": 1e-05,
|
| 85 |
+
"rope_scaling": {
|
| 86 |
+
"factor": 2.0,
|
| 87 |
+
"type": "dynamic"
|
| 88 |
+
},
|
| 89 |
+
"rope_theta": 1000000,
|
| 90 |
+
"sep_token_id": null,
|
| 91 |
+
"suppress_tokens": null,
|
| 92 |
+
"task_specific_params": null,
|
| 93 |
+
"temperature": 1.0,
|
| 94 |
+
"tf_legacy_loss": false,
|
| 95 |
+
"tie_encoder_decoder": false,
|
| 96 |
+
"tie_word_embeddings": false,
|
| 97 |
+
"tokenizer_class": null,
|
| 98 |
+
"top_k": 50,
|
| 99 |
+
"top_p": 1.0,
|
| 100 |
+
"torch_dtype": "bfloat16",
|
| 101 |
+
"torchscript": false,
|
| 102 |
+
"transformers_version": "4.46.1",
|
| 103 |
+
"typical_p": 1.0,
|
| 104 |
+
"use_bfloat16": true,
|
| 105 |
+
"use_cache": false,
|
| 106 |
+
"vocab_size": 96653
|
| 107 |
+
},
|
| 108 |
+
"max_dynamic_patch": 1,
|
| 109 |
+
"min_dynamic_patch": 1,
|
| 110 |
+
"model_type": "internvl_chat",
|
| 111 |
+
"pad2square": false,
|
| 112 |
+
"ps_version": "v2",
|
| 113 |
+
"select_layer": -1,
|
| 114 |
+
"template": "internvl2_5",
|
| 115 |
+
"tie_word_embeddings": false,
|
| 116 |
+
"torch_dtype": "bfloat16",
|
| 117 |
+
"transformers_version": null,
|
| 118 |
+
"use_backbone_lora": 0,
|
| 119 |
+
"use_llm_lora": 0,
|
| 120 |
+
"use_thumbnail": true,
|
| 121 |
+
"vision_config": {
|
| 122 |
+
"_attn_implementation_autoset": true,
|
| 123 |
+
"_name_or_path": "",
|
| 124 |
+
"add_cross_attention": false,
|
| 125 |
+
"architectures": [
|
| 126 |
+
"InternVisionModel"
|
| 127 |
+
],
|
| 128 |
+
"attention_dropout": 0.0,
|
| 129 |
+
"bad_words_ids": null,
|
| 130 |
+
"begin_suppress_tokens": null,
|
| 131 |
+
"bos_token_id": null,
|
| 132 |
+
"chunk_size_feed_forward": 0,
|
| 133 |
+
"cross_attention_hidden_size": null,
|
| 134 |
+
"decoder_start_token_id": null,
|
| 135 |
+
"diversity_penalty": 0.0,
|
| 136 |
+
"do_sample": false,
|
| 137 |
+
"drop_path_rate": 0.1,
|
| 138 |
+
"dropout": 0.0,
|
| 139 |
+
"early_stopping": false,
|
| 140 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 141 |
+
"eos_token_id": null,
|
| 142 |
+
"exponential_decay_length_penalty": null,
|
| 143 |
+
"finetuning_task": null,
|
| 144 |
+
"forced_bos_token_id": null,
|
| 145 |
+
"forced_eos_token_id": null,
|
| 146 |
+
"hidden_act": "gelu",
|
| 147 |
+
"hidden_size": 1024,
|
| 148 |
+
"id2label": {
|
| 149 |
+
"0": "LABEL_0",
|
| 150 |
+
"1": "LABEL_1"
|
| 151 |
+
},
|
| 152 |
+
"image_size": 448,
|
| 153 |
+
"initializer_factor": 1.0,
|
| 154 |
+
"initializer_range": 0.02,
|
| 155 |
+
"intermediate_size": 4096,
|
| 156 |
+
"is_decoder": false,
|
| 157 |
+
"is_encoder_decoder": false,
|
| 158 |
+
"label2id": {
|
| 159 |
+
"LABEL_0": 0,
|
| 160 |
+
"LABEL_1": 1
|
| 161 |
+
},
|
| 162 |
+
"layer_norm_eps": 1e-06,
|
| 163 |
+
"length_penalty": 1.0,
|
| 164 |
+
"max_length": 20,
|
| 165 |
+
"min_length": 0,
|
| 166 |
+
"model_type": "intern_vit_6b",
|
| 167 |
+
"no_repeat_ngram_size": 0,
|
| 168 |
+
"norm_type": "layer_norm",
|
| 169 |
+
"num_attention_heads": 16,
|
| 170 |
+
"num_beam_groups": 1,
|
| 171 |
+
"num_beams": 1,
|
| 172 |
+
"num_channels": 3,
|
| 173 |
+
"num_hidden_layers": 24,
|
| 174 |
+
"num_return_sequences": 1,
|
| 175 |
+
"output_attentions": false,
|
| 176 |
+
"output_hidden_states": false,
|
| 177 |
+
"output_scores": false,
|
| 178 |
+
"pad_token_id": null,
|
| 179 |
+
"patch_size": 14,
|
| 180 |
+
"prefix": null,
|
| 181 |
+
"problem_type": null,
|
| 182 |
+
"pruned_heads": {},
|
| 183 |
+
"qk_normalization": false,
|
| 184 |
+
"qkv_bias": true,
|
| 185 |
+
"remove_invalid_values": false,
|
| 186 |
+
"repetition_penalty": 1.0,
|
| 187 |
+
"return_dict": true,
|
| 188 |
+
"return_dict_in_generate": false,
|
| 189 |
+
"sep_token_id": null,
|
| 190 |
+
"suppress_tokens": null,
|
| 191 |
+
"task_specific_params": null,
|
| 192 |
+
"temperature": 1.0,
|
| 193 |
+
"tf_legacy_loss": false,
|
| 194 |
+
"tie_encoder_decoder": false,
|
| 195 |
+
"tie_word_embeddings": true,
|
| 196 |
+
"tokenizer_class": null,
|
| 197 |
+
"top_k": 50,
|
| 198 |
+
"top_p": 1.0,
|
| 199 |
+
"torch_dtype": "bfloat16",
|
| 200 |
+
"torchscript": false,
|
| 201 |
+
"transformers_version": "4.46.1",
|
| 202 |
+
"typical_p": 1.0,
|
| 203 |
+
"use_bfloat16": true,
|
| 204 |
+
"use_flash_attn": true
|
| 205 |
+
}
|
| 206 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
92542,
|
| 5 |
+
92543
|
| 6 |
+
],
|
| 7 |
+
"transformers_version": "4.46.1"
|
| 8 |
+
}
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bc6b1c75fd83a574f89258866de5c487544c4668df2bad45709aa634bb597c6
|
| 3 |
+
size 4979102184
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9283dcee40c307649243523856cf63603b5621ace553b59a938d648d6bd1d680
|
| 3 |
+
size 4915914584
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4cb2c13d5e4cce351f37b038ea9535eb67bbd1b9f74e7a34a3c798922b055bc
|
| 3 |
+
size 4915914592
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4060ec2a2f45a3904d4d2c8c5191a93c0a687457cb27d249be3e0f40170fb040
|
| 3 |
+
size 1630984262
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,908 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16441806598
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"image_tokenizer.decoder.conv_in.bias": "model-00004-of-00004.safetensors",
|
| 7 |
+
"image_tokenizer.decoder.conv_in.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"image_tokenizer.decoder.conv_out.bias": "model-00004-of-00004.safetensors",
|
| 9 |
+
"image_tokenizer.decoder.conv_out.weight": "model-00004-of-00004.safetensors",
|
| 10 |
+
"image_tokenizer.decoder.mid.attn_1.norm.bias": "model-00004-of-00004.safetensors",
|
| 11 |
+
"image_tokenizer.decoder.mid.attn_1.norm.weight": "model-00004-of-00004.safetensors",
|
| 12 |
+
"image_tokenizer.decoder.mid.attn_1.proj_out.bias": "model-00004-of-00004.safetensors",
|
| 13 |
+
"image_tokenizer.decoder.mid.attn_1.proj_out.weight": "model-00004-of-00004.safetensors",
|
| 14 |
+
"image_tokenizer.decoder.mid.attn_1.qkv.bias": "model-00004-of-00004.safetensors",
|
| 15 |
+
"image_tokenizer.decoder.mid.attn_1.qkv.weight": "model-00004-of-00004.safetensors",
|
| 16 |
+
"image_tokenizer.decoder.mid.block_1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 17 |
+
"image_tokenizer.decoder.mid.block_1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 18 |
+
"image_tokenizer.decoder.mid.block_1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 19 |
+
"image_tokenizer.decoder.mid.block_1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 20 |
+
"image_tokenizer.decoder.mid.block_1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 21 |
+
"image_tokenizer.decoder.mid.block_1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 22 |
+
"image_tokenizer.decoder.mid.block_1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 23 |
+
"image_tokenizer.decoder.mid.block_1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 24 |
+
"image_tokenizer.decoder.mid.block_2.conv1.bias": "model-00004-of-00004.safetensors",
|
| 25 |
+
"image_tokenizer.decoder.mid.block_2.conv1.weight": "model-00004-of-00004.safetensors",
|
| 26 |
+
"image_tokenizer.decoder.mid.block_2.conv2.bias": "model-00004-of-00004.safetensors",
|
| 27 |
+
"image_tokenizer.decoder.mid.block_2.conv2.weight": "model-00004-of-00004.safetensors",
|
| 28 |
+
"image_tokenizer.decoder.mid.block_2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 29 |
+
"image_tokenizer.decoder.mid.block_2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 30 |
+
"image_tokenizer.decoder.mid.block_2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 31 |
+
"image_tokenizer.decoder.mid.block_2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 32 |
+
"image_tokenizer.decoder.norm_out.bias": "model-00004-of-00004.safetensors",
|
| 33 |
+
"image_tokenizer.decoder.norm_out.weight": "model-00004-of-00004.safetensors",
|
| 34 |
+
"image_tokenizer.decoder.up.0.block.0.conv1.bias": "model-00004-of-00004.safetensors",
|
| 35 |
+
"image_tokenizer.decoder.up.0.block.0.conv1.weight": "model-00004-of-00004.safetensors",
|
| 36 |
+
"image_tokenizer.decoder.up.0.block.0.conv2.bias": "model-00004-of-00004.safetensors",
|
| 37 |
+
"image_tokenizer.decoder.up.0.block.0.conv2.weight": "model-00004-of-00004.safetensors",
|
| 38 |
+
"image_tokenizer.decoder.up.0.block.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 39 |
+
"image_tokenizer.decoder.up.0.block.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 40 |
+
"image_tokenizer.decoder.up.0.block.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 41 |
+
"image_tokenizer.decoder.up.0.block.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 42 |
+
"image_tokenizer.decoder.up.0.block.1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 43 |
+
"image_tokenizer.decoder.up.0.block.1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 44 |
+
"image_tokenizer.decoder.up.0.block.1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 45 |
+
"image_tokenizer.decoder.up.0.block.1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 46 |
+
"image_tokenizer.decoder.up.0.block.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 47 |
+
"image_tokenizer.decoder.up.0.block.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 48 |
+
"image_tokenizer.decoder.up.0.block.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 49 |
+
"image_tokenizer.decoder.up.0.block.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 50 |
+
"image_tokenizer.decoder.up.0.block.2.conv1.bias": "model-00004-of-00004.safetensors",
|
| 51 |
+
"image_tokenizer.decoder.up.0.block.2.conv1.weight": "model-00004-of-00004.safetensors",
|
| 52 |
+
"image_tokenizer.decoder.up.0.block.2.conv2.bias": "model-00004-of-00004.safetensors",
|
| 53 |
+
"image_tokenizer.decoder.up.0.block.2.conv2.weight": "model-00004-of-00004.safetensors",
|
| 54 |
+
"image_tokenizer.decoder.up.0.block.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 55 |
+
"image_tokenizer.decoder.up.0.block.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 56 |
+
"image_tokenizer.decoder.up.0.block.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 57 |
+
"image_tokenizer.decoder.up.0.block.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 58 |
+
"image_tokenizer.decoder.up.1.block.0.conv1.bias": "model-00004-of-00004.safetensors",
|
| 59 |
+
"image_tokenizer.decoder.up.1.block.0.conv1.weight": "model-00004-of-00004.safetensors",
|
| 60 |
+
"image_tokenizer.decoder.up.1.block.0.conv2.bias": "model-00004-of-00004.safetensors",
|
| 61 |
+
"image_tokenizer.decoder.up.1.block.0.conv2.weight": "model-00004-of-00004.safetensors",
|
| 62 |
+
"image_tokenizer.decoder.up.1.block.0.nin_shortcut.bias": "model-00004-of-00004.safetensors",
|
| 63 |
+
"image_tokenizer.decoder.up.1.block.0.nin_shortcut.weight": "model-00004-of-00004.safetensors",
|
| 64 |
+
"image_tokenizer.decoder.up.1.block.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 65 |
+
"image_tokenizer.decoder.up.1.block.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 66 |
+
"image_tokenizer.decoder.up.1.block.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 67 |
+
"image_tokenizer.decoder.up.1.block.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 68 |
+
"image_tokenizer.decoder.up.1.block.1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 69 |
+
"image_tokenizer.decoder.up.1.block.1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 70 |
+
"image_tokenizer.decoder.up.1.block.1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 71 |
+
"image_tokenizer.decoder.up.1.block.1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 72 |
+
"image_tokenizer.decoder.up.1.block.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 73 |
+
"image_tokenizer.decoder.up.1.block.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 74 |
