kirp@umich.edu
commited on
Commit
•
b175204
1
Parent(s):
6fb10b9
update readme
Browse files- .gitattributes +1 -5
- README.md +81 -3
- config.json +151 -3
- generation_config.json +9 -3
- md.py +32 -0
- model.safetensors.index.json +621 -3
- ocr.py +68 -0
- output.png +3 -0
- preprocessor_config.json +5 -3
- tokenizer.json +0 -0
- tokenizer_config.json +10 -3
.gitattributes
CHANGED
@@ -33,9 +33,5 @@ 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
|
36 |
-
receipt_00008.png filter=lfs diff=lfs merge=lfs -text
|
37 |
-
.png filter=lfs diff=lfs merge=lfs -text
|
38 |
-
*.md filter=lfs diff=lfs merge=lfs -text
|
39 |
-
*.py filter=lfs diff=lfs merge=lfs -text
|
40 |
-
*.json filter=lfs diff=lfs merge=lfs -text
|
41 |
*.png 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 |
*.png filter=lfs diff=lfs merge=lfs -text
|
37 |
+
|
README.md
CHANGED
@@ -1,3 +1,81 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
license: mit
|
4 |
+
---
|
5 |
+
# Kosmos-2.5 (Testing)
|
6 |
+
|
7 |
+
[Microsoft Document AI](https://www.microsoft.com/en-us/research/project/document-ai/) | [GitHub](https://github.com/microsoft/unilm/tree/master/kosmos-2.5)
|
8 |
+
|
9 |
+
## Model description
|
10 |
+
|
11 |
+
Kosmos-2.5 is a multimodal literate model for machine reading of text-intensive images. Pre-trained on large-scale text-intensive images, Kosmos-2.5 excels in two distinct yet cooperative transcription tasks: (1) generating spatially-aware text blocks, where each block of text is assigned its spatial coordinates within the image, and (2) producing structured text output that captures styles and structures into the markdown format. This unified multimodal literate capability is achieved through a shared decoder-only auto-regressive Transformer architecture, task-specific prompts, and flexible text representations. We evaluate Kosmos-2.5 on end-to-end document-level text recognition and image-to-markdown text generation. Furthermore, the model can be readily adapted for any text-intensive image understanding task with different prompts through supervised fine-tuning, making it a general-purpose tool for real-world applications involving text-rich images. This work also paves the way for the future scaling of multimodal large language models.
|
12 |
+
|
13 |
+
[Kosmos-2.5: A Multimodal Literate Model](https://arxiv.org/abs/2309.11419)
|
14 |
+
|
15 |
+
## NOTE
|
16 |
+
Since this is a generative model, there is a risk of **hallucination** during the generation process, and it **CAN NOT** guarantee the accuracy of all OCR/Markdown results in the images.
|
17 |
+
|
18 |
+
## Download transformers:
|
19 |
+
```bash
|
20 |
+
pip install git+https://github.com/tic-top/transformers.git
|
21 |
+
```
|
22 |
+
This repo will be soon merged to official Transformers.
|
23 |
+
|
24 |
+
## Usage
|
25 |
+
### OCR
|
26 |
+
Run with [ocr.py](ocr.py).
|
27 |
+
```text
|
28 |
+
55,595,71,595,71,629,55,629,1
|
29 |
+
82,595,481,595,481,635,82,635,[REG] BLACK SAKURA
|
30 |
+
716,590,841,590,841,629,716,629,45,455
|
31 |
+
55,637,71,637,71,672,55,672,1
|
32 |
+
82,637,486,637,486,675,82,675,COOKIE DOH SAUCES
|
33 |
+
818,632,843,632,843,668,818,668,0
|
34 |
+
51,683,71,683,71,719,51,719,1
|
35 |
+
82,683,371,683,371,719,82,719,NATA DE COCO
|
36 |
+
820,677,845,677,845,713,820,713,0
|
37 |
+
32,770,851,770,851,811,32,811,Sub Total 45,455
|
38 |
+
28,811,853,811,853,858,28,858,PB1 (10%) 4,545
|
39 |
+
28,857,855,857,855,905,28,905,Rounding 0
|
40 |
+
24,905,858,905,858,956,24,956,Total 50,000
|
41 |
+
17,1096,868,1096,868,1150,17,1150,Card Payment 50,000
|
42 |
+
```
|
43 |
+
![output](output.png)
|
44 |
+
### Markdown
|
45 |
+
Run with [md.py](md.py).
|
46 |
+
|
47 |
+
```text
|
48 |
+
- **1 \[REG\] BLACK SAKURA** 45,455
|
49 |
+
- **1 COOKIE DOH SAUCES** 0
|
50 |
+
- **1 NATA DE COCO** 0
|
51 |
+
- **Sub Total** 45,455
|
52 |
+
- **PB1 (10%)** 4,545
|
53 |
+
- **Rounding** 0
|
54 |
+
- **Total** **50,000**
|
55 |
+
|
56 |
+
Card Payment 50,000
|
57 |
+
```
|
58 |
+
|
59 |
+
|
60 |
+
|
61 |
+
|
62 |
+
## Citation
|
63 |
+
|
64 |
+
If you find Kosmos-2.5 useful in your research, please cite the following paper:
|
65 |
+
|
66 |
+
```
|
67 |
+
@article{lv2023kosmos,
|
68 |
+
title={Kosmos-2.5: A multimodal literate model},
|
69 |
+
author={Lv, Tengchao and Huang, Yupan and Chen, Jingye and Cui, Lei and Ma, Shuming and Chang, Yaoyao and Huang, Shaohan and Wang, Wenhui and Dong, Li and Luo, Weiyao and others},
|
70 |
+
journal={arXiv preprint arXiv:2309.11419},
|
71 |
+
year={2023}
|
72 |
+
}
|
73 |
+
```
|
74 |
+
|
75 |
+
## License
|
76 |
+
The content of this project itself is licensed under the [MIT](https://github.com/microsoft/unilm/blob/master/kosmos-2.5/LICENSE)
|
77 |
+
|
78 |
+
[Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct)
|
79 |
+
|
80 |
+
|
81 |
+
|
config.json
CHANGED
@@ -1,3 +1,151 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Kosmos2_5ForConditionalGeneration"
|
4 |
+
],
|
5 |
+
"latent_query_num": 2048,
|
6 |
+
"model_type": "kosmos-2.5",
|
7 |
+
"text_config": {
|
8 |
+
"_name_or_path": "",
|
9 |
+
"activation_dropout": 0.0,
|
10 |
+
"activation_function": "gelu",
|
11 |
+
"add_cross_attention": false,
|
12 |
+
"architectures": null,
|
13 |
+
"attention_dropout": 0.0,
|
14 |
+
"attention_heads": 16,
|
15 |
+
"bad_words_ids": null,
|
16 |
+
"begin_suppress_tokens": null,
|
17 |
+
"bos_token_id": 0,
|
18 |
+
"chunk_size_feed_forward": 0,
|
19 |
+
"cross_attention_hidden_size": null,
|
20 |
+
"decoder_start_token_id": null,
|
21 |
+
"dropout": 0,
|
22 |
+
"early_stopping": false,
|
23 |
+
"embed_dim": 1536,
|
24 |
+
"pad_token_id": 1,
|
25 |
+
"eos_token_id": 2,
|
26 |
+
"exponential_decay_length_penalty": null,
|
27 |
+
"ffn_dim": 6144,
|
28 |
+
"finetuning_task": null,
|
29 |
+
"forced_bos_token_id": null,
|
30 |
+
"forced_eos_token_id": null,
|
31 |
+
"id2label": {
|
32 |
+
"0": "LABEL_0",
|
33 |
+
"1": "LABEL_1"
|
34 |
+
},
|
35 |
+
"init_std": 0.02,
|
36 |
+
"is_decoder": false,
|
37 |
+
"is_encoder_decoder": false,
|
38 |
+
"label2id": {
|
39 |
+
"LABEL_0": 0,
|
40 |
+
"LABEL_1": 1
|
41 |
+
},
|
42 |
+
"layer_norm_eps": 1e-05,
|
43 |
+
"layerdrop": 0.0,
|
44 |
+
"layers": 24,
|
45 |
+
"max_length": 20,
|
46 |
+
"max_position_embeddings": 4096,
|
47 |
+
"min_length": 0,
|
48 |
+
"model_type": "kosmos_2_5_text_model",
|
49 |
+
"num_return_sequences": 1,
|
50 |
+
"output_attentions": false,
|
51 |
+
"output_hidden_states": false,
|
52 |
+
"output_scores": false,
|
53 |
+
"prefix": null,
|
54 |
+
"problem_type": null,
|
55 |
+
"pruned_heads": {},
|
56 |
+
"remove_invalid_values": false,
|
57 |
+
"return_dict": true,
|
58 |
+
"return_dict_in_generate": false,
|
59 |
+
"scale_embedding": true,
|
60 |
+
"sep_token_id": null,
|
61 |
+
"suppress_tokens": null,
|
62 |
+
"task_specific_params": null,
|
63 |
+
"tf_legacy_loss": false,
|
64 |
+
"tie_encoder_decoder": false,
|
65 |
+
"tie_word_embeddings": true,
|
66 |
+
"tokenizer_class": null,
|
67 |
+
"torch_dtype": null,
|
68 |
+
"torchscript": false,
|
69 |
+
"use_bfloat16": false,
|
70 |
+
"use_cache": true,
|
71 |
+
"vocab_size": 108481
|
72 |
+
},
|
73 |
+
"torch_dtype": "float32",
|
74 |
+
"transformers_version": "4.42.0.dev0",
|
75 |
+
"vision_config": {
|
76 |
+
"_name_or_path": "",
|
77 |
+
"add_cross_attention": false,
|
78 |
+
"architectures": null,
|
79 |
+
"attention_dropout": 0.0,
|
80 |
+
"bad_words_ids": null,
|
81 |
+
"begin_suppress_tokens": null,
|
82 |
+
"bos_token_id": null,
|
83 |
+
"chunk_size_feed_forward": 0,
|
84 |
+
"cross_attention_hidden_size": null,
|
85 |
+
"d_ff": 3968,
|
86 |
+
"d_kv": 64,
|
87 |
+
"decoder_start_token_id": null,
|
88 |
+
"dense_act_fn": "gelu_new",
|
89 |
+
"diversity_penalty": 0.0,
|
90 |
+
"do_sample": false,
|
91 |
+
"dropout_rate": 0.0,
|
92 |
+
"early_stopping": false,
|
93 |
+
"encoder_no_repeat_ngram_size": 0,
|
94 |
+
"eos_token_id": null,
|
95 |
+
"exponential_decay_length_penalty": null,
|
96 |
+
"finetuning_task": null,
|
97 |
+
"forced_bos_token_id": null,
|
98 |
+
"forced_eos_token_id": null,
|
99 |
+
"hidden_size": 1536,
|
100 |
+
"id2label": {
|
101 |
+
"0": "LABEL_0",
|
102 |
+
"1": "LABEL_1"
|
103 |
+
},
|
104 |
+
"initializer_factor": 1.0,
|
105 |
+
"initializer_range": 1e-10,
|
106 |
+
"is_decoder": false,
|
107 |
+
"is_encoder_decoder": false,
|
108 |
+
"label2id": {
|
109 |
+
