Add OmniParser icon_caption converted to MLX (bf16), MIT
Browse files- LICENSE +21 -0
- README.md +34 -0
- config.json +246 -0
- generation_config.json +13 -0
- model.safetensors +3 -0
- model.safetensors.index.json +673 -0
- preprocessor_config.json +44 -0
- processor_config.json +32 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
- vocab.json +0 -0
LICENSE
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
MIT License
|
| 2 |
+
|
| 3 |
+
Copyright (c) Microsoft Corporation.
|
| 4 |
+
|
| 5 |
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
| 6 |
+
of this software and associated documentation files (the "Software"), to deal
|
| 7 |
+
in the Software without restriction, including without limitation the rights
|
| 8 |
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
| 9 |
+
copies of the Software, and to permit persons to whom the Software is
|
| 10 |
+
furnished to do so, subject to the following conditions:
|
| 11 |
+
|
| 12 |
+
The above copyright notice and this permission notice shall be included in all
|
| 13 |
+
copies or substantial portions of the Software.
|
| 14 |
+
|
| 15 |
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
| 16 |
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
| 17 |
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
| 18 |
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
| 19 |
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
| 20 |
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
| 21 |
+
SOFTWARE
|
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: mlx
|
| 4 |
+
tags:
|
| 5 |
+
- mlx
|
| 6 |
+
- florence2
|
| 7 |
+
- omniparser
|
| 8 |
+
- ui
|
| 9 |
+
- apple-silicon
|
| 10 |
+
base_model: microsoft/OmniParser-v2.0
|
| 11 |
+
pipeline_tag: image-text-to-text
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# OmniParser icon_caption — MLX
|
| 15 |
+
|
| 16 |
+
**MLX (bfloat16) conversion of [microsoft/OmniParser-v2.0](https://huggingface.co/microsoft/OmniParser-v2.0)'s `icon_caption`** — a Florence-2 fine-tuned on UI elements, for captioning interactive icons in screenshots. Runs on Apple Silicon via `mlx_vlm` with **no PyTorch**.
|
| 17 |
+
|
| 18 |
+
License: **MIT** (© Microsoft Corporation) — see `LICENSE`. This repo redistributes the original MIT-licensed weights converted to MLX format.
|
| 19 |
+
|
| 20 |
+
## Usage
|
| 21 |
+
|
| 22 |
+
Needs a small no-torch patch on transformers 5.x (register `florence2_language`, route the image processor to `CLIPImageProcessorPil`). See the conversion recipe at the bottom.
|
| 23 |
+
|
| 24 |
+
```python
|
| 25 |
+
# apply the florence2 no-torch patch first (see recipe), then:
|
| 26 |
+
from mlx_vlm import load, generate
|
| 27 |
+
model, processor = load("PlusMinus1/omniparser-icon-caption-mlx")
|
| 28 |
+
out = generate(model, processor, "<CAPTION>", image=["icon_crop.png"], max_tokens=20)
|
| 29 |
+
```
|
| 30 |
+
|
| 31 |
+
## Provenance
|
| 32 |
+
- Base: microsoft/Florence-2-base (MIT)
|
| 33 |
+
- Fine-tune: microsoft/OmniParser-v2.0 `icon_caption` (MIT)
|
| 34 |
+
- Conversion: `mlx_vlm.convert` (bfloat16) + a transformers-5.x no-torch compatibility patch.
|
config.json
ADDED
|
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Florence2ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 2,
|
| 6 |
+
"eos_token_id": 1,
|
| 7 |
+
"generation_config": {
|
| 8 |
+
"_from_model_config": true,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"decoder_start_token_id": 2,
|
| 11 |
+
"early_stopping": true,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"forced_bos_token_id": 0,
|
| 14 |
+
"forced_eos_token_id": 2,
|
| 15 |
+
"no_repeat_ngram_size": 3,
|
| 16 |
+
"num_beams": 3,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"transformers_version": "4.46.1"
|
| 19 |
+
},
|
| 20 |
+
"ignore_index": -100,
|
| 21 |
+
"is_encoder_decoder": true,
|
| 22 |
+
"model_type": "florence2",
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"projection_dim": 768,
|
| 25 |
+
"text_config": {
|
| 26 |
+
"_attn_implementation_autoset": true,
|
| 27 |
+
"_name_or_path": "",
|
| 28 |
+
"activation_dropout": 0.1,
|
| 29 |
+
"activation_function": "gelu",
|
| 30 |
+
"add_bias_logits": false,
|
| 31 |
+
"add_cross_attention": false,
|
| 32 |
+
"add_final_layer_norm": false,
|
| 33 |
+
"architectures": null,
|
| 34 |
+
"attention_dropout": 0.1,
|
| 35 |
+
"bad_words_ids": null,
|
| 36 |
+
"begin_suppress_tokens": null,
|
| 37 |
+
"bos_token_id": 0,
|
| 38 |
+
"chunk_size_feed_forward": 0,
|
| 39 |
+
"classif_dropout": 0.1,
|
| 40 |
+
"classifier_dropout": 0.0,
|
| 41 |
+
"cross_attention_hidden_size": null,
|
| 42 |
+
"d_model": 768,
|
| 43 |
+
"decoder_attention_heads": 12,
|
| 44 |
+
"decoder_ffn_dim": 3072,
|
| 45 |
+
"decoder_layerdrop": 0.0,
|
| 46 |
+
"decoder_layers": 6,
|
| 47 |
+
"decoder_start_token_id": 2,
|
| 48 |
+
"diversity_penalty": 0.0,
|
| 49 |
+
"do_sample": false,
|
| 50 |
+
"dropout": 0.1,
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"encoder_attention_heads": 12,
|
| 53 |
+
"encoder_ffn_dim": 3072,
|
| 54 |
+
"encoder_layerdrop": 0.0,
|
| 55 |
+
"encoder_layers": 6,
|
| 56 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 57 |
+
"eos_token_id": 2,
|
| 58 |
+
"exponential_decay_length_penalty": null,
|
| 59 |
+
"finetuning_task": null,
|
| 60 |
+
"forced_bos_token_id": 0,
|
| 61 |
+
"forced_eos_token_id": 2,
|
| 62 |
+
"gradient_checkpointing": false,
|
| 63 |
+
"id2label": {
|
| 64 |
+
"0": "LABEL_0",
|
| 65 |
+
"1": "LABEL_1",
|
| 66 |
+
"2": "LABEL_2"
|
| 67 |
+
},
|
| 68 |
+
"init_std": 0.02,
|
| 69 |
+
"is_decoder": false,
|
| 70 |
+
"is_encoder_decoder": true,
|
| 71 |
+
"label2id": {
|
| 72 |
+
"LABEL_0": 0,
|
| 73 |
+
"LABEL_1": 1,
|
| 74 |
+
"LABEL_2": 2
|
| 75 |
+
},
|
| 76 |
+
"length_penalty": 1.0,
|
| 77 |
+
"max_length": 20,
|
| 78 |
+
"max_position_embeddings": 1024,
|
| 79 |
+
"min_length": 0,
|
| 80 |
+
"model_type": "florence2_language",
|
| 81 |
+
"no_repeat_ngram_size": 3,
|
| 82 |
+
"normalize_before": false,
|
| 83 |
+
"num_beam_groups": 1,
|
| 84 |
+
"num_beams": 3,
|
| 85 |
+
"num_hidden_layers": 6,
|
| 86 |
+
"num_return_sequences": 1,
|
| 87 |
+
"output_attentions": false,
|
| 88 |
+
"output_hidden_states": false,
|
| 89 |
+
"output_scores": false,
|
| 90 |
+
"pad_token_id": 1,
|
| 91 |
+
"prefix": null,
|
| 92 |
+
"problem_type": null,
|
| 93 |
+
"pruned_heads": {},
|
| 94 |
+
"remove_invalid_values": false,
|
| 95 |
+
"repetition_penalty": 1.0,
|
| 96 |
+
"return_dict": true,
|
| 97 |
+
"return_dict_in_generate": false,
|
| 98 |
+
"scale_embedding": false,
|
| 99 |
+
"sep_token_id": null,
|
| 100 |
+
"suppress_tokens": null,
|
| 101 |
+
"task_specific_params": null,
|
| 102 |
+
"temperature": 1.0,
|
| 103 |
+
"tf_legacy_loss": false,
|
| 104 |
+
"tie_encoder_decoder": false,
|
| 105 |
+
"tie_word_embeddings": true,
|
| 106 |
+
"tokenizer_class": null,
|
| 107 |
+
"top_k": 50,
|
| 108 |
+
"top_p": 1.0,
|
| 109 |
+
"torch_dtype": null,
|
| 110 |
+
"torchscript": false,
|
| 111 |
+
"typical_p": 1.0,
|
| 112 |
+
"use_bfloat16": false,
|
| 113 |
+
"use_cache": true,
|
| 114 |
+
"vocab_size": 51289
|
| 115 |
+
},
|
| 116 |
+
"transformers_version": "4.46.1",
|
| 117 |
+
"vision_config": {
|
| 118 |
+
"_attn_implementation_autoset": false,
|
| 119 |
+
"_name_or_path": "",
|
| 120 |
+
"add_cross_attention": false,
|
| 121 |
+
"architectures": null,
|
| 122 |
+
"bad_words_ids": null,
|
| 123 |
+
"begin_suppress_tokens": null,
|
| 124 |
+
"bos_token_id": null,
|
| 125 |
+
"chunk_size_feed_forward": 0,
|
| 126 |
+
"cross_attention_hidden_size": null,
|
| 127 |
+
"decoder_start_token_id": null,
|
| 128 |
+
"depths": [
|
| 129 |
+
1,
|
| 130 |
+
1,
|
| 131 |
+
9,
|
| 132 |
+
1
|
| 133 |
+
],
|
| 134 |
+
"dim_embed": [
|
| 135 |
+
128,
|
| 136 |
+
256,
|
| 137 |
+
512,
|
| 138 |
+
1024
|
| 139 |
+
],
|
| 140 |
+
"diversity_penalty": 0.0,
|
| 141 |
+
"do_sample": false,
|
| 142 |
+
"drop_path_rate": 0.1,
|
| 143 |
+
"early_stopping": false,
|
| 144 |
+
"enable_checkpoint": false,
|
| 145 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 146 |
+
"eos_token_id": null,
|
| 147 |
+
"exponential_decay_length_penalty": null,
|
| 148 |
+
"finetuning_task": null,
|
| 149 |
+
"forced_bos_token_id": null,
|
| 150 |
+
"forced_eos_token_id": null,
|
| 151 |
+
"id2label": {
|
| 152 |
+
"0": "LABEL_0",
|
| 153 |
+
"1": "LABEL_1"
|
| 154 |
+
},
|
| 155 |
+
"image_feature_source": [
|
| 156 |
+
"spatial_avg_pool",
|
| 157 |
+
"temporal_avg_pool"
|
| 158 |
+
],
|
| 159 |
+
"image_pos_embed": {
|
| 160 |
+
"max_pos_embeddings": 50,
|
| 161 |
+
"type": "learned_abs_2d"
|
| 162 |
+
},
|
| 163 |
+
"is_decoder": false,
|
| 164 |
+
"is_encoder_decoder": false,