+
"image_tokenizer.decoder.up.1.block.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 75 |
+
"image_tokenizer.decoder.up.1.block.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 76 |
+
"image_tokenizer.decoder.up.1.block.2.conv1.bias": "model-00004-of-00004.safetensors",
|
| 77 |
+
"image_tokenizer.decoder.up.1.block.2.conv1.weight": "model-00004-of-00004.safetensors",
|
| 78 |
+
"image_tokenizer.decoder.up.1.block.2.conv2.bias": "model-00004-of-00004.safetensors",
|
| 79 |
+
"image_tokenizer.decoder.up.1.block.2.conv2.weight": "model-00004-of-00004.safetensors",
|
| 80 |
+
"image_tokenizer.decoder.up.1.block.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 81 |
+
"image_tokenizer.decoder.up.1.block.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 82 |
+
"image_tokenizer.decoder.up.1.block.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 83 |
+
"image_tokenizer.decoder.up.1.block.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 84 |
+
"image_tokenizer.decoder.up.1.upsample.conv.bias": "model-00004-of-00004.safetensors",
|
| 85 |
+
"image_tokenizer.decoder.up.1.upsample.conv.weight": "model-00004-of-00004.safetensors",
|
| 86 |
+
"image_tokenizer.decoder.up.2.block.0.conv1.bias": "model-00004-of-00004.safetensors",
|
| 87 |
+
"image_tokenizer.decoder.up.2.block.0.conv1.weight": "model-00004-of-00004.safetensors",
|
| 88 |
+
"image_tokenizer.decoder.up.2.block.0.conv2.bias": "model-00004-of-00004.safetensors",
|
| 89 |
+
"image_tokenizer.decoder.up.2.block.0.conv2.weight": "model-00004-of-00004.safetensors",
|
| 90 |
+
"image_tokenizer.decoder.up.2.block.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 91 |
+
"image_tokenizer.decoder.up.2.block.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 92 |
+
"image_tokenizer.decoder.up.2.block.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 93 |
+
"image_tokenizer.decoder.up.2.block.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 94 |
+
"image_tokenizer.decoder.up.2.block.1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 95 |
+
"image_tokenizer.decoder.up.2.block.1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 96 |
+
"image_tokenizer.decoder.up.2.block.1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 97 |
+
"image_tokenizer.decoder.up.2.block.1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 98 |
+
"image_tokenizer.decoder.up.2.block.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 99 |
+
"image_tokenizer.decoder.up.2.block.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 100 |
+
"image_tokenizer.decoder.up.2.block.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 101 |
+
"image_tokenizer.decoder.up.2.block.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 102 |
+
"image_tokenizer.decoder.up.2.block.2.conv1.bias": "model-00004-of-00004.safetensors",
|
| 103 |
+
"image_tokenizer.decoder.up.2.block.2.conv1.weight": "model-00004-of-00004.safetensors",
|
| 104 |
+
"image_tokenizer.decoder.up.2.block.2.conv2.bias": "model-00004-of-00004.safetensors",
|
| 105 |
+
"image_tokenizer.decoder.up.2.block.2.conv2.weight": "model-00004-of-00004.safetensors",
|
| 106 |
+
"image_tokenizer.decoder.up.2.block.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 107 |
+
"image_tokenizer.decoder.up.2.block.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 108 |
+
"image_tokenizer.decoder.up.2.block.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 109 |
+
"image_tokenizer.decoder.up.2.block.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 110 |
+
"image_tokenizer.decoder.up.2.upsample.conv.bias": "model-00004-of-00004.safetensors",
|
| 111 |
+
"image_tokenizer.decoder.up.2.upsample.conv.weight": "model-00004-of-00004.safetensors",
|
| 112 |
+
"image_tokenizer.decoder.up.3.block.0.conv1.bias": "model-00004-of-00004.safetensors",
|
| 113 |
+
"image_tokenizer.decoder.up.3.block.0.conv1.weight": "model-00004-of-00004.safetensors",
|
| 114 |
+
"image_tokenizer.decoder.up.3.block.0.conv2.bias": "model-00004-of-00004.safetensors",
|
| 115 |
+
"image_tokenizer.decoder.up.3.block.0.conv2.weight": "model-00004-of-00004.safetensors",
|
| 116 |
+
"image_tokenizer.decoder.up.3.block.0.nin_shortcut.bias": "model-00004-of-00004.safetensors",
|
| 117 |
+
"image_tokenizer.decoder.up.3.block.0.nin_shortcut.weight": "model-00004-of-00004.safetensors",
|
| 118 |
+
"image_tokenizer.decoder.up.3.block.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 119 |
+
"image_tokenizer.decoder.up.3.block.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 120 |
+
"image_tokenizer.decoder.up.3.block.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 121 |
+
"image_tokenizer.decoder.up.3.block.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 122 |
+
"image_tokenizer.decoder.up.3.block.1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 123 |
+
"image_tokenizer.decoder.up.3.block.1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 124 |
+
"image_tokenizer.decoder.up.3.block.1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 125 |
+
"image_tokenizer.decoder.up.3.block.1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 126 |
+
"image_tokenizer.decoder.up.3.block.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 127 |
+
"image_tokenizer.decoder.up.3.block.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 128 |
+
"image_tokenizer.decoder.up.3.block.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 129 |
+
"image_tokenizer.decoder.up.3.block.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 130 |
+
"image_tokenizer.decoder.up.3.block.2.conv1.bias": "model-00004-of-00004.safetensors",
|
| 131 |
+
"image_tokenizer.decoder.up.3.block.2.conv1.weight": "model-00004-of-00004.safetensors",
|
| 132 |
+
"image_tokenizer.decoder.up.3.block.2.conv2.bias": "model-00004-of-00004.safetensors",
|
| 133 |
+
"image_tokenizer.decoder.up.3.block.2.conv2.weight": "model-00004-of-00004.safetensors",
|
| 134 |
+
"image_tokenizer.decoder.up.3.block.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 135 |
+
"image_tokenizer.decoder.up.3.block.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 136 |
+
"image_tokenizer.decoder.up.3.block.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 137 |
+
"image_tokenizer.decoder.up.3.block.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 138 |
+
"image_tokenizer.decoder.up.3.upsample.conv.bias": "model-00004-of-00004.safetensors",
|
| 139 |
+
"image_tokenizer.decoder.up.3.upsample.conv.weight": "model-00004-of-00004.safetensors",
|
| 140 |
+
"image_tokenizer.decoder.up.4.attn.0.norm.bias": "model-00004-of-00004.safetensors",
|
| 141 |
+
"image_tokenizer.decoder.up.4.attn.0.norm.weight": "model-00004-of-00004.safetensors",
|
| 142 |
+
"image_tokenizer.decoder.up.4.attn.0.proj_out.bias": "model-00004-of-00004.safetensors",
|
| 143 |
+
"image_tokenizer.decoder.up.4.attn.0.proj_out.weight": "model-00004-of-00004.safetensors",
|
| 144 |
+
"image_tokenizer.decoder.up.4.attn.0.qkv.bias": "model-00004-of-00004.safetensors",
|
| 145 |
+
"image_tokenizer.decoder.up.4.attn.0.qkv.weight": "model-00004-of-00004.safetensors",
|
| 146 |
+
"image_tokenizer.decoder.up.4.attn.1.norm.bias": "model-00004-of-00004.safetensors",
|
| 147 |
+
"image_tokenizer.decoder.up.4.attn.1.norm.weight": "model-00004-of-00004.safetensors",
|
| 148 |
+
"image_tokenizer.decoder.up.4.attn.1.proj_out.bias": "model-00004-of-00004.safetensors",
|
| 149 |
+
"image_tokenizer.decoder.up.4.attn.1.proj_out.weight": "model-00004-of-00004.safetensors",
|
| 150 |
+
"image_tokenizer.decoder.up.4.attn.1.qkv.bias": "model-00004-of-00004.safetensors",
|
| 151 |
+
"image_tokenizer.decoder.up.4.attn.1.qkv.weight": "model-00004-of-00004.safetensors",
|
| 152 |
+
"image_tokenizer.decoder.up.4.attn.2.norm.bias": "model-00004-of-00004.safetensors",
|
| 153 |
+
"image_tokenizer.decoder.up.4.attn.2.norm.weight": "model-00004-of-00004.safetensors",
|
| 154 |
+
"image_tokenizer.decoder.up.4.attn.2.proj_out.bias": "model-00004-of-00004.safetensors",
|
| 155 |
+
"image_tokenizer.decoder.up.4.attn.2.proj_out.weight": "model-00004-of-00004.safetensors",
|
| 156 |
+
"image_tokenizer.decoder.up.4.attn.2.qkv.bias": "model-00004-of-00004.safetensors",
|
| 157 |
+
"image_tokenizer.decoder.up.4.attn.2.qkv.weight": "model-00004-of-00004.safetensors",
|
| 158 |
+
"image_tokenizer.decoder.up.4.block.0.conv1.bias": "model-00004-of-00004.safetensors",
|
| 159 |
+
"image_tokenizer.decoder.up.4.block.0.conv1.weight": "model-00004-of-00004.safetensors",
|
| 160 |
+
"image_tokenizer.decoder.up.4.block.0.conv2.bias": "model-00004-of-00004.safetensors",
|
| 161 |
+
"image_tokenizer.decoder.up.4.block.0.conv2.weight": "model-00004-of-00004.safetensors",
|
| 162 |
+
"image_tokenizer.decoder.up.4.block.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 163 |
+
"image_tokenizer.decoder.up.4.block.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 164 |
+
"image_tokenizer.decoder.up.4.block.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 165 |
+
"image_tokenizer.decoder.up.4.block.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 166 |
+
"image_tokenizer.decoder.up.4.block.1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 167 |
+
"image_tokenizer.decoder.up.4.block.1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 168 |
+
"image_tokenizer.decoder.up.4.block.1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 169 |
+
"image_tokenizer.decoder.up.4.block.1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 170 |
+
"image_tokenizer.decoder.up.4.block.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 171 |
+
"image_tokenizer.decoder.up.4.block.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 172 |
+
"image_tokenizer.decoder.up.4.block.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 173 |
+
"image_tokenizer.decoder.up.4.block.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 174 |
+
"image_tokenizer.decoder.up.4.block.2.conv1.bias": "model-00004-of-00004.safetensors",
|
| 175 |
+
"image_tokenizer.decoder.up.4.block.2.conv1.weight": "model-00004-of-00004.safetensors",
|
| 176 |
+
"image_tokenizer.decoder.up.4.block.2.conv2.bias": "model-00004-of-00004.safetensors",
|
| 177 |
+
"image_tokenizer.decoder.up.4.block.2.conv2.weight": "model-00004-of-00004.safetensors",
|
| 178 |
+
"image_tokenizer.decoder.up.4.block.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 179 |
+
"image_tokenizer.decoder.up.4.block.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 180 |
+
"image_tokenizer.decoder.up.4.block.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 181 |
+
"image_tokenizer.decoder.up.4.block.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 182 |
+
"image_tokenizer.decoder.up.4.upsample.conv.bias": "model-00004-of-00004.safetensors",
|
| 183 |
+
"image_tokenizer.decoder.up.4.upsample.conv.weight": "model-00004-of-00004.safetensors",
|
| 184 |
+
"image_tokenizer.encoder.conv_in.bias": "model-00004-of-00004.safetensors",
|
| 185 |
+
"image_tokenizer.encoder.conv_in.weight": "model-00004-of-00004.safetensors",
|
| 186 |
+
"image_tokenizer.encoder.conv_out.bias": "model-00004-of-00004.safetensors",
|
| 187 |
+
"image_tokenizer.encoder.conv_out.weight": "model-00004-of-00004.safetensors",
|
| 188 |
+
"image_tokenizer.encoder.down.0.block.0.conv1.bias": "model-00004-of-00004.safetensors",
|
| 189 |
+
"image_tokenizer.encoder.down.0.block.0.conv1.weight": "model-00004-of-00004.safetensors",
|
| 190 |
+
"image_tokenizer.encoder.down.0.block.0.conv2.bias": "model-00004-of-00004.safetensors",
|
| 191 |
+
"image_tokenizer.encoder.down.0.block.0.conv2.weight": "model-00004-of-00004.safetensors",
|
| 192 |