"LABEL_0": 0,
|
110 |
+
"LABEL_1": 1
|
111 |
+
},
|
112 |
+
"layer_norm_eps": 1e-06,
|
113 |
+
"length_penalty": 1.0,
|
114 |
+
"max_length": 4096,
|
115 |
+
"min_length": 0,
|
116 |
+
"model_type": "kosmos_2_5_vision_model",
|
117 |
+
"no_repeat_ngram_size": 0,
|
118 |
+
"num_attention_heads": 24,
|
119 |
+
"num_beam_groups": 1,
|
120 |
+
"num_beams": 1,
|
121 |
+
"num_hidden_layers": 18,
|
122 |
+
"num_return_sequences": 1,
|
123 |
+
"output_attentions": false,
|
124 |
+
"output_hidden_states": false,
|
125 |
+
"output_scores": false,
|
126 |
+
"pad_token_id": null,
|
127 |
+
"patch_embed_hidden_size": 768,
|
128 |
+
"prefix": null,
|
129 |
+
"problem_type": null,
|
130 |
+
"pruned_heads": {},
|
131 |
+
"remove_invalid_values": false,
|
132 |
+
"repetition_penalty": 1.0,
|
133 |
+
"return_dict": true,
|
134 |
+
"return_dict_in_generate": false,
|
135 |
+
"sep_token_id": null,
|
136 |
+
"seq_len": 4096,
|
137 |
+
"suppress_tokens": null,
|
138 |
+
"task_specific_params": null,
|
139 |
+
"temperature": 1.0,
|
140 |
+
"tf_legacy_loss": false,
|
141 |
+
"tie_encoder_decoder": false,
|
142 |
+
"tie_word_embeddings": true,
|
143 |
+
"tokenizer_class": null,
|
144 |
+
"top_k": 50,
|
145 |
+
"top_p": 1.0,
|
146 |
+
"torch_dtype": null,
|
147 |
+
"torchscript": false,
|
148 |
+
"typical_p": 1.0,
|
149 |
+
"use_bfloat16": false
|
150 |
+
}
|
151 |
+
}
|
generation_config.json
CHANGED
@@ -1,3 +1,9 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": false,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.42.0.dev0",
|
7 |
+
"num_beam" : 1,
|
8 |
+
"do_sample": false
|
9 |
+
}
|
md.py
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import re
|
2 |
+
import torch
|
3 |
+
import requests
|
4 |
+
from PIL import Image, ImageDraw
|
5 |
+
from transformers import AutoProcessor, Kosmos2_5ForConditionalGeneration
|
6 |
+
|
7 |
+
repo = "microsoft/kosmos-2.5" #
|
8 |
+
repo = "kirp/kosmos2_5"
|
9 |
+
device = "cuda:0"
|
10 |
+
dtype = torch.bfloat16
|
11 |
+
model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=device, torch_dtype=dtype)
|
12 |
+
processor = AutoProcessor.from_pretrained(repo)
|
13 |
+
|
14 |
+
url = "https://huggingface.co/kirp/kosmos2_5/resolve/main/receipt_00008.png"
|
15 |
+
image = Image.open(requests.get(url, stream=True).raw)
|
16 |
+
prompt = "<md>"
|
17 |
+
inputs = processor(text=prompt, images=image, return_tensors="pt")
|
18 |
+
|
19 |
+
height, width = inputs.pop("height"), inputs.pop("width")
|
20 |
+
raw_width, raw_height = image.size
|
21 |
+
scale_height = raw_height / height
|
22 |
+
scale_width = raw_width / width
|
23 |
+
|
24 |
+
inputs = {k: v.to(device) if v is not None else None for k, v in inputs.items()}
|
25 |
+
inputs["flattened_patches"] = inputs["flattened_patches"].to(dtype)
|
26 |
+
generated_ids = model.generate(
|
27 |
+
**inputs,
|
28 |
+
max_new_tokens=1024,
|
29 |
+
)
|
30 |
+
|
31 |
+
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
|
32 |
+
print(generated_text[0])
|
model.safetensors.index.json
CHANGED
@@ -1,3 +1,621 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 5498585088
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"image_to_text_projection.dense.bias": "model-00002-of-00002.safetensors",
|
7 |
+
"image_to_text_projection.dense.weight": "model-00002-of-00002.safetensors",
|
8 |
+
"image_to_text_projection.latent_query": "model-00002-of-00002.safetensors",
|
9 |
+
"image_to_text_projection.x_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
10 |
+
"image_to_text_projection.x_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
11 |
+
"image_to_text_projection.x_attn.out_proj.bias": "model-00002-of-00002.safetensors",
|
12 |
+
"image_to_text_projection.x_attn.out_proj.weight": "model-00002-of-00002.safetensors",
|
13 |
+
"image_to_text_projection.x_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
14 |
+
"image_to_text_projection.x_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
15 |
+
"image_to_text_projection.x_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
16 |
+
"image_to_text_projection.x_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
17 |
+
"text_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
18 |
+
"text_model.model.layer_norm.bias": "model-00001-of-00002.safetensors",
|
19 |
+
"text_model.model.layer_norm.weight": "model-00001-of-00002.safetensors",
|
20 |
+
"text_model.model.layers.0.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
21 |
+
"text_model.model.layers.0.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
22 |
+
"text_model.model.layers.0.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
23 |
+
"text_model.model.layers.0.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
24 |
+
"text_model.model.layers.0.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
25 |
+
"text_model.model.layers.0.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
26 |
+
"text_model.model.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
27 |
+
"text_model.model.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
28 |
+
"text_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
29 |
+
"text_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
30 |
+
"text_model.model.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
31 |
+
"text_model.model.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
32 |
+
"text_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
33 |
+
"text_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
34 |
+
"text_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
35 |
+
"text_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
36 |
+
"text_model.model.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
37 |
+
"text_model.model.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
38 |
+
"text_model.model.layers.1.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
39 |
+
"text_model.model.layers.1.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
40 |
+
"text_model.model.layers.1.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
41 |
+
"text_model.model.layers.1.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
42 |
+
"text_model.model.layers.1.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
43 |
+
"text_model.model.layers.1.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
44 |
+
"text_model.model.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
45 |
+
"text_model.model.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
46 |
+
"text_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
47 |
+
"text_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
48 |
+
"text_model.model.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
49 |
+
"text_model.model.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
50 |
+
"text_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
51 |
+
"text_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
52 |
+
"text_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
53 |
+
"text_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
54 |
+
"text_model.model.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
55 |
+
"text_model.model.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
56 |
+
"text_model.model.layers.10.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
57 |
+
"text_model.model.layers.10.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
58 |
+
"text_model.model.layers.10.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
59 |
+
"text_model.model.layers.10.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
60 |
+
"text_model.model.layers.10.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
61 |
+
"text_model.model.layers.10.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
62 |
+
"text_model.model.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
63 |
+
"text_model.model.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
64 |
+
"text_model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
65 |
+
"text_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
66 |
+
"text_model.model.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
67 |
+
"text_model.model.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
68 |
+
"text_model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
69 |
+
"text_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
70 |
+
"text_model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