|
| 165 |
+
"label2id": {
|
| 166 |
+
"LABEL_0": 0,
|
| 167 |
+
"LABEL_1": 1
|
| 168 |
+
},
|
| 169 |
+
"length_penalty": 1.0,
|
| 170 |
+
"max_length": 20,
|
| 171 |
+
"min_length": 0,
|
| 172 |
+
"model_type": "davit",
|
| 173 |
+
"no_repeat_ngram_size": 0,
|
| 174 |
+
"num_beam_groups": 1,
|
| 175 |
+
"num_beams": 1,
|
| 176 |
+
"num_groups": [
|
| 177 |
+
4,
|
| 178 |
+
8,
|
| 179 |
+
16,
|
| 180 |
+
32
|
| 181 |
+
],
|
| 182 |
+
"num_heads": [
|
| 183 |
+
4,
|
| 184 |
+
8,
|
| 185 |
+
16,
|
| 186 |
+
32
|
| 187 |
+
],
|
| 188 |
+
"num_return_sequences": 1,
|
| 189 |
+
"output_attentions": false,
|
| 190 |
+
"output_hidden_states": false,
|
| 191 |
+
"output_scores": false,
|
| 192 |
+
"pad_token_id": null,
|
| 193 |
+
"patch_padding": [
|
| 194 |
+
3,
|
| 195 |
+
1,
|
| 196 |
+
1,
|
| 197 |
+
1
|
| 198 |
+
],
|
| 199 |
+
"patch_prenorm": [
|
| 200 |
+
false,
|
| 201 |
+
true,
|
| 202 |
+
true,
|
| 203 |
+
true
|
| 204 |
+
],
|
| 205 |
+
"patch_size": [
|
| 206 |
+
7,
|
| 207 |
+
3,
|
| 208 |
+
3,
|
| 209 |
+
3
|
| 210 |
+
],
|
| 211 |
+
"patch_stride": [
|
| 212 |
+
4,
|
| 213 |
+
2,
|
| 214 |
+
2,
|
| 215 |
+
2
|
| 216 |
+
],
|
| 217 |
+
"prefix": null,
|
| 218 |
+
"problem_type": null,
|
| 219 |
+
"projection_dim": 768,
|
| 220 |
+
"pruned_heads": {},
|
| 221 |
+
"remove_invalid_values": false,
|
| 222 |
+
"repetition_penalty": 1.0,
|
| 223 |
+
"return_dict": true,
|
| 224 |
+
"return_dict_in_generate": false,
|
| 225 |
+
"sep_token_id": null,
|
| 226 |
+
"suppress_tokens": null,
|
| 227 |
+
"task_specific_params": null,
|
| 228 |
+
"temperature": 1.0,
|
| 229 |
+
"tf_legacy_loss": false,
|
| 230 |
+
"tie_encoder_decoder": false,
|
| 231 |
+
"tie_word_embeddings": true,
|
| 232 |
+
"tokenizer_class": null,
|
| 233 |
+
"top_k": 50,
|
| 234 |
+
"top_p": 1.0,
|
| 235 |
+
"torch_dtype": null,
|
| 236 |
+
"torchscript": false,
|
| 237 |
+
"typical_p": 1.0,
|
| 238 |
+
"use_bfloat16": false,
|
| 239 |
+
"visual_temporal_embedding": {
|
| 240 |
+
"max_temporal_embeddings": 100,
|
| 241 |
+
"type": "COSINE"
|
| 242 |
+
},
|
| 243 |
+
"window_size": 12
|
| 244 |
+
},
|
| 245 |
+
"vocab_size": 51289
|
| 246 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 1,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 3,
|
| 11 |
+
"pad_token_id": 0,
|
| 12 |
+
"transformers_version": "4.46.1"
|
| 13 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3d9242681e4af420ed4002f3bbb8d9b8246785a7575d29094bb1782e1a75368
|
| 3 |
+
size 541899275
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,673 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 541812736
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"image_pos_embed.column_embeddings.weight": "model.safetensors",
|
| 7 |
+
"image_pos_embed.row_embeddings.weight": "model.safetensors",
|
| 8 |
+
"image_proj_norm.bias": "model.safetensors",
|
| 9 |
+
"image_proj_norm.weight": "model.safetensors",
|
| 10 |
+
"image_projection": "model.safetensors",
|
| 11 |
+
"language_model.lm_head.weight": "model.safetensors",
|
| 12 |
+
"language_model.model.decoder.embed_positions.weight": "model.safetensors",
|
| 13 |
+
"language_model.model.decoder.layernorm_embedding.bias": "model.safetensors",
|
| 14 |
+
"language_model.model.decoder.layernorm_embedding.weight": "model.safetensors",
|
| 15 |
+
"language_model.model.decoder.layers.0.encoder_attn.k_proj.bias": "model.safetensors",
|
| 16 |
+
"language_model.model.decoder.layers.0.encoder_attn.k_proj.weight": "model.safetensors",
|
| 17 |
+
"language_model.model.decoder.layers.0.encoder_attn.out_proj.bias": "model.safetensors",
|
| 18 |
+
"language_model.model.decoder.layers.0.encoder_attn.out_proj.weight": "model.safetensors",
|
| 19 |
+
"language_model.model.decoder.layers.0.encoder_attn.q_proj.bias": "model.safetensors",
|
| 20 |
+
"language_model.model.decoder.layers.0.encoder_attn.q_proj.weight": "model.safetensors",
|
| 21 |
+
"language_model.model.decoder.layers.0.encoder_attn.v_proj.bias": "model.safetensors",
|
| 22 |
+
"language_model.model.decoder.layers.0.encoder_attn.v_proj.weight": "model.safetensors",
|
| 23 |
+
"language_model.model.decoder.layers.0.encoder_attn_layer_norm.bias": "model.safetensors",
|
| 24 |
+
"language_model.model.decoder.layers.0.encoder_attn_layer_norm.weight": "model.safetensors",
|
| 25 |
+
"language_model.model.decoder.layers.0.fc1.bias": "model.safetensors",
|
| 26 |
+
"language_model.model.decoder.layers.0.fc1.weight": "model.safetensors",
|
| 27 |
+
"language_model.model.decoder.layers.0.fc2.bias": "model.safetensors",
|
| 28 |
+
"language_model.model.decoder.layers.0.fc2.weight": "model.safetensors",
|
| 29 |
+
"language_model.model.decoder.layers.0.final_layer_norm.bias": "model.safetensors",
|
| 30 |
+
"language_model.model.decoder.layers.0.final_layer_norm.weight": "model.safetensors",
|
| 31 |
+
"language_model.model.decoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
|
| 32 |
+
"language_model.model.decoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 33 |
+
"language_model.model.decoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
|
| 34 |
+
"language_model.model.decoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
|
| 35 |
+
"language_model.model.decoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
|
| 36 |
+
"language_model.model.decoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 37 |
+
"language_model.model.decoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
|
| 38 |
+
"language_model.model.decoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 39 |
+
"language_model.model.decoder.layers.0.self_attn_layer_norm.bias": "model.safetensors",
|
| 40 |
+
"language_model.model.decoder.layers.0.self_attn_layer_norm.weight": "model.safetensors",
|
| 41 |
+
"language_model.model.decoder.layers.1.encoder_attn.k_proj.bias": "model.safetensors",
|
| 42 |
+
"language_model.model.decoder.layers.1.encoder_attn.k_proj.weight": "model.safetensors",
|
| 43 |
+
"language_model.model.decoder.layers.1.encoder_attn.out_proj.bias": "model.safetensors",
|
| 44 |
+
"language_model.model.decoder.layers.1.encoder_attn.out_proj.weight": "model.safetensors",
|
| 45 |
+
"language_model.model.decoder.layers.1.encoder_attn.q_proj.bias": "model.safetensors",
|
| 46 |
+
"language_model.model.decoder.layers.1.encoder_attn.q_proj.weight": "model.safetensors",
|
| 47 |
+
"language_model.model.decoder.layers.1.encoder_attn.v_proj.bias": "model.safetensors",
|
| 48 |
+
"language_model.model.decoder.layers.1.encoder_attn.v_proj.weight": "model.safetensors",
|
| 49 |
+
"language_model.model.decoder.layers.1.encoder_attn_layer_norm.bias": "model.safetensors",
|
| 50 |
+
"language_model.model.decoder.layers.1.encoder_attn_layer_norm.weight": "model.safetensors",
|
| 51 |
+
"language_model.model.decoder.layers.1.fc1.bias": "model.safetensors",
|
| 52 |
+
"language_model.model.decoder.layers.1.fc1.weight": "model.safetensors",
|
| 53 |
+
"language_model.model.decoder.layers.1.fc2.bias": "model.safetensors",
|
| 54 |
+
"language_model.model.decoder.layers.1.fc2.weight": "model.safetensors",
|
| 55 |
+
"language_model.model.decoder.layers.1.final_layer_norm.bias": "model.safetensors",
|
| 56 |
+
"language_model.model.decoder.layers.1.final_layer_norm.weight": "model.safetensors",
|
| 57 |
+
"language_model.model.decoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
|
| 58 |
+
"language_model.model.decoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 59 |
+
"language_model.model.decoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
|
| 60 |
+
"language_model.model.decoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
|
| 61 |
+
"language_model.model.decoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
|
| 62 |
+
"language_model.model.decoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 63 |
+
"language_model.model.decoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
|
| 64 |
+
"language_model.model.decoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 65 |
+
"language_model.model.decoder.layers.1.self_attn_layer_norm.bias": "model.safetensors",
|
| 66 |
+
"language_model.model.decoder.layers.1.self_attn_layer_norm.weight": "model.safetensors",
|
| 67 |
+
"language_model.model.decoder.layers.2.encoder_attn.k_proj.bias": "model.safetensors",
|
| 68 |
+
"language_model.model.decoder.layers.2.encoder_attn.k_proj.weight": "model.safetensors",
|
| 69 |
+
"language_model.model.decoder.layers.2.encoder_attn.out_proj.bias": "model.safetensors",
|
| 70 |
+
"language_model.model.decoder.layers.2.encoder_attn.out_proj.weight": "model.safetensors",
|
| 71 |
+
"language_model.model.decoder.layers.2.encoder_attn.q_proj.bias": "model.safetensors",
|