+
"image_tokenizer.encoder.down.0.block.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 193 |
+
"image_tokenizer.encoder.down.0.block.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 194 |
+
"image_tokenizer.encoder.down.0.block.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 195 |
+
"image_tokenizer.encoder.down.0.block.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 196 |
+
"image_tokenizer.encoder.down.0.block.1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 197 |
+
"image_tokenizer.encoder.down.0.block.1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 198 |
+
"image_tokenizer.encoder.down.0.block.1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 199 |
+
"image_tokenizer.encoder.down.0.block.1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 200 |
+
"image_tokenizer.encoder.down.0.block.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 201 |
+
"image_tokenizer.encoder.down.0.block.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 202 |
+
"image_tokenizer.encoder.down.0.block.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 203 |
+
"image_tokenizer.encoder.down.0.block.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 204 |
+
"image_tokenizer.encoder.down.0.downsample.conv.bias": "model-00004-of-00004.safetensors",
|
| 205 |
+
"image_tokenizer.encoder.down.0.downsample.conv.weight": "model-00004-of-00004.safetensors",
|
| 206 |
+
"image_tokenizer.encoder.down.1.block.0.conv1.bias": "model-00004-of-00004.safetensors",
|
| 207 |
+
"image_tokenizer.encoder.down.1.block.0.conv1.weight": "model-00004-of-00004.safetensors",
|
| 208 |
+
"image_tokenizer.encoder.down.1.block.0.conv2.bias": "model-00004-of-00004.safetensors",
|
| 209 |
+
"image_tokenizer.encoder.down.1.block.0.conv2.weight": "model-00004-of-00004.safetensors",
|
| 210 |
+
"image_tokenizer.encoder.down.1.block.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 211 |
+
"image_tokenizer.encoder.down.1.block.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 212 |
+
"image_tokenizer.encoder.down.1.block.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 213 |
+
"image_tokenizer.encoder.down.1.block.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 214 |
+
"image_tokenizer.encoder.down.1.block.1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 215 |
+
"image_tokenizer.encoder.down.1.block.1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 216 |
+
"image_tokenizer.encoder.down.1.block.1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 217 |
+
"image_tokenizer.encoder.down.1.block.1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 218 |
+
"image_tokenizer.encoder.down.1.block.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 219 |
+
"image_tokenizer.encoder.down.1.block.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 220 |
+
"image_tokenizer.encoder.down.1.block.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 221 |
+
"image_tokenizer.encoder.down.1.block.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 222 |
+
"image_tokenizer.encoder.down.1.downsample.conv.bias": "model-00004-of-00004.safetensors",
|
| 223 |
+
"image_tokenizer.encoder.down.1.downsample.conv.weight": "model-00004-of-00004.safetensors",
|
| 224 |
+
"image_tokenizer.encoder.down.2.block.0.conv1.bias": "model-00004-of-00004.safetensors",
|
| 225 |
+
"image_tokenizer.encoder.down.2.block.0.conv1.weight": "model-00004-of-00004.safetensors",
|
| 226 |
+
"image_tokenizer.encoder.down.2.block.0.conv2.bias": "model-00004-of-00004.safetensors",
|
| 227 |
+
"image_tokenizer.encoder.down.2.block.0.conv2.weight": "model-00004-of-00004.safetensors",
|
| 228 |
+
"image_tokenizer.encoder.down.2.block.0.nin_shortcut.bias": "model-00004-of-00004.safetensors",
|
| 229 |
+
"image_tokenizer.encoder.down.2.block.0.nin_shortcut.weight": "model-00004-of-00004.safetensors",
|
| 230 |
+
"image_tokenizer.encoder.down.2.block.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 231 |
+
"image_tokenizer.encoder.down.2.block.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 232 |
+
"image_tokenizer.encoder.down.2.block.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 233 |
+
"image_tokenizer.encoder.down.2.block.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 234 |
+
"image_tokenizer.encoder.down.2.block.1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 235 |
+
"image_tokenizer.encoder.down.2.block.1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 236 |
+
"image_tokenizer.encoder.down.2.block.1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 237 |
+
"image_tokenizer.encoder.down.2.block.1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 238 |
+
"image_tokenizer.encoder.down.2.block.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 239 |
+
"image_tokenizer.encoder.down.2.block.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 240 |
+
"image_tokenizer.encoder.down.2.block.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 241 |
+
"image_tokenizer.encoder.down.2.block.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 242 |
+
"image_tokenizer.encoder.down.2.downsample.conv.bias": "model-00004-of-00004.safetensors",
|
| 243 |
+
"image_tokenizer.encoder.down.2.downsample.conv.weight": "model-00004-of-00004.safetensors",
|
| 244 |
+
"image_tokenizer.encoder.down.3.block.0.conv1.bias": "model-00004-of-00004.safetensors",
|
| 245 |
+
"image_tokenizer.encoder.down.3.block.0.conv1.weight": "model-00004-of-00004.safetensors",
|
| 246 |
+
"image_tokenizer.encoder.down.3.block.0.conv2.bias": "model-00004-of-00004.safetensors",
|
| 247 |
+
"image_tokenizer.encoder.down.3.block.0.conv2.weight": "model-00004-of-00004.safetensors",
|
| 248 |
+
"image_tokenizer.encoder.down.3.block.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 249 |
+
"image_tokenizer.encoder.down.3.block.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 250 |
+
"image_tokenizer.encoder.down.3.block.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 251 |
+
"image_tokenizer.encoder.down.3.block.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 252 |
+
"image_tokenizer.encoder.down.3.block.1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 253 |
+
"image_tokenizer.encoder.down.3.block.1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 254 |
+
"image_tokenizer.encoder.down.3.block.1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 255 |
+
"image_tokenizer.encoder.down.3.block.1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 256 |
+
"image_tokenizer.encoder.down.3.block.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 257 |
+
"image_tokenizer.encoder.down.3.block.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 258 |
+
"image_tokenizer.encoder.down.3.block.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 259 |
+
"image_tokenizer.encoder.down.3.block.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 260 |
+
"image_tokenizer.encoder.down.3.downsample.conv.bias": "model-00004-of-00004.safetensors",
|
| 261 |
+
"image_tokenizer.encoder.down.3.downsample.conv.weight": "model-00004-of-00004.safetensors",
|
| 262 |
+
"image_tokenizer.encoder.down.4.attn.0.norm.bias": "model-00004-of-00004.safetensors",
|
| 263 |
+
"image_tokenizer.encoder.down.4.attn.0.norm.weight": "model-00004-of-00004.safetensors",
|
| 264 |
+
"image_tokenizer.encoder.down.4.attn.0.proj_out.bias": "model-00004-of-00004.safetensors",
|
| 265 |
+
"image_tokenizer.encoder.down.4.attn.0.proj_out.weight": "model-00004-of-00004.safetensors",
|
| 266 |
+
"image_tokenizer.encoder.down.4.attn.0.qkv.bias": "model-00004-of-00004.safetensors",
|
| 267 |
+
"image_tokenizer.encoder.down.4.attn.0.qkv.weight": "model-00004-of-00004.safetensors",
|
| 268 |
+
"image_tokenizer.encoder.down.4.attn.1.norm.bias": "model-00004-of-00004.safetensors",
|
| 269 |
+
"image_tokenizer.encoder.down.4.attn.1.norm.weight": "model-00004-of-00004.safetensors",
|
| 270 |
+
"image_tokenizer.encoder.down.4.attn.1.proj_out.bias": "model-00004-of-00004.safetensors",
|
| 271 |
+
"image_tokenizer.encoder.down.4.attn.1.proj_out.weight": "model-00004-of-00004.safetensors",
|
| 272 |
+
"image_tokenizer.encoder.down.4.attn.1.qkv.bias": "model-00004-of-00004.safetensors",
|
| 273 |
+
"image_tokenizer.encoder.down.4.attn.1.qkv.weight": "model-00004-of-00004.safetensors",
|
| 274 |
+
"image_tokenizer.encoder.down.4.block.0.conv1.bias": "model-00004-of-00004.safetensors",
|
| 275 |
+
"image_tokenizer.encoder.down.4.block.0.conv1.weight": "model-00004-of-00004.safetensors",
|
| 276 |
+
"image_tokenizer.encoder.down.4.block.0.conv2.bias": "model-00004-of-00004.safetensors",
|
| 277 |
+
"image_tokenizer.encoder.down.4.block.0.conv2.weight": "model-00004-of-00004.safetensors",
|
| 278 |
+
"image_tokenizer.encoder.down.4.block.0.nin_shortcut.bias": "model-00004-of-00004.safetensors",
|
| 279 |
+
"image_tokenizer.encoder.down.4.block.0.nin_shortcut.weight": "model-00004-of-00004.safetensors",
|
| 280 |
+
"image_tokenizer.encoder.down.4.block.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 281 |
+
"image_tokenizer.encoder.down.4.block.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 282 |
+
"image_tokenizer.encoder.down.4.block.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 283 |
+
"image_tokenizer.encoder.down.4.block.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 284 |
+
"image_tokenizer.encoder.down.4.block.1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 285 |
+
"image_tokenizer.encoder.down.4.block.1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 286 |
+
"image_tokenizer.encoder.down.4.block.1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 287 |
+
"image_tokenizer.encoder.down.4.block.1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 288 |
+
"image_tokenizer.encoder.down.4.block.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 289 |
+
"image_tokenizer.encoder.down.4.block.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 290 |
+
"image_tokenizer.encoder.down.4.block.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 291 |
+
"image_tokenizer.encoder.down.4.block.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 292 |
+
"image_tokenizer.encoder.mid.attn_1.norm.bias": "model-00004-of-00004.safetensors",
|
| 293 |
+
"image_tokenizer.encoder.mid.attn_1.norm.weight": "model-00004-of-00004.safetensors",
|
| 294 |
+
"image_tokenizer.encoder.mid.attn_1.proj_out.bias": "model-00004-of-00004.safetensors",
|
| 295 |
+
"image_tokenizer.encoder.mid.attn_1.proj_out.weight": "model-00004-of-00004.safetensors",
|
| 296 |
+
"image_tokenizer.encoder.mid.attn_1.qkv.bias": "model-00004-of-00004.safetensors",
|
| 297 |
+
"image_tokenizer.encoder.mid.attn_1.qkv.weight": "model-00004-of-00004.safetensors",
|
| 298 |
+
"image_tokenizer.encoder.mid.block_1.conv1.bias": "model-00004-of-00004.safetensors",
|
| 299 |
+
"image_tokenizer.encoder.mid.block_1.conv1.weight": "model-00004-of-00004.safetensors",
|
| 300 |
+
"image_tokenizer.encoder.mid.block_1.conv2.bias": "model-00004-of-00004.safetensors",
|
| 301 |
+
"image_tokenizer.encoder.mid.block_1.conv2.weight": "model-00004-of-00004.safetensors",
|
| 302 |
+
"image_tokenizer.encoder.mid.block_1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 303 |
+
"image_tokenizer.encoder.mid.block_1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 304 |
+
"image_tokenizer.encoder.mid.block_1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 305 |
+
"image_tokenizer.encoder.mid.block_1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 306 |
+
"image_tokenizer.encoder.mid.block_2.conv1.bias": "model-00004-of-00004.safetensors",
|
| 307 |
+
"image_tokenizer.encoder.mid.block_2.conv1.weight": "model-00004-of-00004.safetensors",