71 |
+
"text_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
72 |
+
"text_model.model.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
73 |
+
"text_model.model.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
74 |
+
"text_model.model.layers.11.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
75 |
+
"text_model.model.layers.11.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
76 |
+
"text_model.model.layers.11.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
77 |
+
"text_model.model.layers.11.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
78 |
+
"text_model.model.layers.11.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
79 |
+
"text_model.model.layers.11.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
80 |
+
"text_model.model.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
81 |
+
"text_model.model.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
82 |
+
"text_model.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
83 |
+
"text_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
84 |
+
"text_model.model.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
85 |
+
"text_model.model.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
86 |
+
"text_model.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
87 |
+
"text_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
88 |
+
"text_model.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
89 |
+
"text_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
90 |
+
"text_model.model.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
91 |
+
"text_model.model.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
92 |
+
"text_model.model.layers.12.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
93 |
+
"text_model.model.layers.12.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
94 |
+
"text_model.model.layers.12.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
95 |
+
"text_model.model.layers.12.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
96 |
+
"text_model.model.layers.12.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
97 |
+
"text_model.model.layers.12.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
98 |
+
"text_model.model.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
99 |
+
"text_model.model.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
100 |
+
"text_model.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
101 |
+
"text_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
102 |
+
"text_model.model.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
103 |
+
"text_model.model.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
104 |
+
"text_model.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
105 |
+
"text_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
106 |
+
"text_model.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
107 |
+
"text_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
108 |
+
"text_model.model.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
109 |
+
"text_model.model.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
110 |
+
"text_model.model.layers.13.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
111 |
+
"text_model.model.layers.13.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
112 |
+
"text_model.model.layers.13.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
113 |
+
"text_model.model.layers.13.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
114 |
+
"text_model.model.layers.13.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
115 |
+
"text_model.model.layers.13.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
116 |
+
"text_model.model.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
117 |
+
"text_model.model.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
118 |
+
"text_model.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
119 |
+
"text_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
120 |
+
"text_model.model.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
121 |
+
"text_model.model.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
122 |
+
"text_model.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
123 |
+
"text_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
124 |
+
"text_model.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
125 |
+
"text_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
126 |
+
"text_model.model.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
127 |
+
"text_model.model.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
128 |
+
"text_model.model.layers.14.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
129 |
+
"text_model.model.layers.14.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
130 |
+
"text_model.model.layers.14.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
131 |
+
"text_model.model.layers.14.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
132 |
+
"text_model.model.layers.14.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
133 |
+
"text_model.model.layers.14.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
134 |
+
"text_model.model.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
135 |
+
"text_model.model.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
136 |
+
"text_model.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
137 |
+
"text_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
138 |
+
"text_model.model.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
139 |
+
"text_model.model.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
140 |
+
"text_model.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
141 |
+
"text_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
142 |
+
"text_model.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
143 |
+
"text_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
144 |
+
"text_model.model.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
145 |
+
"text_model.model.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
146 |
+
"text_model.model.layers.15.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
147 |
+
"text_model.model.layers.15.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
148 |
+
"text_model.model.layers.15.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
149 |
+
"text_model.model.layers.15.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
150 |
+
"text_model.model.layers.15.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
151 |
+
"text_model.model.layers.15.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
152 |
+
"text_model.model.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
153 |
+
"text_model.model.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
154 |
+
"text_model.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
155 |
+
"text_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
156 |
+
"text_model.model.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
157 |
+
"text_model.model.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
158 |
+
"text_model.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
159 |
+
"text_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
160 |
+
"text_model.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
161 |
+
"text_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
162 |
+
"text_model.model.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
163 |
+
"text_model.model.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
164 |
+
"text_model.model.layers.16.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
165 |
+
"text_model.model.layers.16.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
166 |
+
"text_model.model.layers.16.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
167 |
+
"text_model.model.layers.16.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
168 |
+
"text_model.model.layers.16.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
169 |
+
"text_model.model.layers.16.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
170 |
+
"text_model.model.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
171 |
+
"text_model.model.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
172 |
+
"text_model.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
173 |
+
"text_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
174 |
+
"text_model.model.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