| 72 |
+
"language_model.model.decoder.layers.2.encoder_attn.q_proj.weight": "model.safetensors",
|
| 73 |
+
"language_model.model.decoder.layers.2.encoder_attn.v_proj.bias": "model.safetensors",
|
| 74 |
+
"language_model.model.decoder.layers.2.encoder_attn.v_proj.weight": "model.safetensors",
|
| 75 |
+
"language_model.model.decoder.layers.2.encoder_attn_layer_norm.bias": "model.safetensors",
|
| 76 |
+
"language_model.model.decoder.layers.2.encoder_attn_layer_norm.weight": "model.safetensors",
|
| 77 |
+
"language_model.model.decoder.layers.2.fc1.bias": "model.safetensors",
|
| 78 |
+
"language_model.model.decoder.layers.2.fc1.weight": "model.safetensors",
|
| 79 |
+
"language_model.model.decoder.layers.2.fc2.bias": "model.safetensors",
|
| 80 |
+
"language_model.model.decoder.layers.2.fc2.weight": "model.safetensors",
|
| 81 |
+
"language_model.model.decoder.layers.2.final_layer_norm.bias": "model.safetensors",
|
| 82 |
+
"language_model.model.decoder.layers.2.final_layer_norm.weight": "model.safetensors",
|
| 83 |
+
"language_model.model.decoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
|
| 84 |
+
"language_model.model.decoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 85 |
+
"language_model.model.decoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
|
| 86 |
+
"language_model.model.decoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
|
| 87 |
+
"language_model.model.decoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
|
| 88 |
+
"language_model.model.decoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 89 |
+
"language_model.model.decoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
|
| 90 |
+
"language_model.model.decoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 91 |
+
"language_model.model.decoder.layers.2.self_attn_layer_norm.bias": "model.safetensors",
|
| 92 |
+
"language_model.model.decoder.layers.2.self_attn_layer_norm.weight": "model.safetensors",
|
| 93 |
+
"language_model.model.decoder.layers.3.encoder_attn.k_proj.bias": "model.safetensors",
|
| 94 |
+
"language_model.model.decoder.layers.3.encoder_attn.k_proj.weight": "model.safetensors",
|
| 95 |
+
"language_model.model.decoder.layers.3.encoder_attn.out_proj.bias": "model.safetensors",
|
| 96 |
+
"language_model.model.decoder.layers.3.encoder_attn.out_proj.weight": "model.safetensors",
|
| 97 |
+
"language_model.model.decoder.layers.3.encoder_attn.q_proj.bias": "model.safetensors",
|
| 98 |
+
"language_model.model.decoder.layers.3.encoder_attn.q_proj.weight": "model.safetensors",
|
| 99 |
+
"language_model.model.decoder.layers.3.encoder_attn.v_proj.bias": "model.safetensors",
|
| 100 |
+
"language_model.model.decoder.layers.3.encoder_attn.v_proj.weight": "model.safetensors",
|
| 101 |
+
"language_model.model.decoder.layers.3.encoder_attn_layer_norm.bias": "model.safetensors",
|
| 102 |
+
"language_model.model.decoder.layers.3.encoder_attn_layer_norm.weight": "model.safetensors",
|
| 103 |
+
"language_model.model.decoder.layers.3.fc1.bias": "model.safetensors",
|
| 104 |
+
"language_model.model.decoder.layers.3.fc1.weight": "model.safetensors",
|
| 105 |
+
"language_model.model.decoder.layers.3.fc2.bias": "model.safetensors",
|
| 106 |
+
"language_model.model.decoder.layers.3.fc2.weight": "model.safetensors",
|
| 107 |
+
"language_model.model.decoder.layers.3.final_layer_norm.bias": "model.safetensors",
|
| 108 |
+
"language_model.model.decoder.layers.3.final_layer_norm.weight": "model.safetensors",
|
| 109 |
+
"language_model.model.decoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
|
| 110 |
+
"language_model.model.decoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 111 |
+
"language_model.model.decoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
|
| 112 |
+
"language_model.model.decoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
|
| 113 |
+
"language_model.model.decoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
|
| 114 |
+
"language_model.model.decoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 115 |
+
"language_model.model.decoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
|
| 116 |
+
"language_model.model.decoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 117 |
+
"language_model.model.decoder.layers.3.self_attn_layer_norm.bias": "model.safetensors",
|
| 118 |
+
"language_model.model.decoder.layers.3.self_attn_layer_norm.weight": "model.safetensors",
|
| 119 |
+
"language_model.model.decoder.layers.4.encoder_attn.k_proj.bias": "model.safetensors",
|
| 120 |
+
"language_model.model.decoder.layers.4.encoder_attn.k_proj.weight": "model.safetensors",
|
| 121 |
+
"language_model.model.decoder.layers.4.encoder_attn.out_proj.bias": "model.safetensors",
|
| 122 |
+
"language_model.model.decoder.layers.4.encoder_attn.out_proj.weight": "model.safetensors",
|
| 123 |
+
"language_model.model.decoder.layers.4.encoder_attn.q_proj.bias": "model.safetensors",
|
| 124 |
+
"language_model.model.decoder.layers.4.encoder_attn.q_proj.weight": "model.safetensors",
|
| 125 |
+
"language_model.model.decoder.layers.4.encoder_attn.v_proj.bias": "model.safetensors",
|
| 126 |
+
"language_model.model.decoder.layers.4.encoder_attn.v_proj.weight": "model.safetensors",
|
| 127 |
+
"language_model.model.decoder.layers.4.encoder_attn_layer_norm.bias": "model.safetensors",
|
| 128 |
+
"language_model.model.decoder.layers.4.encoder_attn_layer_norm.weight": "model.safetensors",
|
| 129 |
+
"language_model.model.decoder.layers.4.fc1.bias": "model.safetensors",
|
| 130 |
+
"language_model.model.decoder.layers.4.fc1.weight": "model.safetensors",
|
| 131 |
+
"language_model.model.decoder.layers.4.fc2.bias": "model.safetensors",
|
| 132 |
+
"language_model.model.decoder.layers.4.fc2.weight": "model.safetensors",
|
| 133 |
+
"language_model.model.decoder.layers.4.final_layer_norm.bias": "model.safetensors",
|
| 134 |
+
"language_model.model.decoder.layers.4.final_layer_norm.weight": "model.safetensors",
|
| 135 |
+
"language_model.model.decoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
|
| 136 |
+
"language_model.model.decoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 137 |
+
"language_model.model.decoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
|
| 138 |
+
"language_model.model.decoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
|
| 139 |
+
"language_model.model.decoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
|
| 140 |
+
"language_model.model.decoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 141 |
+
"language_model.model.decoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
|
| 142 |
+
"language_model.model.decoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 143 |
+
"language_model.model.decoder.layers.4.self_attn_layer_norm.bias": "model.safetensors",
|
| 144 |
+
"language_model.model.decoder.layers.4.self_attn_layer_norm.weight": "model.safetensors",
|
| 145 |
+
"language_model.model.decoder.layers.5.encoder_attn.k_proj.bias": "model.safetensors",
|
| 146 |
+
"language_model.model.decoder.layers.5.encoder_attn.k_proj.weight": "model.safetensors",
|
| 147 |
+
"language_model.model.decoder.layers.5.encoder_attn.out_proj.bias": "model.safetensors",
|
| 148 |
+
"language_model.model.decoder.layers.5.encoder_attn.out_proj.weight": "model.safetensors",
|
| 149 |
+
"language_model.model.decoder.layers.5.encoder_attn.q_proj.bias": "model.safetensors",
|
| 150 |
+
"language_model.model.decoder.layers.5.encoder_attn.q_proj.weight": "model.safetensors",
|
| 151 |
+
"language_model.model.decoder.layers.5.encoder_attn.v_proj.bias": "model.safetensors",
|
| 152 |
+
"language_model.model.decoder.layers.5.encoder_attn.v_proj.weight": "model.safetensors",
|
| 153 |
+
"language_model.model.decoder.layers.5.encoder_attn_layer_norm.bias": "model.safetensors",
|
| 154 |
+
"language_model.model.decoder.layers.5.encoder_attn_layer_norm.weight": "model.safetensors",
|
| 155 |
+
"language_model.model.decoder.layers.5.fc1.bias": "model.safetensors",
|
| 156 |
+
"language_model.model.decoder.layers.5.fc1.weight": "model.safetensors",
|
| 157 |
+
"language_model.model.decoder.layers.5.fc2.bias": "model.safetensors",
|
| 158 |
+
"language_model.model.decoder.layers.5.fc2.weight": "model.safetensors",
|
| 159 |
+
"language_model.model.decoder.layers.5.final_layer_norm.bias": "model.safetensors",
|
| 160 |
+
"language_model.model.decoder.layers.5.final_layer_norm.weight": "model.safetensors",
|
| 161 |
+
"language_model.model.decoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
|
| 162 |
+
"language_model.model.decoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 163 |
+
"language_model.model.decoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