|
| 308 |
+
"image_tokenizer.encoder.mid.block_2.conv2.bias": "model-00004-of-00004.safetensors",
|
| 309 |
+
"image_tokenizer.encoder.mid.block_2.conv2.weight": "model-00004-of-00004.safetensors",
|
| 310 |
+
"image_tokenizer.encoder.mid.block_2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 311 |
+
"image_tokenizer.encoder.mid.block_2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 312 |
+
"image_tokenizer.encoder.mid.block_2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 313 |
+
"image_tokenizer.encoder.mid.block_2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 314 |
+
"image_tokenizer.encoder.norm_out.bias": "model-00004-of-00004.safetensors",
|
| 315 |
+
"image_tokenizer.encoder.norm_out.weight": "model-00004-of-00004.safetensors",
|
| 316 |
+
"image_tokenizer.post_quant_conv.bias": "model-00004-of-00004.safetensors",
|
| 317 |
+
"image_tokenizer.post_quant_conv.weight": "model-00004-of-00004.safetensors",
|
| 318 |
+
"image_tokenizer.quant_conv.bias": "model-00004-of-00004.safetensors",
|
| 319 |
+
"image_tokenizer.quant_conv.weight": "model-00004-of-00004.safetensors",
|
| 320 |
+
"image_tokenizer.quantize.ema_vocab_hit_SV": "model-00004-of-00004.safetensors",
|
| 321 |
+
"image_tokenizer.quantize.embedding.weight": "model-00004-of-00004.safetensors",
|
| 322 |
+
"image_tokenizer.quantize.quant_resi.qresi_ls.0.bias": "model-00004-of-00004.safetensors",
|
| 323 |
+
"image_tokenizer.quantize.quant_resi.qresi_ls.0.weight": "model-00004-of-00004.safetensors",
|
| 324 |
+
"image_tokenizer.quantize.quant_resi.qresi_ls.1.bias": "model-00004-of-00004.safetensors",
|
| 325 |
+
"image_tokenizer.quantize.quant_resi.qresi_ls.1.weight": "model-00004-of-00004.safetensors",
|
| 326 |
+
"image_tokenizer.quantize.quant_resi.qresi_ls.2.bias": "model-00004-of-00004.safetensors",
|
| 327 |
+
"image_tokenizer.quantize.quant_resi.qresi_ls.2.weight": "model-00004-of-00004.safetensors",
|
| 328 |
+
"image_tokenizer.quantize.quant_resi.qresi_ls.3.bias": "model-00004-of-00004.safetensors",
|
| 329 |
+
"image_tokenizer.quantize.quant_resi.qresi_ls.3.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"language_model.model.layers.0.attention.wo.weight": "model-00001-of-00004.safetensors",
|
| 331 |
+
"language_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
| 332 |
+
"language_model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
|
| 333 |
+
"language_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
| 334 |
+
"language_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
| 335 |
+
"language_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
| 336 |
+
"language_model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
| 337 |
+
"language_model.model.layers.1.attention.wo.weight": "model-00001-of-00004.safetensors",
|
| 338 |
+
"language_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
| 339 |
+
"language_model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"language_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"language_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"language_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"language_model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"language_model.model.layers.10.attention.wo.weight": "model-00002-of-00004.safetensors",
|
| 345 |
+
"language_model.model.layers.10.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
| 346 |
+
"language_model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
|
| 347 |
+
"language_model.model.layers.10.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 348 |
+
"language_model.model.layers.10.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
| 349 |
+
"language_model.model.layers.10.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
| 350 |
+
"language_model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
| 351 |
+
"language_model.model.layers.11.attention.wo.weight": "model-00002-of-00004.safetensors",
|
| 352 |
+
"language_model.model.layers.11.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
| 353 |
+
"language_model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
|
| 354 |
+
"language_model.model.layers.11.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 355 |
+
"language_model.model.layers.11.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
| 356 |
+
"language_model.model.layers.11.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
| 357 |
+
"language_model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
| 358 |
+
"language_model.model.layers.12.attention.wo.weight": "model-00002-of-00004.safetensors",
|
| 359 |
+
"language_model.model.layers.12.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
| 360 |
+
"language_model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
|
| 361 |
+
"language_model.model.layers.12.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 362 |
+
"language_model.model.layers.12.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
| 363 |
+
"language_model.model.layers.12.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
| 364 |
+
"language_model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
| 365 |
+
"language_model.model.layers.13.attention.wo.weight": "model-00002-of-00004.safetensors",
|
| 366 |
+
"language_model.model.layers.13.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
| 367 |
+
"language_model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
|
| 368 |
+
"language_model.model.layers.13.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 369 |
+
"language_model.model.layers.13.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
| 370 |
+
"language_model.model.layers.13.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
| 371 |
+
"language_model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
| 372 |
+
"language_model.model.layers.14.attention.wo.weight": "model-00002-of-00004.safetensors",
|
| 373 |
+
"language_model.model.layers.14.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"language_model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"language_model.model.layers.14.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"language_model.model.layers.14.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"language_model.model.layers.14.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"language_model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"language_model.model.layers.15.attention.wo.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"language_model.model.layers.15.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"language_model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
|
| 382 |
+
"language_model.model.layers.15.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 383 |
+
"language_model.model.layers.15.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
| 384 |
+
"language_model.model.layers.15.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
| 385 |
+
"language_model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
| 386 |
+
"language_model.model.layers.16.attention.wo.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"language_model.model.layers.16.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
| 388 |
+
"language_model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"language_model.model.layers.16.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"language_model.model.layers.16.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
| 391 |
+
"language_model.model.layers.16.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
| 392 |
+
"language_model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"language_model.model.layers.17.attention.wo.weight": "model-00002-of-00004.safetensors",
|
| 394 |
+
"language_model.model.layers.17.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"language_model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"language_model.model.layers.17.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"language_model.model.layers.17.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"language_model.model.layers.17.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"language_model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"language_model.model.layers.18.attention.wo.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"language_model.model.layers.18.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
| 402 |
+
"language_model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"language_model.model.layers.18.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"language_model.model.layers.18.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
| 405 |
+
"language_model.model.layers.18.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
| 406 |
+
"language_model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
| 407 |
+
"language_model.model.layers.19.attention.wo.weight": "model-00002-of-00004.safetensors",
|
| 408 |
+
"language_model.model.layers.19.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
| 409 |
+
"language_model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
|
| 410 |
+
"language_model.model.layers.19.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 411 |
+
"language_model.model.layers.19.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
| 412 |
+
"language_model.model.layers.19.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 413 |
+
"language_model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
| 414 |
+
"language_model.model.layers.2.attention.wo.weight": "model-00001-of-00004.safetensors",
|
| 415 |
+
"language_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"language_model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
|
| 417 |
+
"language_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
| 418 |
+
"language_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
| 419 |
+
"language_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
| 420 |
+
"language_model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
| 421 |
+
"language_model.model.layers.20.attention.wo.weight": "model-00003-of-00004.safetensors",
|
| 422 |
+
"language_model.model.layers.20.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
| 423 |
+
"language_model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
|
| 424 |
+
"language_model.model.layers.20.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
| 425 |
+
"language_model.model.layers.20.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
| 426 |
+
"language_model.model.layers.20.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 427 |
+
"language_model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
| 428 |
+
"language_model.model.layers.21.attention.wo.weight": "model-00003-of-00004.safetensors",
|
| 429 |
+
"language_model.model.layers.21.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
| 430 |
+
"language_model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
|
| 431 |
+
"language_model.model.layers.21.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
| 432 |
+
"language_model.model.layers.21.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
| 433 |
+
"language_model.model.layers.21.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 434 |
+
"language_model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
| 435 |
+
"language_model.model.layers.22.attention.wo.weight": "model-00003-of-00004.safetensors",
|
| 436 |
+
"language_model.model.layers.22.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
| 437 |
+
"language_model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
|
| 438 |
+
"language_model.model.layers.22.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
| 439 |
+