175 |
+
"text_model.model.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
176 |
+
"text_model.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
177 |
+
"text_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
178 |
+
"text_model.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
179 |
+
"text_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
180 |
+
"text_model.model.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
181 |
+
"text_model.model.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
182 |
+
"text_model.model.layers.17.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
183 |
+
"text_model.model.layers.17.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
184 |
+
"text_model.model.layers.17.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
185 |
+
"text_model.model.layers.17.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
186 |
+
"text_model.model.layers.17.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
187 |
+
"text_model.model.layers.17.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
188 |
+
"text_model.model.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
189 |
+
"text_model.model.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
190 |
+
"text_model.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
191 |
+
"text_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
192 |
+
"text_model.model.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
193 |
+
"text_model.model.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
194 |
+
"text_model.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
195 |
+
"text_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
196 |
+
"text_model.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
197 |
+
"text_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
198 |
+
"text_model.model.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
199 |
+
"text_model.model.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
200 |
+
"text_model.model.layers.18.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
201 |
+
"text_model.model.layers.18.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
202 |
+
"text_model.model.layers.18.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
203 |
+
"text_model.model.layers.18.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
204 |
+
"text_model.model.layers.18.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
205 |
+
"text_model.model.layers.18.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
206 |
+
"text_model.model.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
207 |
+
"text_model.model.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
208 |
+
"text_model.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
209 |
+
"text_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
210 |
+
"text_model.model.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
211 |
+
"text_model.model.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
212 |
+
"text_model.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
213 |
+
"text_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
214 |
+
"text_model.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
215 |
+
"text_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
216 |
+
"text_model.model.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
217 |
+
"text_model.model.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
218 |
+
"text_model.model.layers.19.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
219 |
+
"text_model.model.layers.19.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
220 |
+
"text_model.model.layers.19.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
221 |
+
"text_model.model.layers.19.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
222 |
+
"text_model.model.layers.19.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
223 |
+
"text_model.model.layers.19.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
224 |
+
"text_model.model.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
225 |
+
"text_model.model.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
226 |
+
"text_model.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
227 |
+
"text_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
228 |
+
"text_model.model.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
229 |
+
"text_model.model.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
230 |
+
"text_model.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
231 |
+
"text_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
232 |
+
"text_model.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
233 |
+
"text_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
234 |
+
"text_model.model.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
235 |
+
"text_model.model.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
236 |
+
"text_model.model.layers.2.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
237 |
+
"text_model.model.layers.2.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
238 |
+
"text_model.model.layers.2.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
239 |
+
"text_model.model.layers.2.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
240 |
+
"text_model.model.layers.2.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
241 |
+
"text_model.model.layers.2.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
242 |
+
"text_model.model.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
243 |
+
"text_model.model.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
244 |
+
"text_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
245 |
+
"text_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
246 |
+
"text_model.model.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
247 |
+
"text_model.model.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
248 |
+
"text_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
249 |
+
"text_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
250 |
+
"text_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
251 |
+
"text_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
252 |
+
"text_model.model.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
253 |
+
"text_model.model.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
254 |
+
"text_model.model.layers.20.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
255 |
+
"text_model.model.layers.20.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
256 |
+
"text_model.model.layers.20.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
257 |
+
"text_model.model.layers.20.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
258 |
+
"text_model.model.layers.20.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
259 |
+
"text_model.model.layers.20.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
260 |
+
"text_model.model.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
261 |
+
"text_model.model.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
262 |
+
"text_model.model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
263 |
+
"text_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
264 |
+
"text_model.model.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
265 |
+
"text_model.model.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
266 |
+
"text_model.model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
267 |
+
"text_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
268 |
+
"text_model.model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
269 |
+
"text_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
270 |
+
"text_model.model.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
271 |
+
"text_model.model.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
272 |
+
"text_model.model.layers.21.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
273 |
+
"text_model.model.layers.21.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
274 |
+
"text_model.model.layers.21.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
275 |
+
"text_model.model.layers.21.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
276 |
+
"text_model.model.layers.21.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
277 |
+
"text_model.model.layers.21.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
278 |
+
"text_model.model.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