|
| 164 |
+
"language_model.model.decoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
|
| 165 |
+
"language_model.model.decoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
|
| 166 |
+
"language_model.model.decoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 167 |
+
"language_model.model.decoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
|
| 168 |
+
"language_model.model.decoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 169 |
+
"language_model.model.decoder.layers.5.self_attn_layer_norm.bias": "model.safetensors",
|
| 170 |
+
"language_model.model.decoder.layers.5.self_attn_layer_norm.weight": "model.safetensors",
|
| 171 |
+
"language_model.model.encoder.embed_positions.weight": "model.safetensors",
|
| 172 |
+
"language_model.model.encoder.layernorm_embedding.bias": "model.safetensors",
|
| 173 |
+
"language_model.model.encoder.layernorm_embedding.weight": "model.safetensors",
|
| 174 |
+
"language_model.model.encoder.layers.0.fc1.bias": "model.safetensors",
|
| 175 |
+
"language_model.model.encoder.layers.0.fc1.weight": "model.safetensors",
|
| 176 |
+
"language_model.model.encoder.layers.0.fc2.bias": "model.safetensors",
|
| 177 |
+
"language_model.model.encoder.layers.0.fc2.weight": "model.safetensors",
|
| 178 |
+
"language_model.model.encoder.layers.0.final_layer_norm.bias": "model.safetensors",
|
| 179 |
+
"language_model.model.encoder.layers.0.final_layer_norm.weight": "model.safetensors",
|
| 180 |
+
"language_model.model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
|
| 181 |
+
"language_model.model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 182 |
+
"language_model.model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
|
| 183 |
+
"language_model.model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
|
| 184 |
+
"language_model.model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
|
| 185 |
+
"language_model.model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 186 |
+
"language_model.model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
|
| 187 |
+
"language_model.model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 188 |
+
"language_model.model.encoder.layers.0.self_attn_layer_norm.bias": "model.safetensors",
|
| 189 |
+
"language_model.model.encoder.layers.0.self_attn_layer_norm.weight": "model.safetensors",
|
| 190 |
+
"language_model.model.encoder.layers.1.fc1.bias": "model.safetensors",
|
| 191 |
+
"language_model.model.encoder.layers.1.fc1.weight": "model.safetensors",
|
| 192 |
+
"language_model.model.encoder.layers.1.fc2.bias": "model.safetensors",
|
| 193 |
+
"language_model.model.encoder.layers.1.fc2.weight": "model.safetensors",
|
| 194 |
+
"language_model.model.encoder.layers.1.final_layer_norm.bias": "model.safetensors",
|
| 195 |
+
"language_model.model.encoder.layers.1.final_layer_norm.weight": "model.safetensors",
|
| 196 |
+
"language_model.model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
|
| 197 |
+
"language_model.model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 198 |
+
"language_model.model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
|
| 199 |
+
"language_model.model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
|
| 200 |
+
"language_model.model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
|
| 201 |
+
"language_model.model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 202 |
+
"language_model.model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
|
| 203 |
+
"language_model.model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 204 |
+
"language_model.model.encoder.layers.1.self_attn_layer_norm.bias": "model.safetensors",
|
| 205 |
+
"language_model.model.encoder.layers.1.self_attn_layer_norm.weight": "model.safetensors",
|
| 206 |
+
"language_model.model.encoder.layers.2.fc1.bias": "model.safetensors",
|
| 207 |
+
"language_model.model.encoder.layers.2.fc1.weight": "model.safetensors",
|
| 208 |
+
"language_model.model.encoder.layers.2.fc2.bias": "model.safetensors",
|
| 209 |
+
"language_model.model.encoder.layers.2.fc2.weight": "model.safetensors",
|
| 210 |
+
"language_model.model.encoder.layers.2.final_layer_norm.bias": "model.safetensors",
|
| 211 |
+
"language_model.model.encoder.layers.2.final_layer_norm.weight": "model.safetensors",
|
| 212 |
+
"language_model.model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
|
| 213 |
+
"language_model.model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 214 |
+
"language_model.model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
|
| 215 |
+
"language_model.model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
|
| 216 |
+
"language_model.model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
|
| 217 |
+
"language_model.model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 218 |
+
"language_model.model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
|
| 219 |
+
"language_model.model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 220 |
+
"language_model.model.encoder.layers.2.self_attn_layer_norm.bias": "model.safetensors",
|
| 221 |
+
"language_model.model.encoder.layers.2.self_attn_layer_norm.weight": "model.safetensors",
|
| 222 |
+
"language_model.model.encoder.layers.3.fc1.bias": "model.safetensors",
|
| 223 |
+
"language_model.model.encoder.layers.3.fc1.weight": "model.safetensors",
|
| 224 |
+
"language_model.model.encoder.layers.3.fc2.bias": "model.safetensors",
|
| 225 |
+
"language_model.model.encoder.layers.3.fc2.weight": "model.safetensors",
|
| 226 |
+
"language_model.model.encoder.layers.3.final_layer_norm.bias": "model.safetensors",
|
| 227 |
+
"language_model.model.encoder.layers.3.final_layer_norm.weight": "model.safetensors",
|
| 228 |
+
"language_model.model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
|
| 229 |
+
"language_model.model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 230 |
+
"language_model.model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
|
| 231 |
+
"language_model.model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
|
| 232 |
+
"language_model.model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
|
| 233 |
+
"language_model.model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 234 |
+
"language_model.model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
|
| 235 |
+
"language_model.model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 236 |
+
"language_model.model.encoder.layers.3.self_attn_layer_norm.bias": "model.safetensors",
|
| 237 |
+
"language_model.model.encoder.layers.3.self_attn_layer_norm.weight": "model.safetensors",
|
| 238 |
+
"language_model.model.encoder.layers.4.fc1.bias": "model.safetensors",
|
| 239 |
+
"language_model.model.encoder.layers.4.fc1.weight": "model.safetensors",
|
| 240 |
+
"language_model.model.encoder.layers.4.fc2.bias": "model.safetensors",
|
| 241 |
+
"language_model.model.encoder.layers.4.fc2.weight": "model.safetensors",
|
| 242 |
+
"language_model.model.encoder.layers.4.final_layer_norm.bias": "model.safetensors",
|
| 243 |
+
"language_model.model.encoder.layers.4.final_layer_norm.weight": "model.safetensors",
|
| 244 |
+
"language_model.model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
|
| 245 |
+
"language_model.model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 246 |
+
"language_model.model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
|
| 247 |
+
"language_model.model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
|
| 248 |
+
"language_model.model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
|
| 249 |
+
"language_model.model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 250 |
+
"language_model.model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
|
| 251 |
+
"language_model.model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 252 |
+
"language_model.model.encoder.layers.4.self_attn_layer_norm.bias": "model.safetensors",
|
| 253 |
+
"language_model.model.encoder.layers.4.self_attn_layer_norm.weight": "model.safetensors",
|
| 254 |
+
"language_model.model.encoder.layers.5.fc1.bias": "model.safetensors",
|
| 255 |
+
"language_model.model.encoder.layers.5.fc1.weight": "model.safetensors",
|
| 256 |
+
"language_model.model.encoder.layers.5.fc2.bias": "model.safetensors",
|
| 257 |
+
"language_model.model.encoder.layers.5.fc2.weight": "model.safetensors",
|
| 258 |
+
"language_model.model.encoder.layers.5.final_layer_norm.bias": "model.safetensors",
|
| 259 |
+
"language_model.model.encoder.layers.5.final_layer_norm.weight": "model.safetensors",
|
| 260 |
+
"language_model.model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
|
| 261 |
+