"language_model.model.layers.22.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
| 440 |
+
"language_model.model.layers.22.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 441 |
+
"language_model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
| 442 |
+
"language_model.model.layers.23.attention.wo.weight": "model-00003-of-00004.safetensors",
|
| 443 |
+
"language_model.model.layers.23.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
| 444 |
+
"language_model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
|
| 445 |
+
"language_model.model.layers.23.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
| 446 |
+
"language_model.model.layers.23.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
| 447 |
+
"language_model.model.layers.23.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 448 |
+
"language_model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
| 449 |
+
"language_model.model.layers.24.attention.wo.weight": "model-00003-of-00004.safetensors",
|
| 450 |
+
"language_model.model.layers.24.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
| 451 |
+
"language_model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
|
| 452 |
+
"language_model.model.layers.24.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
| 453 |
+
"language_model.model.layers.24.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
| 454 |
+
"language_model.model.layers.24.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 455 |
+
"language_model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
| 456 |
+
"language_model.model.layers.25.attention.wo.weight": "model-00003-of-00004.safetensors",
|
| 457 |
+
"language_model.model.layers.25.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
| 458 |
+
"language_model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
|
| 459 |
+
"language_model.model.layers.25.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
| 460 |
+
"language_model.model.layers.25.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
| 461 |
+
"language_model.model.layers.25.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 462 |
+
"language_model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
| 463 |
+
"language_model.model.layers.26.attention.wo.weight": "model-00003-of-00004.safetensors",
|
| 464 |
+
"language_model.model.layers.26.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
| 465 |
+
"language_model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
|
| 466 |
+
"language_model.model.layers.26.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
| 467 |
+
"language_model.model.layers.26.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
| 468 |
+
"language_model.model.layers.26.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 469 |
+
"language_model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
| 470 |
+
"language_model.model.layers.27.attention.wo.weight": "model-00003-of-00004.safetensors",
|
| 471 |
+
"language_model.model.layers.27.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
| 472 |
+
"language_model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
|
| 473 |
+
"language_model.model.layers.27.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
| 474 |
+
"language_model.model.layers.27.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
| 475 |
+
"language_model.model.layers.27.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 476 |
+
"language_model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
| 477 |
+
"language_model.model.layers.28.attention.wo.weight": "model-00003-of-00004.safetensors",
|
| 478 |
+
"language_model.model.layers.28.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
| 479 |
+
"language_model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
|
| 480 |
+
"language_model.model.layers.28.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
| 481 |
+
"language_model.model.layers.28.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
| 482 |
+
"language_model.model.layers.28.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 483 |
+
"language_model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
| 484 |
+
"language_model.model.layers.29.attention.wo.weight": "model-00003-of-00004.safetensors",
|
| 485 |
+
"language_model.model.layers.29.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
| 486 |
+
"language_model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
|
| 487 |
+
"language_model.model.layers.29.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
| 488 |
+
"language_model.model.layers.29.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
|
| 489 |
+
"language_model.model.layers.29.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 490 |
+
"language_model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
|
| 491 |
+
"language_model.model.layers.3.attention.wo.weight": "model-00001-of-00004.safetensors",
|
| 492 |
+
"language_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
| 493 |
+
"language_model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
|
| 494 |
+
"language_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
| 495 |
+
"language_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
| 496 |
+
"language_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
| 497 |
+
"language_model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
| 498 |
+
"language_model.model.layers.30.attention.wo.weight": "model-00003-of-00004.safetensors",
|
| 499 |
+
"language_model.model.layers.30.attention.wqkv.weight": "model-00003-of-00004.safetensors",
|
| 500 |
+
"language_model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
|
| 501 |
+
"language_model.model.layers.30.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
|
| 502 |
+
"language_model.model.layers.30.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
|
| 503 |
+
"language_model.model.layers.30.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
|
| 504 |
+
"language_model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
|
| 505 |
+
"language_model.model.layers.31.attention.wo.weight": "model-00004-of-00004.safetensors",
|
| 506 |
+
"language_model.model.layers.31.attention.wqkv.weight": "model-00004-of-00004.safetensors",
|
| 507 |
+
"language_model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
|
| 508 |
+
"language_model.model.layers.31.feed_forward.w1.weight": "model-00004-of-00004.safetensors",
|
| 509 |
+
"language_model.model.layers.31.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
|
| 510 |
+
"language_model.model.layers.31.feed_forward.w3.weight": "model-00004-of-00004.safetensors",
|
| 511 |
+
"language_model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
|
| 512 |
+
"language_model.model.layers.4.attention.wo.weight": "model-00001-of-00004.safetensors",
|
| 513 |
+
"language_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
| 514 |
+
"language_model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
|
| 515 |
+
"language_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
| 516 |
+
"language_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
| 517 |
+
"language_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
| 518 |
+
"language_model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
| 519 |
+
"language_model.model.layers.5.attention.wo.weight": "model-00001-of-00004.safetensors",
|
| 520 |
+
"language_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
| 521 |
+
"language_model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
|
| 522 |
+
"language_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
| 523 |
+
"language_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
| 524 |
+
"language_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
| 525 |
+
"language_model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
| 526 |
+
"language_model.model.layers.6.attention.wo.weight": "model-00001-of-00004.safetensors",
|
| 527 |
+
"language_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
| 528 |
+
"language_model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
|
| 529 |
+
"language_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
| 530 |
+
"language_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
| 531 |
+
"language_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
| 532 |
+
"language_model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
| 533 |
+
"language_model.model.layers.7.attention.wo.weight": "model-00001-of-00004.safetensors",
|
| 534 |
+
"language_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
| 535 |
+
"language_model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
|
| 536 |
+
"language_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
|
| 537 |
+
"language_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
|
| 538 |
+
"language_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
|
| 539 |
+
"language_model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
|
| 540 |
+
"language_model.model.layers.8.attention.wo.weight": "model-00001-of-00004.safetensors",
|
| 541 |
+
"language_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00004.safetensors",
|
| 542 |
+
"language_model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
|
| 543 |
+
"language_model.model.layers.8.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 544 |
+
"language_model.model.layers.8.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
| 545 |
+
"language_model.model.layers.8.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
| 546 |
+
"language_model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
| 547 |
+
"language_model.model.layers.9.attention.wo.weight": "model-00002-of-00004.safetensors",
|
| 548 |
+
"language_model.model.layers.9.attention.wqkv.weight": "model-00002-of-00004.safetensors",
|
| 549 |
+
"language_model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
|
| 550 |
+
"language_model.model.layers.9.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
|
| 551 |
+
"language_model.model.layers.9.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
|
| 552 |
+
"language_model.model.layers.9.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
|
| 553 |
+
"language_model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
|
| 554 |
+
"language_model.model.norm.weight": "model-00004-of-00004.safetensors",
|
| 555 |
+
"language_model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
|
| 556 |
+
"language_model.output.weight": "model-00004-of-00004.safetensors",
|
| 557 |
+
"lvl_embed.weight": "model-00004-of-00004.safetensors",
|
| 558 |
+
"mlp1.0.bias": "model-00004-of-00004.safetensors",
|
| 559 |
+
"mlp1.0.weight": "model-00004-of-00004.safetensors",
|
| 560 |
+
"mlp1.1.bias": "model-00004-of-00004.safetensors",
|
| 561 |
+
"mlp1.1.weight": "model-00004-of-00004.safetensors",
|
| 562 |
+
"mlp1.3.bias": "model-00004-of-00004.safetensors",
|
| 563 |
+
"mlp1.3.weight": "model-00004-of-00004.safetensors",
|
| 564 |
+
"pos_1LC": "model-00001-of-00004.safetensors",
|
| 565 |
+
"vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
|
| 566 |
+
"vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
|
| 567 |
+
"vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
|
| 568 |
+
"vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
|
| 569 |
+
"vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 570 |
+
"vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 571 |
+
"vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 572 |
+
"vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 573 |
+
"vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
|
| 574 |
+
"vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
|
| 575 |
+
"vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 576 |