279 |
+
"text_model.model.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
280 |
+
"text_model.model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
281 |
+
"text_model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
282 |
+
"text_model.model.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
283 |
+
"text_model.model.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
284 |
+
"text_model.model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
285 |
+
"text_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
286 |
+
"text_model.model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
287 |
+
"text_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
288 |
+
"text_model.model.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
289 |
+
"text_model.model.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
290 |
+
"text_model.model.layers.22.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
291 |
+
"text_model.model.layers.22.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
292 |
+
"text_model.model.layers.22.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
293 |
+
"text_model.model.layers.22.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
294 |
+
"text_model.model.layers.22.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
295 |
+
"text_model.model.layers.22.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
296 |
+
"text_model.model.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
297 |
+
"text_model.model.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
298 |
+
"text_model.model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
299 |
+
"text_model.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
300 |
+
"text_model.model.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
301 |
+
"text_model.model.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
302 |
+
"text_model.model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
303 |
+
"text_model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
304 |
+
"text_model.model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
305 |
+
"text_model.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
306 |
+
"text_model.model.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
307 |
+
"text_model.model.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
308 |
+
"text_model.model.layers.23.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
309 |
+
"text_model.model.layers.23.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
310 |
+
"text_model.model.layers.23.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
311 |
+
"text_model.model.layers.23.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
312 |
+
"text_model.model.layers.23.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
313 |
+
"text_model.model.layers.23.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
314 |
+
"text_model.model.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
315 |
+
"text_model.model.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
316 |
+
"text_model.model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
317 |
+
"text_model.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
318 |
+
"text_model.model.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
319 |
+
"text_model.model.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
320 |
+
"text_model.model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
321 |
+
"text_model.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
322 |
+
"text_model.model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
323 |
+
"text_model.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
324 |
+
"text_model.model.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
325 |
+
"text_model.model.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
326 |
+
"text_model.model.layers.3.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
327 |
+
"text_model.model.layers.3.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
328 |
+
"text_model.model.layers.3.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
329 |
+
"text_model.model.layers.3.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
330 |
+
"text_model.model.layers.3.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
331 |
+
"text_model.model.layers.3.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
332 |
+
"text_model.model.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
333 |
+
"text_model.model.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
334 |
+
"text_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
335 |
+
"text_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
336 |
+
"text_model.model.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
337 |
+
"text_model.model.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
338 |
+
"text_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
339 |
+
"text_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
340 |
+
"text_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
341 |
+
"text_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
342 |
+
"text_model.model.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
343 |
+
"text_model.model.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
344 |
+
"text_model.model.layers.4.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
345 |
+
"text_model.model.layers.4.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
346 |
+
"text_model.model.layers.4.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
347 |
+
"text_model.model.layers.4.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
348 |
+
"text_model.model.layers.4.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
349 |
+
"text_model.model.layers.4.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
350 |
+
"text_model.model.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
351 |
+
"text_model.model.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
352 |
+
"text_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
353 |
+
"text_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
354 |
+
"text_model.model.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
355 |
+
"text_model.model.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
356 |
+
"text_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
357 |
+
"text_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
358 |
+
"text_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
359 |
+
"text_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
360 |
+
"text_model.model.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
361 |
+
"text_model.model.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
362 |
+
"text_model.model.layers.5.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
363 |
+
"text_model.model.layers.5.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
364 |
+
"text_model.model.layers.5.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
365 |
+
"text_model.model.layers.5.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
366 |
+
"text_model.model.layers.5.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
367 |
+
"text_model.model.layers.5.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
368 |
+
"text_model.model.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
369 |
+
"text_model.model.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
370 |
+
"text_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
371 |
+
"text_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
372 |
+
"text_model.model.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
373 |
+
"text_model.model.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
374 |
+
"text_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
375 |
+
"text_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
376 |
+
"text_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
377 |
+
"text_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
378 |
+
"text_model.model.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
379 |
+
"text_model.model.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
380 |
+
"text_model.model.layers.6.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
381 |
+
"text_model.model.layers.6.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
382 |
+
"text_model.model.layers.6.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