"language_model.model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 262 |
+
"language_model.model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
|
| 263 |
+
"language_model.model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
|
| 264 |
+
"language_model.model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
|
| 265 |
+
"language_model.model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 266 |
+
"language_model.model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
|
| 267 |
+
"language_model.model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 268 |
+
"language_model.model.encoder.layers.5.self_attn_layer_norm.bias": "model.safetensors",
|
| 269 |
+
"language_model.model.encoder.layers.5.self_attn_layer_norm.weight": "model.safetensors",
|
| 270 |
+
"language_model.model.shared.weight": "model.safetensors",
|
| 271 |
+
"vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 272 |
+
"vision_tower.blocks.0.0.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 273 |
+
"vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 274 |
+
"vision_tower.blocks.0.0.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 275 |
+
"vision_tower.blocks.0.0.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 276 |
+
"vision_tower.blocks.0.0.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 277 |
+
"vision_tower.blocks.0.0.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 278 |
+
"vision_tower.blocks.0.0.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 279 |
+
"vision_tower.blocks.0.0.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 280 |
+
"vision_tower.blocks.0.0.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 281 |
+
"vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 282 |
+
"vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 283 |
+
"vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 284 |
+
"vision_tower.blocks.0.0.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 285 |
+
"vision_tower.blocks.0.0.channel_block.ffn.norm.bias": "model.safetensors",
|
| 286 |
+
"vision_tower.blocks.0.0.channel_block.ffn.norm.weight": "model.safetensors",
|
| 287 |
+
"vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 288 |
+
"vision_tower.blocks.0.0.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 289 |
+
"vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 290 |
+
"vision_tower.blocks.0.0.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 291 |
+
"vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 292 |
+
"vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 293 |
+
"vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 294 |
+
"vision_tower.blocks.0.0.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 295 |
+
"vision_tower.blocks.0.0.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 296 |
+
"vision_tower.blocks.0.0.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 297 |
+
"vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 298 |
+
"vision_tower.blocks.0.0.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 299 |
+
"vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 300 |
+
"vision_tower.blocks.0.0.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 301 |
+
"vision_tower.blocks.0.0.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 302 |
+
"vision_tower.blocks.0.0.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 303 |
+
"vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 304 |
+
"vision_tower.blocks.1.0.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 305 |
+
"vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 306 |
+
"vision_tower.blocks.1.0.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 307 |
+
"vision_tower.blocks.1.0.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 308 |
+
"vision_tower.blocks.1.0.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 309 |
+
"vision_tower.blocks.1.0.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 310 |
+
"vision_tower.blocks.1.0.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 311 |
+
"vision_tower.blocks.1.0.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 312 |
+
"vision_tower.blocks.1.0.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 313 |
+
"vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 314 |
+
"vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 315 |
+
"vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 316 |
+
"vision_tower.blocks.1.0.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 317 |
+
"vision_tower.blocks.1.0.channel_block.ffn.norm.bias": "model.safetensors",
|
| 318 |
+
"vision_tower.blocks.1.0.channel_block.ffn.norm.weight": "model.safetensors",
|
| 319 |
+
"vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 320 |
+
"vision_tower.blocks.1.0.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 321 |
+
"vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 322 |
+
"vision_tower.blocks.1.0.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 323 |
+
"vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 324 |
+
"vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 325 |
+
"vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 326 |
+
"vision_tower.blocks.1.0.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 327 |
+
"vision_tower.blocks.1.0.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 328 |
+
"vision_tower.blocks.1.0.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 329 |
+
"vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 330 |
+
"vision_tower.blocks.1.0.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 331 |
+
"vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 332 |
+
"vision_tower.blocks.1.0.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 333 |
+
"vision_tower.blocks.1.0.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 334 |
+
"vision_tower.blocks.1.0.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 335 |
+
"vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 336 |
+
"vision_tower.blocks.2.0.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 337 |
+
"vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 338 |
+
"vision_tower.blocks.2.0.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 339 |
+
"vision_tower.blocks.2.0.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 340 |
+
"vision_tower.blocks.2.0.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 341 |
+
"vision_tower.blocks.2.0.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 342 |
+
"vision_tower.blocks.2.0.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 343 |
+
"vision_tower.blocks.2.0.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 344 |
+
"vision_tower.blocks.2.0.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 345 |
+
"vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 346 |
+
"vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 347 |
+
"vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 348 |
+
"vision_tower.blocks.2.0.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 349 |
+
"vision_tower.blocks.2.0.channel_block.ffn.norm.bias": "model.safetensors",
|
| 350 |
+
"vision_tower.blocks.2.0.channel_block.ffn.norm.weight": "model.safetensors",
|
| 351 |
+
"vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 352 |
+
"vision_tower.blocks.2.0.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 353 |
+
"vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 354 |
+
"vision_tower.blocks.2.0.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 355 |
+
"vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 356 |
+
"vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 357 |
+
"vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 358 |
+
"vision_tower.blocks.2.0.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 359 |
+
"vision_tower.blocks.2.0.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 360 |
+
"vision_tower.blocks.2.0.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 361 |
+
"vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 362 |
+
"vision_tower.blocks.2.0.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 363 |
+
"vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 364 |
+
"vision_tower.blocks.2.0.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 365 |
+
"vision_tower.blocks.2.0.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 366 |
+
"vision_tower.blocks.2.0.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 367 |
+
"vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 368 |
+
"vision_tower.blocks.2.1.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 369 |
+
"vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 370 |
+
"vision_tower.blocks.2.1.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 371 |
+