+
"vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 577 |
+
"vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 578 |
+
"vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 579 |
+
"vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
|
| 580 |
+
"vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 581 |
+
"vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
|
| 582 |
+
"vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 583 |
+
"vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 584 |
+
"vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 585 |
+
"vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 586 |
+
"vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 587 |
+
"vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
|
| 588 |
+
"vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
|
| 589 |
+
"vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 590 |
+
"vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 591 |
+
"vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 592 |
+
"vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 593 |
+
"vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
|
| 594 |
+
"vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 595 |
+
"vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
|
| 596 |
+
"vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 597 |
+
"vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 598 |
+
"vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 599 |
+
"vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 600 |
+
"vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 601 |
+
"vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
|
| 602 |
+
"vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
|
| 603 |
+
"vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 604 |
+
"vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 605 |
+
"vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 606 |
+
"vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 607 |
+
"vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
|
| 608 |
+
"vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 609 |
+
"vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
|
| 610 |
+
"vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 611 |
+
"vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 612 |
+
"vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 613 |
+
"vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 614 |
+
"vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 615 |
+
"vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
|
| 616 |
+
"vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
|
| 617 |
+
"vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 618 |
+
"vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 619 |
+
"vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 620 |
+
"vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 621 |
+
"vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
|
| 622 |
+
"vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 623 |
+
"vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
|
| 624 |
+
"vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 625 |
+
"vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 626 |
+
"vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 627 |
+
"vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 628 |
+
"vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 629 |
+
"vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
|
| 630 |
+
"vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
|
| 631 |
+
"vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 632 |
+
"vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 633 |
+
"vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 634 |
+
"vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 635 |
+
"vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
|
| 636 |
+
"vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 637 |
+
"vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
|
| 638 |
+
"vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 639 |
+
"vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 640 |
+
"vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 641 |
+
"vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 642 |
+
"vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 643 |
+
"vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
|
| 644 |
+
"vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
|
| 645 |
+
"vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 646 |
+
"vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 647 |
+
"vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 648 |
+
"vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 649 |
+
"vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
|
| 650 |
+
"vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 651 |
+
"vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
|
| 652 |
+
"vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 653 |
+
"vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 654 |
+
"vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 655 |
+
"vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 656 |
+
"vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 657 |
+
"vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
|
| 658 |
+
"vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
|
| 659 |
+
"vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 660 |
+
"vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 661 |
+
"vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 662 |
+
"vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 663 |
+
"vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
|
| 664 |
+
"vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 665 |
+
"vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
|
| 666 |
+
"vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 667 |
+
"vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 668 |
+
"vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 669 |
+
"vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 670 |
+
"vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 671 |
+
"vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
|
| 672 |
+
"vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
|
| 673 |
+
"vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 674 |
+
"vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 675 |
+
"vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 676 |
+
"vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 677 |
+
"vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
|
| 678 |
+
"vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 679 |
+
"vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
|
| 680 |
+
"vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 681 |
+
"vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 682 |
+
"vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 683 |
+
"vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 684 |
+
"vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 685 |
+
"vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
|
| 686 |
+
"vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
|
| 687 |
+
"vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 688 |
+
"vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 689 |
+
"vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 690 |
+
"vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 691 |
+
"vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
|
| 692 |
+
"vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 693 |
+
"vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
|
| 694 |
+
"vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 695 |
+
"vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 696 |
+
"vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 697 |
+
"vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 698 |
+
"vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 699 |
+
"vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
|
| 700 |
+
"vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
|
| 701 |
+
"vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 702 |
+
"vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 703 |
+
"vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 704 |
+
"vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 705 |
+
"vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
|
| 706 |
+
"vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 707 |
+
"vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
|
| 708 |
+
"vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 709 |
+
"vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 710 |
+
"vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 711 |
+
"vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 712 |
+
"vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 713 |
+
"vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
|
| 714 |
+
"vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
|
| 715 |
+
"vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 716 |
+
"vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 717 |
+
"vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 718 |
+
"vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 719 |
+
"vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
|
| 720 |
+
"vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 721 |
+
"vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
|
| 722 |
+
"vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 723 |
+
"vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 724 |
+
"vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 725 |
+
"vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 726 |
+
"vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 727 |
+
"vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
|
| 728 |
+
"vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
|
| 729 |
+
"vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 730 |
+
"vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 731 |
+
"vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 732 |
+
"vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 733 |
+
"vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
|
| 734 |
+
"vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 735 |
+
"vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
|
| 736 |
+
"vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 737 |
+
"vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 738 |
+
"vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 739 |
+
"vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 740 |
+
"vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 741 |
+
"vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
|
| 742 |
+
"vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
|
| 743 |
+
"vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 744 |
+
"vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 745 |
+
"vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 746 |
+
"vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 747 |
+
"vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
|
| 748 |
+
"vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 749 |
+
"vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
|
| 750 |
+
"vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 751 |
+
"vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 752 |
+
"vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 753 |
+
"vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 754 |
+
"vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 755 |
+
"vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
|
| 756 |
+
"vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
|
| 757 |
+
"vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 758 |
+
"vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 759 |
+
"vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 760 |
+
"vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 761 |
+
"vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
|
| 762 |
+
"vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 763 |
+
"vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
|
| 764 |
+
"vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 765 |
+
"vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 766 |
+
"vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 767 |
+
"vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 768 |
+
"vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 769 |
+
"vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
|
| 770 |
+
"vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
|
| 771 |
+
"vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 772 |
+
"vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 773 |
+
"vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 774 |
+
"vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 775 |
+
"vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
|
| 776 |
+
"vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 777 |
+
"vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
|
| 778 |
+
"vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 779 |
+
"vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 780 |
+
"vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 781 |
+
"vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 782 |
+
"vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 783 |
+
"vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
|
| 784 |
+
"vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
|
| 785 |
+
"vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 786 |
+
"vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 787 |
+
"vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 788 |
+
"vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 789 |
+
"vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
|
| 790 |
+
"vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 791 |
+
"vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
|
| 792 |
+
"vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 793 |
+
"vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 794 |
+
"vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 795 |
+
"vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 796 |
+
"vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 797 |
+
"vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
|
| 798 |
+
"vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
|
| 799 |
+
"vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 800 |
+
"vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 801 |
+
"vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 802 |
+
"vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 803 |
+
"vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
|
| 804 |
+
"vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 805 |
+
"vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
|
| 806 |
+
"vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 807 |
+
"vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 808 |
+
"vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 809 |
+
"vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 810 |
+
"vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 811 |
+
"vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
|
| 812 |
+
"vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
|
| 813 |
+
"vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 814 |
+
"vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 815 |
+
"vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 816 |
+
"vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 817 |
+
"vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
|
| 818 |
+
"vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 819 |
+
"vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
|
| 820 |
+
"vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 821 |
+
"vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 822 |
+
"vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 823 |
+
"vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 824 |
+
"vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 825 |
+
"vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
|
| 826 |
+
"vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
|
| 827 |
+
"vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 828 |
+
"vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 829 |
+
"vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 830 |
+
"vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 831 |
+
"vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
|
| 832 |
+
"vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 833 |
+
"vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
|
| 834 |
+
"vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 835 |
+
"vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 836 |
+
"vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 837 |
+
"vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 838 |
+
"vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 839 |
+
"vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
|
| 840 |
+
"vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
|
| 841 |
+
"vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 842 |
+
"vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 843 |
+
"vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 844 |
+
"vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 845 |
+
"vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
|
| 846 |
+
"vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 847 |
+
"vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
|
| 848 |
+
"vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 849 |
+
"vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 850 |
+
"vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 851 |
+
"vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 852 |
+
"vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 853 |
+
"vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
|
| 854 |
+
"vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
|
| 855 |
+
"vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 856 |
+
"vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 857 |
+
"vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 858 |
+
"vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 859 |
+
"vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
|
| 860 |
+
"vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 861 |
+
"vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
|
| 862 |
+
"vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 863 |
+
"vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 864 |
+
"vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 865 |
+
"vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 866 |
+
"vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 867 |
+
"vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
|
| 868 |
+
"vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
|
| 869 |
+
"vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 870 |
+
"vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 871 |
+
"vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 872 |
+
"vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 873 |
+
"vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
|
| 874 |
+
"vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 875 |
+
"vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
|
| 876 |
+
"vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 877 |
+
"vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 878 |
+
"vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 879 |
+
"vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 880 |
+
"vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 881 |
+
"vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
|
| 882 |
+
"vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
|
| 883 |
+
"vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 884 |
+
"vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 885 |
+
"vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 886 |
+
"vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 887 |
+
"vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
|
| 888 |
+
"vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 889 |
+
"vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
|
| 890 |
+
"vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 891 |
+
"vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 892 |
+
"vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 893 |
+
"vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 894 |
+
"vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 895 |
+
"vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
|
| 896 |
+
"vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
|
| 897 |
+
"vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
|
| 898 |
+
"vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
|
| 899 |
+
"vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
|
| 900 |
+
"vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
|
| 901 |
+
"vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
|
| 902 |
+
"vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 903 |
+
"vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
|
| 904 |
+
"vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 905 |
+
"word_embed.bias": "model-00004-of-00004.safetensors",
|
| 906 |
+
"word_embed.weight": "model-00004-of-00004.safetensors"
|
| 907 |
+
}
|
| 908 |
+
}
|
special_tokens_map.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenization_internlm2.py
ADDED
|
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
|
| 2 |
+
#
|
| 3 |
+
# This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
|
| 4 |
+
#
|
| 5 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
| 6 |
+
# you may not use this file except in compliance with the License.
|
| 7 |
+
# You may obtain a copy of the License at
|
| 8 |
+
#
|
| 9 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
| 10 |
+
#
|
| 11 |
+
# Unless required by applicable law or agreed to in writing, software
|
| 12 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
| 13 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 14 |
+
# See the License for the specific language governing permissions and
|
| 15 |
+
# limitations under the License.
|
| 16 |
+
|
| 17 |
+
"""Tokenization classes for InternLM."""
|
| 18 |
+
import os
|
| 19 |
+
from shutil import copyfile
|
| 20 |
+
from typing import Any, Dict, List, Optional, Tuple
|
| 21 |
+
|
| 22 |
+
import sentencepiece as spm
|
| 23 |
+
from transformers.tokenization_utils import PreTrainedTokenizer
|
| 24 |
+
from transformers.utils import logging
|
| 25 |
+
|
| 26 |
+
logger = logging.get_logger(__name__)
|
| 27 |
+
|
| 28 |
+
VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
|
| 29 |
+
|
| 30 |
+
PRETRAINED_VOCAB_FILES_MAP = {}
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
# Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
|
| 34 |
+
class InternLM2Tokenizer(PreTrainedTokenizer):
|
| 35 |
+
"""
|
| 36 |
+
Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
|
| 37 |
+
|
| 38 |
+
Args:
|
| 39 |
+
vocab_file (`str`):
|
| 40 |
+
Path to the vocabulary file.