383 |
+
"text_model.model.layers.6.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
384 |
+
"text_model.model.layers.6.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
385 |
+
"text_model.model.layers.6.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
386 |
+
"text_model.model.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
387 |
+
"text_model.model.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
388 |
+
"text_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
389 |
+
"text_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
390 |
+
"text_model.model.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
391 |
+
"text_model.model.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
392 |
+
"text_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
393 |
+
"text_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
394 |
+
"text_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
395 |
+
"text_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
396 |
+
"text_model.model.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
397 |
+
"text_model.model.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
398 |
+
"text_model.model.layers.7.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
399 |
+
"text_model.model.layers.7.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
400 |
+
"text_model.model.layers.7.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
401 |
+
"text_model.model.layers.7.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
402 |
+
"text_model.model.layers.7.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
403 |
+
"text_model.model.layers.7.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
404 |
+
"text_model.model.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
405 |
+
"text_model.model.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
406 |
+
"text_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
407 |
+
"text_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
408 |
+
"text_model.model.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
409 |
+
"text_model.model.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
410 |
+
"text_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
411 |
+
"text_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
412 |
+
"text_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
413 |
+
"text_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
414 |
+
"text_model.model.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
415 |
+
"text_model.model.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
416 |
+
"text_model.model.layers.8.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
417 |
+
"text_model.model.layers.8.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
418 |
+
"text_model.model.layers.8.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
419 |
+
"text_model.model.layers.8.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
420 |
+
"text_model.model.layers.8.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
421 |
+
"text_model.model.layers.8.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
422 |
+
"text_model.model.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
423 |
+
"text_model.model.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
424 |
+
"text_model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
425 |
+
"text_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
426 |
+
"text_model.model.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
427 |
+
"text_model.model.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
428 |
+
"text_model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
429 |
+
"text_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
430 |
+
"text_model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
431 |
+
"text_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
432 |
+
"text_model.model.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
433 |
+
"text_model.model.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
434 |
+
"text_model.model.layers.9.ffn.fc1.bias": "model-00001-of-00002.safetensors",
|
435 |
+
"text_model.model.layers.9.ffn.fc1.weight": "model-00001-of-00002.safetensors",
|
436 |
+
"text_model.model.layers.9.ffn.fc2.bias": "model-00001-of-00002.safetensors",
|
437 |
+
"text_model.model.layers.9.ffn.fc2.weight": "model-00001-of-00002.safetensors",
|
438 |
+
"text_model.model.layers.9.ffn.ffn_layernorm.bias": "model-00001-of-00002.safetensors",
|
439 |
+
"text_model.model.layers.9.ffn.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
|
440 |
+
"text_model.model.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
441 |
+
"text_model.model.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
442 |
+
"text_model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
443 |
+
"text_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
444 |
+
"text_model.model.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
445 |
+
"text_model.model.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
446 |
+
"text_model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
447 |
+
"text_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
448 |
+
"text_model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
449 |
+
"text_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
450 |
+
"text_model.model.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
451 |
+
"text_model.model.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
452 |
+
"text_model.model.segment_emb.weight": "model-00001-of-00002.safetensors",
|
453 |
+
"vision_model.embeddings.column_embedder.weight": "model-00001-of-00002.safetensors",
|
454 |
+
"vision_model.embeddings.patch_projection.bias": "model-00001-of-00002.safetensors",
|
455 |
+
"vision_model.embeddings.patch_projection.weight": "model-00001-of-00002.safetensors",
|
456 |
+
"vision_model.embeddings.row_embedder.weight": "model-00001-of-00002.safetensors",
|
457 |
+
"vision_model.encoder.layer.0.attention.key.weight": "model-00001-of-00002.safetensors",
|
458 |
+
"vision_model.encoder.layer.0.attention.output.weight": "model-00001-of-00002.safetensors",
|
459 |
+
"vision_model.encoder.layer.0.attention.query.weight": "model-00001-of-00002.safetensors",
|
460 |
+
"vision_model.encoder.layer.0.attention.value.weight": "model-00001-of-00002.safetensors",
|
461 |
+
"vision_model.encoder.layer.0.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
462 |
+
"vision_model.encoder.layer.0.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
463 |
+
"vision_model.encoder.layer.0.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
464 |
+
"vision_model.encoder.layer.0.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
465 |
+
"vision_model.encoder.layer.0.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
466 |
+
"vision_model.encoder.layer.1.attention.key.weight": "model-00001-of-00002.safetensors",
|
467 |
+
"vision_model.encoder.layer.1.attention.output.weight": "model-00001-of-00002.safetensors",
|
468 |
+
"vision_model.encoder.layer.1.attention.query.weight": "model-00001-of-00002.safetensors",
|
469 |
+
"vision_model.encoder.layer.1.attention.value.weight": "model-00001-of-00002.safetensors",
|
470 |
+
"vision_model.encoder.layer.1.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
471 |
+
"vision_model.encoder.layer.1.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
472 |
+
"vision_model.encoder.layer.1.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
473 |
+
"vision_model.encoder.layer.1.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
474 |
+
"vision_model.encoder.layer.1.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
475 |
+
"vision_model.encoder.layer.10.attention.key.weight": "model-00001-of-00002.safetensors",
|
476 |
+
"vision_model.encoder.layer.10.attention.output.weight": "model-00001-of-00002.safetensors",
|
477 |
+
"vision_model.encoder.layer.10.attention.query.weight": "model-00001-of-00002.safetensors",
|
478 |
+
"vision_model.encoder.layer.10.attention.value.weight": "model-00001-of-00002.safetensors",
|
479 |
+
"vision_model.encoder.layer.10.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
480 |
+
"vision_model.encoder.layer.10.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
481 |
+
"vision_model.encoder.layer.10.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