"vision_tower.blocks.2.1.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 372 |
+
"vision_tower.blocks.2.1.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 373 |
+
"vision_tower.blocks.2.1.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 374 |
+
"vision_tower.blocks.2.1.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 375 |
+
"vision_tower.blocks.2.1.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 376 |
+
"vision_tower.blocks.2.1.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 377 |
+
"vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 378 |
+
"vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 379 |
+
"vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 380 |
+
"vision_tower.blocks.2.1.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 381 |
+
"vision_tower.blocks.2.1.channel_block.ffn.norm.bias": "model.safetensors",
|
| 382 |
+
"vision_tower.blocks.2.1.channel_block.ffn.norm.weight": "model.safetensors",
|
| 383 |
+
"vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 384 |
+
"vision_tower.blocks.2.1.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 385 |
+
"vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 386 |
+
"vision_tower.blocks.2.1.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 387 |
+
"vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 388 |
+
"vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 389 |
+
"vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 390 |
+
"vision_tower.blocks.2.1.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 391 |
+
"vision_tower.blocks.2.1.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 392 |
+
"vision_tower.blocks.2.1.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 393 |
+
"vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 394 |
+
"vision_tower.blocks.2.1.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 395 |
+
"vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 396 |
+
"vision_tower.blocks.2.1.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 397 |
+
"vision_tower.blocks.2.1.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 398 |
+
"vision_tower.blocks.2.1.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 399 |
+
"vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 400 |
+
"vision_tower.blocks.2.2.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 401 |
+
"vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 402 |
+
"vision_tower.blocks.2.2.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 403 |
+
"vision_tower.blocks.2.2.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 404 |
+
"vision_tower.blocks.2.2.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 405 |
+
"vision_tower.blocks.2.2.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 406 |
+
"vision_tower.blocks.2.2.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 407 |
+
"vision_tower.blocks.2.2.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 408 |
+
"vision_tower.blocks.2.2.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 409 |
+
"vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 410 |
+
"vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 411 |
+
"vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 412 |
+
"vision_tower.blocks.2.2.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 413 |
+
"vision_tower.blocks.2.2.channel_block.ffn.norm.bias": "model.safetensors",
|
| 414 |
+
"vision_tower.blocks.2.2.channel_block.ffn.norm.weight": "model.safetensors",
|
| 415 |
+
"vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 416 |
+
"vision_tower.blocks.2.2.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 417 |
+
"vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 418 |
+
"vision_tower.blocks.2.2.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 419 |
+
"vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 420 |
+
"vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 421 |
+
"vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 422 |
+
"vision_tower.blocks.2.2.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 423 |
+
"vision_tower.blocks.2.2.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 424 |
+
"vision_tower.blocks.2.2.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 425 |
+
"vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 426 |
+
"vision_tower.blocks.2.2.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 427 |
+
"vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 428 |
+
"vision_tower.blocks.2.2.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 429 |
+
"vision_tower.blocks.2.2.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 430 |
+
"vision_tower.blocks.2.2.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 431 |
+
"vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 432 |
+
"vision_tower.blocks.2.3.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 433 |
+
"vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 434 |
+
"vision_tower.blocks.2.3.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 435 |
+
"vision_tower.blocks.2.3.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 436 |
+
"vision_tower.blocks.2.3.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 437 |
+
"vision_tower.blocks.2.3.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 438 |
+
"vision_tower.blocks.2.3.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 439 |
+
"vision_tower.blocks.2.3.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 440 |
+
"vision_tower.blocks.2.3.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 441 |
+
"vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 442 |
+
"vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 443 |
+
"vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 444 |
+
"vision_tower.blocks.2.3.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 445 |
+
"vision_tower.blocks.2.3.channel_block.ffn.norm.bias": "model.safetensors",
|
| 446 |
+
"vision_tower.blocks.2.3.channel_block.ffn.norm.weight": "model.safetensors",
|
| 447 |
+
"vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 448 |
+
"vision_tower.blocks.2.3.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 449 |
+
"vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 450 |
+
"vision_tower.blocks.2.3.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 451 |
+
"vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 452 |
+
"vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 453 |
+
"vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 454 |
+
"vision_tower.blocks.2.3.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 455 |
+
"vision_tower.blocks.2.3.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 456 |
+
"vision_tower.blocks.2.3.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 457 |
+
"vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 458 |
+
"vision_tower.blocks.2.3.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 459 |
+
"vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 460 |
+
"vision_tower.blocks.2.3.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 461 |
+
"vision_tower.blocks.2.3.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 462 |
+
"vision_tower.blocks.2.3.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 463 |
+
"vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 464 |
+
"vision_tower.blocks.2.4.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 465 |
+
"vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 466 |
+
"vision_tower.blocks.2.4.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 467 |
+
"vision_tower.blocks.2.4.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 468 |
+
"vision_tower.blocks.2.4.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 469 |
+
"vision_tower.blocks.2.4.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 470 |
+
"vision_tower.blocks.2.4.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 471 |
+
"vision_tower.blocks.2.4.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 472 |
+
"vision_tower.blocks.2.4.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 473 |
+
"vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 474 |
+
"vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 475 |
+
"vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 476 |
+
"vision_tower.blocks.2.4.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 477 |
+
"vision_tower.blocks.2.4.channel_block.ffn.norm.bias": "model.safetensors",
|
| 478 |
+
"vision_tower.blocks.2.4.channel_block.ffn.norm.weight": "model.safetensors",
|
| 479 |
+
"vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 480 |
+
"vision_tower.blocks.2.4.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 481 |
+
"vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 482 |
+
"vision_tower.blocks.2.4.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 483 |
+
"vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 484 |
+
"vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 485 |
+
"vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 486 |
+
"vision_tower.blocks.2.4.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 487 |
+
"vision_tower.blocks.2.4.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 488 |
+
"vision_tower.blocks.2.4.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 489 |
+
"vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 490 |
+
"vision_tower.blocks.2.4.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 491 |
+
"vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 492 |
+
"vision_tower.blocks.2.4.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 493 |
+
"vision_tower.blocks.2.4.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 494 |
+
"vision_tower.blocks.2.4.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 495 |
+
"vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 496 |
+
"vision_tower.blocks.2.5.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 497 |
+
"vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 498 |
+
"vision_tower.blocks.2.5.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 499 |
+
"vision_tower.blocks.2.5.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 500 |
+
"vision_tower.blocks.2.5.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 501 |
+
"vision_tower.blocks.2.5.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 502 |
+
"vision_tower.blocks.2.5.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 503 |
+
"vision_tower.blocks.2.5.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 504 |
+
"vision_tower.blocks.2.5.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 505 |
+
"vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 506 |
+
"vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 507 |
+
"vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 508 |
+
"vision_tower.blocks.2.5.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 509 |
+
"vision_tower.blocks.2.5.channel_block.ffn.norm.bias": "model.safetensors",
|
| 510 |
+
"vision_tower.blocks.2.5.channel_block.ffn.norm.weight": "model.safetensors",
|
| 511 |
+
"vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 512 |
+
"vision_tower.blocks.2.5.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 513 |
+
"vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 514 |
+
"vision_tower.blocks.2.5.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 515 |
+
"vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 516 |
+
"vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 517 |
+
"vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 518 |
+
"vision_tower.blocks.2.5.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 519 |
+
"vision_tower.blocks.2.5.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 520 |
+
"vision_tower.blocks.2.5.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 521 |
+
"vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 522 |
+
"vision_tower.blocks.2.5.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 523 |
+
"vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 524 |
+
"vision_tower.blocks.2.5.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 525 |
+
"vision_tower.blocks.2.5.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 526 |
+
"vision_tower.blocks.2.5.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 527 |
+
"vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 528 |
+
"vision_tower.blocks.2.6.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 529 |
+
"vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 530 |
+
"vision_tower.blocks.2.6.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 531 |
+
"vision_tower.blocks.2.6.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 532 |
+
"vision_tower.blocks.2.6.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 533 |
+
"vision_tower.blocks.2.6.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 534 |
+
"vision_tower.blocks.2.6.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 535 |
+
"vision_tower.blocks.2.6.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 536 |
+
"vision_tower.blocks.2.6.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 537 |
+
"vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 538 |
+
"vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 539 |
+
"vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 540 |
+
"vision_tower.blocks.2.6.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 541 |
+
"vision_tower.blocks.2.6.channel_block.ffn.norm.bias": "model.safetensors",
|
| 542 |
+
"vision_tower.blocks.2.6.channel_block.ffn.norm.weight": "model.safetensors",
|
| 543 |
+
"vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 544 |
+
"vision_tower.blocks.2.6.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 545 |
+
"vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 546 |
+
"vision_tower.blocks.2.6.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 547 |
+
"vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 548 |
+
"vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 549 |
+
"vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 550 |
+
"vision_tower.blocks.2.6.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 551 |
+
"vision_tower.blocks.2.6.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 552 |
+
"vision_tower.blocks.2.6.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 553 |
+
"vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 554 |
+
"vision_tower.blocks.2.6.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 555 |
+
"vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 556 |
+
"vision_tower.blocks.2.6.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 557 |
+
"vision_tower.blocks.2.6.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 558 |
+
"vision_tower.blocks.2.6.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 559 |
+
"vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 560 |
+
"vision_tower.blocks.2.7.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 561 |
+
"vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 562 |
+
"vision_tower.blocks.2.7.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 563 |
+
"vision_tower.blocks.2.7.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 564 |
+
"vision_tower.blocks.2.7.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 565 |
+
"vision_tower.blocks.2.7.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 566 |
+
"vision_tower.blocks.2.7.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 567 |
+
"vision_tower.blocks.2.7.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 568 |
+
"vision_tower.blocks.2.7.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 569 |
+
"vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 570 |
+
"vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 571 |
+
"vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 572 |
+
"vision_tower.blocks.2.7.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 573 |
+
"vision_tower.blocks.2.7.channel_block.ffn.norm.bias": "model.safetensors",
|
| 574 |
+
"vision_tower.blocks.2.7.channel_block.ffn.norm.weight": "model.safetensors",
|
| 575 |
+
"vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 576 |
+
"vision_tower.blocks.2.7.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 577 |
+
"vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 578 |
+
"vision_tower.blocks.2.7.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 579 |
+
"vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 580 |
+
"vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 581 |
+
"vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 582 |
+
"vision_tower.blocks.2.7.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 583 |
+
"vision_tower.blocks.2.7.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 584 |
+
"vision_tower.blocks.2.7.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 585 |
+
"vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 586 |
+
"vision_tower.blocks.2.7.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 587 |
+
"vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 588 |
+
"vision_tower.blocks.2.7.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 589 |
+
"vision_tower.blocks.2.7.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 590 |
+
"vision_tower.blocks.2.7.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 591 |
+
"vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 592 |
+