|
| 41 |
+
"""
|
| 42 |
+
|
| 43 |
+
vocab_files_names = VOCAB_FILES_NAMES
|
| 44 |
+
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
|
| 45 |
+
model_input_names = ['input_ids', 'attention_mask']
|
| 46 |
+
_auto_class = 'AutoTokenizer'
|
| 47 |
+
|
| 48 |
+
def __init__(
|
| 49 |
+
self,
|
| 50 |
+
vocab_file,
|
| 51 |
+
unk_token='<unk>',
|
| 52 |
+
bos_token='<s>',
|
| 53 |
+
eos_token='</s>',
|
| 54 |
+
pad_token='</s>',
|
| 55 |
+
sp_model_kwargs: Optional[Dict[str, Any]] = None,
|
| 56 |
+
add_bos_token=True,
|
| 57 |
+
add_eos_token=False,
|
| 58 |
+
decode_with_prefix_space=False,
|
| 59 |
+
clean_up_tokenization_spaces=False,
|
| 60 |
+
**kwargs,
|
| 61 |
+
):
|
| 62 |
+
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
|
| 63 |
+
self.vocab_file = vocab_file
|
| 64 |
+
self.add_bos_token = add_bos_token
|
| 65 |
+
self.add_eos_token = add_eos_token
|
| 66 |
+
self.decode_with_prefix_space = decode_with_prefix_space
|
| 67 |
+
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
|
| 68 |
+
self.sp_model.Load(vocab_file)
|
| 69 |
+
self._no_prefix_space_tokens = None
|
| 70 |
+
super().__init__(
|
| 71 |
+
bos_token=bos_token,
|
| 72 |
+
eos_token=eos_token,
|
| 73 |
+
unk_token=unk_token,
|
| 74 |
+
pad_token=pad_token,
|
| 75 |
+
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
|
| 76 |
+
**kwargs,
|
| 77 |
+
)
|
| 78 |
+
|
| 79 |
+
@property
|
| 80 |
+
def no_prefix_space_tokens(self):
|
| 81 |
+
if self._no_prefix_space_tokens is None:
|
| 82 |
+
vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
|
| 83 |
+
self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
|
| 84 |
+
return self._no_prefix_space_tokens
|
| 85 |
+
|
| 86 |
+
@property
|
| 87 |
+
def vocab_size(self):
|
| 88 |
+
"""Returns vocab size"""
|
| 89 |
+
return self.sp_model.get_piece_size()
|
| 90 |
+
|
| 91 |
+
@property
|
| 92 |
+
def bos_token_id(self) -> Optional[int]:
|
| 93 |
+
return self.sp_model.bos_id()
|
| 94 |
+
|
| 95 |
+
@property
|
| 96 |
+
def eos_token_id(self) -> Optional[int]:
|
| 97 |
+
return self.sp_model.eos_id()
|
| 98 |
+
|
| 99 |
+
def get_vocab(self):
|
| 100 |
+
"""Returns vocab as a dict"""
|
| 101 |
+
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
|
| 102 |
+
vocab.update(self.added_tokens_encoder)
|
| 103 |
+
return vocab
|
| 104 |
+
|
| 105 |
+
def _tokenize(self, text):
|
| 106 |
+
"""Returns a tokenized string."""
|
| 107 |
+
return self.sp_model.encode(text, out_type=str)
|
| 108 |
+
|
| 109 |
+
def _convert_token_to_id(self, token):
|
| 110 |
+
"""Converts a token (str) in an id using the vocab."""
|
| 111 |
+
return self.sp_model.piece_to_id(token)
|
| 112 |
+
|
| 113 |
+
def _convert_id_to_token(self, index):
|
| 114 |
+
"""Converts an index (integer) in a token (str) using the vocab."""
|
| 115 |
+
token = self.sp_model.IdToPiece(index)
|
| 116 |
+
return token
|
| 117 |
+
|
| 118 |
+
def _maybe_add_prefix_space(self, tokens, decoded):
|
| 119 |
+
if tokens and tokens[0] not in self.no_prefix_space_tokens:
|
| 120 |
+
return ' ' + decoded
|
| 121 |
+
else:
|
| 122 |
+
return decoded
|
| 123 |
+
|
| 124 |
+
def convert_tokens_to_string(self, tokens):
|
| 125 |
+
"""Converts a sequence of tokens (string) in a single string."""
|
| 126 |
+
current_sub_tokens = []
|
| 127 |
+
out_string = ''
|
| 128 |
+
prev_is_special = False
|
| 129 |
+
for token in tokens:
|
| 130 |
+
# make sure that special tokens are not decoded using sentencepiece model
|
| 131 |
+
if token in self.all_special_tokens:
|
| 132 |
+
if not prev_is_special:
|
| 133 |
+
out_string += ' '
|
| 134 |
+
out_string += self.sp_model.decode(current_sub_tokens) + token
|
| 135 |
+
prev_is_special = True
|
| 136 |
+
current_sub_tokens = []
|
| 137 |
+
else:
|
| 138 |
+
current_sub_tokens.append(token)
|
| 139 |
+
prev_is_special = False
|
| 140 |
+
out_string += self.sp_model.decode(current_sub_tokens)
|
| 141 |
+
out_string = self.clean_up_tokenization(out_string)
|
| 142 |
+
out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
|
| 143 |
+
return out_string[1:]
|
| 144 |
+
|
| 145 |
+
def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
|
| 146 |
+
"""
|
| 147 |
+
Save the vocabulary and special tokens file to a directory.
|
| 148 |
+
|
| 149 |
+
Args:
|
| 150 |
+
save_directory (`str`):
|
| 151 |
+
The directory in which to save the vocabulary.
|
| 152 |
+
|
| 153 |
+
Returns:
|
| 154 |
+
`Tuple(str)`: Paths to the files saved.
|
| 155 |
+
"""
|
| 156 |
+
if not os.path.isdir(save_directory):
|
| 157 |
+
logger.error(f'Vocabulary path ({save_directory}) should be a directory')
|
| 158 |
+
return
|
| 159 |
+
out_vocab_file = os.path.join(
|
| 160 |
+
save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
|
| 161 |
+
)
|
| 162 |
+
|
| 163 |
+
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
|
| 164 |
+
copyfile(self.vocab_file, out_vocab_file)
|
| 165 |
+
elif not os.path.isfile(self.vocab_file):
|
| 166 |
+
with open(out_vocab_file, 'wb') as fi:
|
| 167 |
+
content_spiece_model = self.sp_model.serialized_model_proto()
|
| 168 |
+
fi.write(content_spiece_model)
|
| 169 |
+
|
| 170 |
+
return (out_vocab_file,)
|
| 171 |
+
|
| 172 |
+
def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
|
| 173 |
+
if self.add_bos_token:
|
| 174 |
+
bos_token_ids = [self.bos_token_id]
|
| 175 |
+
else:
|
| 176 |
+
bos_token_ids = []
|
| 177 |
+
|
| 178 |
+
output = bos_token_ids + token_ids_0
|
| 179 |
+
|
| 180 |
+
if token_ids_1 is not None:
|
| 181 |
+
output = output + token_ids_1
|
| 182 |
+
|
| 183 |
+
if self.add_eos_token:
|
| 184 |
+
output = output + [self.eos_token_id]
|
| 185 |
+
|
| 186 |
+
return output
|
| 187 |
+
|
| 188 |
+
def get_special_tokens_mask(
|
| 189 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
|
| 190 |
+
) -> List[int]:
|
| 191 |
+
"""
|
| 192 |
+
Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
|
| 193 |
+
special tokens using the tokenizer `prepare_for_model` method.
|
| 194 |
+
|
| 195 |
+
Args:
|
| 196 |
+
token_ids_0 (`List[int]`):
|
| 197 |
+
List of IDs.
|
| 198 |
+
token_ids_1 (`List[int]`, *optional*):
|
| 199 |
+
Optional second list of IDs for sequence pairs.
|
| 200 |
+
already_has_special_tokens (`bool`, *optional*, defaults to `False`):
|
| 201 |
+
Whether or not the token list is already formatted with special tokens for the model.
|
| 202 |
+
|
| 203 |
+
Returns:
|
| 204 |
+
`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
|
| 205 |
+
"""
|
| 206 |
+
if already_has_special_tokens:
|
| 207 |
+
return super().get_special_tokens_mask(
|
| 208 |
+
token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
|
| 209 |
+
)
|
| 210 |
+
|
| 211 |
+
if token_ids_1 is None:
|
| 212 |
+
return [1] + ([0] * len(token_ids_0)) + [1]
|
| 213 |
+
return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
|
| 214 |
+
|
| 215 |
+
def create_token_type_ids_from_sequences(
|
| 216 |
+
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
|
| 217 |
+
) -> List[int]:
|
| 218 |
+
"""
|
| 219 |
+
Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
|
| 220 |
+
use of token type ids, therefore a list of zeros is returned.
|
| 221 |
+
|
| 222 |
+
Args:
|
| 223 |
+
token_ids_0 (`List[int]`):
|
| 224 |
+
List of IDs.
|
| 225 |
+
token_ids_1 (`List[int]`, *optional*):
|
| 226 |
+
Optional second list of IDs for sequence pairs.
|
| 227 |
+
|
| 228 |
+
Returns:
|
| 229 |
+
`List[int]`: List of zeros.
|
| 230 |
+
"""
|
| 231 |
+
eos = [self.eos_token_id]
|
| 232 |
+
|
| 233 |
+
if token_ids_1 is None:
|
| 234 |
+
return len(token_ids_0 + eos) * [0]
|
| 235 |
+
return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
|
| 3 |
+
size 1477754
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|