482 |
+
"vision_model.encoder.layer.10.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
483 |
+
"vision_model.encoder.layer.10.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
484 |
+
"vision_model.encoder.layer.11.attention.key.weight": "model-00001-of-00002.safetensors",
|
485 |
+
"vision_model.encoder.layer.11.attention.output.weight": "model-00001-of-00002.safetensors",
|
486 |
+
"vision_model.encoder.layer.11.attention.query.weight": "model-00001-of-00002.safetensors",
|
487 |
+
"vision_model.encoder.layer.11.attention.value.weight": "model-00001-of-00002.safetensors",
|
488 |
+
"vision_model.encoder.layer.11.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
489 |
+
"vision_model.encoder.layer.11.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
490 |
+
"vision_model.encoder.layer.11.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
491 |
+
"vision_model.encoder.layer.11.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
492 |
+
"vision_model.encoder.layer.11.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
493 |
+
"vision_model.encoder.layer.12.attention.key.weight": "model-00001-of-00002.safetensors",
|
494 |
+
"vision_model.encoder.layer.12.attention.output.weight": "model-00001-of-00002.safetensors",
|
495 |
+
"vision_model.encoder.layer.12.attention.query.weight": "model-00001-of-00002.safetensors",
|
496 |
+
"vision_model.encoder.layer.12.attention.value.weight": "model-00001-of-00002.safetensors",
|
497 |
+
"vision_model.encoder.layer.12.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
498 |
+
"vision_model.encoder.layer.12.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
499 |
+
"vision_model.encoder.layer.12.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
500 |
+
"vision_model.encoder.layer.12.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
501 |
+
"vision_model.encoder.layer.12.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
502 |
+
"vision_model.encoder.layer.13.attention.key.weight": "model-00001-of-00002.safetensors",
|
503 |
+
"vision_model.encoder.layer.13.attention.output.weight": "model-00001-of-00002.safetensors",
|
504 |
+
"vision_model.encoder.layer.13.attention.query.weight": "model-00001-of-00002.safetensors",
|
505 |
+
"vision_model.encoder.layer.13.attention.value.weight": "model-00001-of-00002.safetensors",
|
506 |
+
"vision_model.encoder.layer.13.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
507 |
+
"vision_model.encoder.layer.13.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
508 |
+
"vision_model.encoder.layer.13.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
509 |
+
"vision_model.encoder.layer.13.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
510 |
+
"vision_model.encoder.layer.13.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
511 |
+
"vision_model.encoder.layer.14.attention.key.weight": "model-00002-of-00002.safetensors",
|
512 |
+
"vision_model.encoder.layer.14.attention.output.weight": "model-00002-of-00002.safetensors",
|
513 |
+
"vision_model.encoder.layer.14.attention.query.weight": "model-00002-of-00002.safetensors",
|
514 |
+
"vision_model.encoder.layer.14.attention.value.weight": "model-00002-of-00002.safetensors",
|
515 |
+
"vision_model.encoder.layer.14.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
|
516 |
+
"vision_model.encoder.layer.14.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
|
517 |
+
"vision_model.encoder.layer.14.mlp.wo.weight": "model-00002-of-00002.safetensors",
|
518 |
+
"vision_model.encoder.layer.14.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
|
519 |
+
"vision_model.encoder.layer.14.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
|
520 |
+
"vision_model.encoder.layer.15.attention.key.weight": "model-00002-of-00002.safetensors",
|
521 |
+
"vision_model.encoder.layer.15.attention.output.weight": "model-00002-of-00002.safetensors",
|
522 |
+
"vision_model.encoder.layer.15.attention.query.weight": "model-00002-of-00002.safetensors",
|
523 |
+
"vision_model.encoder.layer.15.attention.value.weight": "model-00002-of-00002.safetensors",
|
524 |
+
"vision_model.encoder.layer.15.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
|
525 |
+
"vision_model.encoder.layer.15.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
|
526 |
+
"vision_model.encoder.layer.15.mlp.wo.weight": "model-00002-of-00002.safetensors",
|
527 |
+
"vision_model.encoder.layer.15.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
|
528 |
+
"vision_model.encoder.layer.15.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
|
529 |
+
"vision_model.encoder.layer.16.attention.key.weight": "model-00002-of-00002.safetensors",
|
530 |
+
"vision_model.encoder.layer.16.attention.output.weight": "model-00002-of-00002.safetensors",
|
531 |
+
"vision_model.encoder.layer.16.attention.query.weight": "model-00002-of-00002.safetensors",
|
532 |
+
"vision_model.encoder.layer.16.attention.value.weight": "model-00002-of-00002.safetensors",
|
533 |
+
"vision_model.encoder.layer.16.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
|
534 |
+
"vision_model.encoder.layer.16.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
|
535 |
+
"vision_model.encoder.layer.16.mlp.wo.weight": "model-00002-of-00002.safetensors",
|
536 |
+
"vision_model.encoder.layer.16.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
|
537 |
+
"vision_model.encoder.layer.16.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
|
538 |
+
"vision_model.encoder.layer.17.attention.key.weight": "model-00002-of-00002.safetensors",
|
539 |
+
"vision_model.encoder.layer.17.attention.output.weight": "model-00002-of-00002.safetensors",
|
540 |
+
"vision_model.encoder.layer.17.attention.query.weight": "model-00002-of-00002.safetensors",
|
541 |
+
"vision_model.encoder.layer.17.attention.value.weight": "model-00002-of-00002.safetensors",
|
542 |
+
"vision_model.encoder.layer.17.mlp.wi_0.weight": "model-00002-of-00002.safetensors",
|
543 |
+
"vision_model.encoder.layer.17.mlp.wi_1.weight": "model-00002-of-00002.safetensors",
|
544 |
+
"vision_model.encoder.layer.17.mlp.wo.weight": "model-00002-of-00002.safetensors",
|
545 |
+
"vision_model.encoder.layer.17.pre_attention_layer_norm.weight": "model-00002-of-00002.safetensors",
|
546 |
+
"vision_model.encoder.layer.17.pre_mlp_layer_norm.weight": "model-00002-of-00002.safetensors",
|
547 |
+
"vision_model.encoder.layer.2.attention.key.weight": "model-00001-of-00002.safetensors",
|
548 |
+
"vision_model.encoder.layer.2.attention.output.weight": "model-00001-of-00002.safetensors",
|
549 |
+
"vision_model.encoder.layer.2.attention.query.weight": "model-00001-of-00002.safetensors",
|
550 |
+
"vision_model.encoder.layer.2.attention.value.weight": "model-00001-of-00002.safetensors",
|
551 |
+
"vision_model.encoder.layer.2.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
552 |
+
"vision_model.encoder.layer.2.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
553 |
+
"vision_model.encoder.layer.2.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
554 |
+
"vision_model.encoder.layer.2.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
555 |
+
"vision_model.encoder.layer.2.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
556 |
+
"vision_model.encoder.layer.3.attention.key.weight": "model-00001-of-00002.safetensors",
|
557 |
+
"vision_model.encoder.layer.3.attention.output.weight": "model-00001-of-00002.safetensors",
|
558 |
+
"vision_model.encoder.layer.3.attention.query.weight": "model-00001-of-00002.safetensors",
|
559 |
+
"vision_model.encoder.layer.3.attention.value.weight": "model-00001-of-00002.safetensors",
|
560 |
+
"vision_model.encoder.layer.3.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
561 |
+
"vision_model.encoder.layer.3.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
562 |
+
"vision_model.encoder.layer.3.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
563 |
+
"vision_model.encoder.layer.3.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
564 |
+
"vision_model.encoder.layer.3.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
565 |
+
"vision_model.encoder.layer.4.attention.key.weight": "model-00001-of-00002.safetensors",
|
566 |
+
"vision_model.encoder.layer.4.attention.output.weight": "model-00001-of-00002.safetensors",
|
567 |
+
"vision_model.encoder.layer.4.attention.query.weight": "model-00001-of-00002.safetensors",