"vision_tower.blocks.2.8.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 593 |
+
"vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 594 |
+
"vision_tower.blocks.2.8.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 595 |
+
"vision_tower.blocks.2.8.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 596 |
+
"vision_tower.blocks.2.8.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 597 |
+
"vision_tower.blocks.2.8.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 598 |
+
"vision_tower.blocks.2.8.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 599 |
+
"vision_tower.blocks.2.8.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 600 |
+
"vision_tower.blocks.2.8.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 601 |
+
"vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 602 |
+
"vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 603 |
+
"vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 604 |
+
"vision_tower.blocks.2.8.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 605 |
+
"vision_tower.blocks.2.8.channel_block.ffn.norm.bias": "model.safetensors",
|
| 606 |
+
"vision_tower.blocks.2.8.channel_block.ffn.norm.weight": "model.safetensors",
|
| 607 |
+
"vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 608 |
+
"vision_tower.blocks.2.8.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 609 |
+
"vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 610 |
+
"vision_tower.blocks.2.8.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 611 |
+
"vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 612 |
+
"vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 613 |
+
"vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 614 |
+
"vision_tower.blocks.2.8.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 615 |
+
"vision_tower.blocks.2.8.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 616 |
+
"vision_tower.blocks.2.8.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 617 |
+
"vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 618 |
+
"vision_tower.blocks.2.8.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 619 |
+
"vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 620 |
+
"vision_tower.blocks.2.8.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 621 |
+
"vision_tower.blocks.2.8.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 622 |
+
"vision_tower.blocks.2.8.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 623 |
+
"vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.bias": "model.safetensors",
|
| 624 |
+
"vision_tower.blocks.3.0.channel_block.channel_attn.fn.proj.weight": "model.safetensors",
|
| 625 |
+
"vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.bias": "model.safetensors",
|
| 626 |
+
"vision_tower.blocks.3.0.channel_block.channel_attn.fn.qkv.weight": "model.safetensors",
|
| 627 |
+
"vision_tower.blocks.3.0.channel_block.channel_attn.norm.bias": "model.safetensors",
|
| 628 |
+
"vision_tower.blocks.3.0.channel_block.channel_attn.norm.weight": "model.safetensors",
|
| 629 |
+
"vision_tower.blocks.3.0.channel_block.conv1.fn.dw.bias": "model.safetensors",
|
| 630 |
+
"vision_tower.blocks.3.0.channel_block.conv1.fn.dw.weight": "model.safetensors",
|
| 631 |
+
"vision_tower.blocks.3.0.channel_block.conv2.fn.dw.bias": "model.safetensors",
|
| 632 |
+
"vision_tower.blocks.3.0.channel_block.conv2.fn.dw.weight": "model.safetensors",
|
| 633 |
+
"vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 634 |
+
"vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 635 |
+
"vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 636 |
+
"vision_tower.blocks.3.0.channel_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 637 |
+
"vision_tower.blocks.3.0.channel_block.ffn.norm.bias": "model.safetensors",
|
| 638 |
+
"vision_tower.blocks.3.0.channel_block.ffn.norm.weight": "model.safetensors",
|
| 639 |
+
"vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.bias": "model.safetensors",
|
| 640 |
+
"vision_tower.blocks.3.0.spatial_block.conv1.fn.dw.weight": "model.safetensors",
|
| 641 |
+
"vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.bias": "model.safetensors",
|
| 642 |
+
"vision_tower.blocks.3.0.spatial_block.conv2.fn.dw.weight": "model.safetensors",
|
| 643 |
+
"vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.bias": "model.safetensors",
|
| 644 |
+
"vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc1.weight": "model.safetensors",
|
| 645 |
+
"vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.bias": "model.safetensors",
|
| 646 |
+
"vision_tower.blocks.3.0.spatial_block.ffn.fn.net.fc2.weight": "model.safetensors",
|
| 647 |
+
"vision_tower.blocks.3.0.spatial_block.ffn.norm.bias": "model.safetensors",
|
| 648 |
+
"vision_tower.blocks.3.0.spatial_block.ffn.norm.weight": "model.safetensors",
|
| 649 |
+
"vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.bias": "model.safetensors",
|
| 650 |
+
"vision_tower.blocks.3.0.spatial_block.window_attn.fn.proj.weight": "model.safetensors",
|
| 651 |
+
"vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.bias": "model.safetensors",
|
| 652 |
+
"vision_tower.blocks.3.0.spatial_block.window_attn.fn.qkv.weight": "model.safetensors",
|
| 653 |
+
"vision_tower.blocks.3.0.spatial_block.window_attn.norm.bias": "model.safetensors",
|
| 654 |
+
"vision_tower.blocks.3.0.spatial_block.window_attn.norm.weight": "model.safetensors",
|
| 655 |
+
"vision_tower.convs.0.norm.bias": "model.safetensors",
|
| 656 |
+
"vision_tower.convs.0.norm.weight": "model.safetensors",
|
| 657 |
+
"vision_tower.convs.0.proj.bias": "model.safetensors",
|
| 658 |
+
"vision_tower.convs.0.proj.weight": "model.safetensors",
|
| 659 |
+
"vision_tower.convs.1.norm.bias": "model.safetensors",
|
| 660 |
+
"vision_tower.convs.1.norm.weight": "model.safetensors",
|
| 661 |
+
"vision_tower.convs.1.proj.bias": "model.safetensors",
|
| 662 |
+
"vision_tower.convs.1.proj.weight": "model.safetensors",
|
| 663 |
+
"vision_tower.convs.2.norm.bias": "model.safetensors",
|
| 664 |
+
"vision_tower.convs.2.norm.weight": "model.safetensors",
|
| 665 |
+
"vision_tower.convs.2.proj.bias": "model.safetensors",
|
| 666 |
+
"vision_tower.convs.2.proj.weight": "model.safetensors",
|
| 667 |
+
"vision_tower.convs.3.norm.bias": "model.safetensors",
|
| 668 |
+
"vision_tower.convs.3.norm.weight": "model.safetensors",
|
| 669 |
+
"vision_tower.convs.3.proj.bias": "model.safetensors",
|
| 670 |
+
"vision_tower.convs.3.proj.weight": "model.safetensors",
|
| 671 |
+
"visual_temporal_embed.pos_idx_to_embed": "model.safetensors"
|
| 672 |
+
}
|
| 673 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format",
|
| 15 |
+
"do_convert_rgb"
|
| 16 |
+
],
|
| 17 |
+
"do_convert_rgb": null,
|
| 18 |
+
"do_normalize": true,
|
| 19 |
+
"do_rescale": true,
|
| 20 |
+
"do_resize": true,
|
| 21 |
+
"do_center_crop": false,
|
| 22 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 23 |
+
"image_seq_length": 577,
|
| 24 |
+
"image_mean": [
|
| 25 |
+
0.485,
|
| 26 |
+
0.456,
|
| 27 |
+
0.406
|
| 28 |
+
],
|
| 29 |
+
"image_std": [
|
| 30 |
+
0.229,
|
| 31 |
+
0.224,
|
| 32 |
+
0.225
|
| 33 |
+
],
|
| 34 |
+
"processor_class": "Florence2Processor",
|
| 35 |
+
"resample": 3,
|
| 36 |
+
"size": {
|
| 37 |
+
"height": 768,
|
| 38 |
+
"width": 768
|
| 39 |
+
},
|
| 40 |
+
"crop_size": {
|
| 41 |
+
"height": 768,
|
| 42 |
+
"width": 768
|
| 43 |
+
}
|
| 44 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"crop_size": {
|
| 4 |
+
"height": 768,
|
| 5 |
+
"width": 768
|
| 6 |
+
},
|
| 7 |
+
"do_center_crop": false,
|
| 8 |
+
"do_convert_rgb": null,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_rescale": true,
|
| 11 |
+
"do_resize": true,
|
| 12 |
+
"image_mean": [
|
| 13 |
+
0.485,
|
| 14 |
+
0.456,
|
| 15 |
+
0.406
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 18 |
+
"image_seq_length": 577,
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.229,
|
| 21 |
+
0.224,
|
| 22 |
+
0.225
|
| 23 |
+
],
|
| 24 |
+
"resample": 3,
|
| 25 |
+
"rescale_factor": 0.00392156862745098,
|
| 26 |
+
"size": {
|
| 27 |
+
"height": 768,
|
| 28 |
+
"width": 768
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"processor_class": "Florence2Processor"
|
| 32 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<florence_image>"
|
| 10 |
+
],
|
| 11 |
+
"is_local": true,
|
| 12 |
+
"local_files_only": true,
|
| 13 |
+
"mask_token": "<mask>",
|
| 14 |
+
"model_max_length": 1024,
|
| 15 |
+
"pad_token": "<pad>",
|
| 16 |
+
"processor_class": "Florence2Processor",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 19 |
+
"trim_offsets": true,
|
| 20 |
+
"unk_token": "<unk>"
|
| 21 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|