|
568 |
+
"vision_model.encoder.layer.4.attention.value.weight": "model-00001-of-00002.safetensors",
|
569 |
+
"vision_model.encoder.layer.4.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
570 |
+
"vision_model.encoder.layer.4.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
571 |
+
"vision_model.encoder.layer.4.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
572 |
+
"vision_model.encoder.layer.4.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
573 |
+
"vision_model.encoder.layer.4.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
574 |
+
"vision_model.encoder.layer.5.attention.key.weight": "model-00001-of-00002.safetensors",
|
575 |
+
"vision_model.encoder.layer.5.attention.output.weight": "model-00001-of-00002.safetensors",
|
576 |
+
"vision_model.encoder.layer.5.attention.query.weight": "model-00001-of-00002.safetensors",
|
577 |
+
"vision_model.encoder.layer.5.attention.value.weight": "model-00001-of-00002.safetensors",
|
578 |
+
"vision_model.encoder.layer.5.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
579 |
+
"vision_model.encoder.layer.5.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
580 |
+
"vision_model.encoder.layer.5.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
581 |
+
"vision_model.encoder.layer.5.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
582 |
+
"vision_model.encoder.layer.5.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
583 |
+
"vision_model.encoder.layer.6.attention.key.weight": "model-00001-of-00002.safetensors",
|
584 |
+
"vision_model.encoder.layer.6.attention.output.weight": "model-00001-of-00002.safetensors",
|
585 |
+
"vision_model.encoder.layer.6.attention.query.weight": "model-00001-of-00002.safetensors",
|
586 |
+
"vision_model.encoder.layer.6.attention.value.weight": "model-00001-of-00002.safetensors",
|
587 |
+
"vision_model.encoder.layer.6.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
588 |
+
"vision_model.encoder.layer.6.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
589 |
+
"vision_model.encoder.layer.6.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
590 |
+
"vision_model.encoder.layer.6.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
591 |
+
"vision_model.encoder.layer.6.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
592 |
+
"vision_model.encoder.layer.7.attention.key.weight": "model-00001-of-00002.safetensors",
|
593 |
+
"vision_model.encoder.layer.7.attention.output.weight": "model-00001-of-00002.safetensors",
|
594 |
+
"vision_model.encoder.layer.7.attention.query.weight": "model-00001-of-00002.safetensors",
|
595 |
+
"vision_model.encoder.layer.7.attention.value.weight": "model-00001-of-00002.safetensors",
|
596 |
+
"vision_model.encoder.layer.7.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
597 |
+
"vision_model.encoder.layer.7.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
598 |
+
"vision_model.encoder.layer.7.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
599 |
+
"vision_model.encoder.layer.7.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
600 |
+
"vision_model.encoder.layer.7.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
601 |
+
"vision_model.encoder.layer.8.attention.key.weight": "model-00001-of-00002.safetensors",
|
602 |
+
"vision_model.encoder.layer.8.attention.output.weight": "model-00001-of-00002.safetensors",
|
603 |
+
"vision_model.encoder.layer.8.attention.query.weight": "model-00001-of-00002.safetensors",
|
604 |
+
"vision_model.encoder.layer.8.attention.value.weight": "model-00001-of-00002.safetensors",
|
605 |
+
"vision_model.encoder.layer.8.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
606 |
+
"vision_model.encoder.layer.8.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
607 |
+
"vision_model.encoder.layer.8.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
608 |
+
"vision_model.encoder.layer.8.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
609 |
+
"vision_model.encoder.layer.8.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
610 |
+
"vision_model.encoder.layer.9.attention.key.weight": "model-00001-of-00002.safetensors",
|
611 |
+
"vision_model.encoder.layer.9.attention.output.weight": "model-00001-of-00002.safetensors",
|
612 |
+
"vision_model.encoder.layer.9.attention.query.weight": "model-00001-of-00002.safetensors",
|
613 |
+
"vision_model.encoder.layer.9.attention.value.weight": "model-00001-of-00002.safetensors",
|
614 |
+
"vision_model.encoder.layer.9.mlp.wi_0.weight": "model-00001-of-00002.safetensors",
|
615 |
+
"vision_model.encoder.layer.9.mlp.wi_1.weight": "model-00001-of-00002.safetensors",
|
616 |
+
"vision_model.encoder.layer.9.mlp.wo.weight": "model-00001-of-00002.safetensors",
|
617 |
+
"vision_model.encoder.layer.9.pre_attention_layer_norm.weight": "model-00001-of-00002.safetensors",
|
618 |
+
"vision_model.encoder.layer.9.pre_mlp_layer_norm.weight": "model-00001-of-00002.safetensors",
|
619 |
+
"vision_model.layernorm.weight": "model-00002-of-00002.safetensors"
|
620 |
+
}
|
621 |
+
}
|
ocr.py
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import re
|
2 |
+
import torch
|
3 |
+
import requests
|
4 |
+
from PIL import Image, ImageDraw
|
5 |
+
from transformers import AutoProcessor, Kosmos2_5ForConditionalGeneration
|
6 |
+
|
7 |
+
|
8 |
+
repo = "microsoft/kosmos-2.5" #
|
9 |
+
repo = "kirp/kosmos2_5"
|
10 |
+
device = "cuda:0"
|
11 |
+
dtype = torch.bfloat16
|
12 |
+
model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=device, torch_dtype=dtype)
|
13 |
+
processor = AutoProcessor.from_pretrained(repo)
|
14 |
+
|
15 |
+
url = "https://huggingface.co/kirp/kosmos2_5/resolve/main/receipt_00008.png"
|
16 |
+
image = Image.open(requests.get(url, stream=True).raw)
|
17 |
+
prompt = "<ocr>"
|
18 |
+
inputs = processor(text=prompt, images=image, return_tensors="pt")
|
19 |
+
# batch input
|
20 |
+
# inputs = processor(text=[prompt, prompt], images=[image,image], return_tensors="pt")
|
21 |
+
|
22 |
+
height, width = inputs.pop("height"), inputs.pop("width")
|
23 |
+
raw_width, raw_height = image.size
|
24 |
+
scale_height = raw_height / height
|
25 |
+
scale_width = raw_width / width
|
26 |
+
|
27 |
+
inputs = {k: v.to(device) if v is not None else None for k, v in inputs.items()}
|
28 |
+
inputs["flattened_patches"] = inputs["flattened_patches"].to(dtype)
|
29 |
+
generated_ids = model.generate(
|
30 |
+
**inputs,
|
31 |
+
max_new_tokens=1024,
|
32 |
+
)
|
33 |
+
|
34 |
+
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
|
35 |
+
def post_process(y, scale_height, scale_width):
|
36 |
+
y = y.replace(prompt, "")
|
37 |
+
if "<md>" in prompt:
|
38 |
+
return y
|
39 |
+
pattern = r"<bbox><x_\d+><y_\d+><x_\d+><y_\d+></bbox>"
|
40 |
+
bboxs_raw = re.findall(pattern, y)
|
41 |
+
lines = re.split(pattern, y)[1:]
|
42 |
+
bboxs = [re.findall(r"\d+", i) for i in bboxs_raw]
|
43 |
+
bboxs = [[int(j) for j in i] for i in bboxs]
|
44 |
+
info = ""
|
45 |
+
for i in range(len(lines)):
|
46 |
+
box = bboxs[i]
|
47 |
+
x0, y0, x1, y1 = box
|
48 |
+
if not (x0 >= x1 or y0 >= y1):
|
49 |
+
x0 = int(x0 * scale_width)
|
50 |
+
y0 = int(y0 * scale_height)
|
51 |
+
x1 = int(x1 * scale_width)
|
52 |
+
y1 = int(y1 * scale_height)
|
53 |
+
info += f"{x0},{y0},{x1},{y0},{x1},{y1},{x0},{y1},{lines[i]}"
|
54 |
+
return info
|
55 |
+
|
56 |
+
output_text = post_process(generated_text[0], scale_height, scale_width)
|
57 |
+
print(output_text)
|
58 |
+
|
59 |
+
draw = ImageDraw.Draw(image)
|
60 |
+
lines = output_text.split("\n")
|
61 |
+
for line in lines:
|
62 |
+
# draw the bounding box
|
63 |
+
line = list(line.split(","))
|
64 |
+
if len(line) < 8:
|
65 |
+
continue
|
66 |
+
line = list(map(int, line[:8]))
|
67 |
+
draw.polygon(line, outline="red")
|
68 |
+
image.save("output.png")
|
output.png
ADDED
![]() |
Git LFS Details
|
preprocessor_config.json
CHANGED
@@ -1,3 +1,5 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"image_processor_type": "Kosmos2_5ImageProcessor",
|
3 |
+
"processor_class": "Kosmos2_5Processor"
|
4 |
+
}
|
5 |
+
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,3 +1,10 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": false,
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"model_max_length": 4096,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
9 |
+
"unk_token": "<unk>"
|
10 |
+
}
|