BleachNick
commited on
Commit
•
6a3ffbb
1
Parent(s):
a362f46
Upload StableDiffusion3InstructPix2PixPipeline
Browse files- README.md +198 -0
- model_index.json +41 -0
- scheduler/scheduler_config.json +6 -0
- text_encoder/config.json +25 -0
- text_encoder/model.safetensors +3 -0
- text_encoder_2/config.json +25 -0
- text_encoder_2/model.safetensors +3 -0
- text_encoder_3/config.json +32 -0
- text_encoder_3/model-00001-of-00004.safetensors +3 -0
- text_encoder_3/model-00002-of-00004.safetensors +3 -0
- text_encoder_3/model-00003-of-00004.safetensors +3 -0
- text_encoder_3/model-00004-of-00004.safetensors +3 -0
- text_encoder_3/model.safetensors.index.json +226 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +30 -0
- tokenizer/tokenizer_config.json +30 -0
- tokenizer/vocab.json +0 -0
- tokenizer_2/merges.txt +0 -0
- tokenizer_2/special_tokens_map.json +30 -0
- tokenizer_2/tokenizer_config.json +38 -0
- tokenizer_2/vocab.json +0 -0
- tokenizer_3/special_tokens_map.json +125 -0
- tokenizer_3/spiece.model +3 -0
- tokenizer_3/tokenizer.json +0 -0
- tokenizer_3/tokenizer_config.json +940 -0
- transformer/config.json +16 -0
- transformer/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +37 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,198 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: diffusers
|
3 |
+
---
|
4 |
+
|
5 |
+
# Model Card for Model ID
|
6 |
+
|
7 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
8 |
+
|
9 |
+
|
10 |
+
|
11 |
+
## Model Details
|
12 |
+
|
13 |
+
### Model Description
|
14 |
+
|
15 |
+
<!-- Provide a longer summary of what this model is. -->
|
16 |
+
|
17 |
+
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
|
18 |
+
|
19 |
+
- **Developed by:** [More Information Needed]
|
20 |
+
- **Funded by [optional]:** [More Information Needed]
|
21 |
+
- **Shared by [optional]:** [More Information Needed]
|
22 |
+
- **Model type:** [More Information Needed]
|
23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
24 |
+
- **License:** [More Information Needed]
|
25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
26 |
+
|
27 |
+
### Model Sources [optional]
|
28 |
+
|
29 |
+
<!-- Provide the basic links for the model. -->
|
30 |
+
|
31 |
+
- **Repository:** [More Information Needed]
|
32 |
+
- **Paper [optional]:** [More Information Needed]
|
33 |
+
- **Demo [optional]:** [More Information Needed]
|
34 |
+
|
35 |
+
## Uses
|
36 |
+
|
37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
38 |
+
|
39 |
+
### Direct Use
|
40 |
+
|
41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
42 |
+
|
43 |
+
[More Information Needed]
|
44 |
+
|
45 |
+
### Downstream Use [optional]
|
46 |
+
|
47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
48 |
+
|
49 |
+
[More Information Needed]
|
50 |
+
|
51 |
+
### Out-of-Scope Use
|
52 |
+
|
53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
54 |
+
|
55 |
+
[More Information Needed]
|
56 |
+
|
57 |
+
## Bias, Risks, and Limitations
|
58 |
+
|
59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
60 |
+
|
61 |
+
[More Information Needed]
|
62 |
+
|
63 |
+
### Recommendations
|
64 |
+
|
65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
66 |
+
|
67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
68 |
+
|
69 |
+
## How to Get Started with the Model
|
70 |
+
|
71 |
+
Use the code below to get started with the model.
|
72 |
+
|
73 |
+
[More Information Needed]
|
74 |
+
|
75 |
+
## Training Details
|
76 |
+
|
77 |
+
### Training Data
|
78 |
+
|
79 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
80 |
+
|
81 |
+
[More Information Needed]
|
82 |
+
|
83 |
+
### Training Procedure
|
84 |
+
|
85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
86 |
+
|
87 |
+
#### Preprocessing [optional]
|
88 |
+
|
89 |
+
[More Information Needed]
|
90 |
+
|
91 |
+
|
92 |
+
#### Training Hyperparameters
|
93 |
+
|
94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
95 |
+
|
96 |
+
#### Speeds, Sizes, Times [optional]
|
97 |
+
|
98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
99 |
+
|
100 |
+
[More Information Needed]
|
101 |
+
|
102 |
+
## Evaluation
|
103 |
+
|
104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
105 |
+
|
106 |
+
### Testing Data, Factors & Metrics
|
107 |
+
|
108 |
+
#### Testing Data
|
109 |
+
|
110 |
+
<!-- This should link to a Dataset Card if possible. -->
|
111 |
+
|
112 |
+
[More Information Needed]
|
113 |
+
|
114 |
+
#### Factors
|
115 |
+
|
116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
117 |
+
|
118 |
+
[More Information Needed]
|
119 |
+
|
120 |
+
#### Metrics
|
121 |
+
|
122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
123 |
+
|
124 |
+
[More Information Needed]
|
125 |
+
|
126 |
+
### Results
|
127 |
+
|
128 |
+
[More Information Needed]
|
129 |
+
|
130 |
+
#### Summary
|
131 |
+
|
132 |
+
|
133 |
+
|
134 |
+
## Model Examination [optional]
|
135 |
+
|
136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
137 |
+
|
138 |
+
[More Information Needed]
|
139 |
+
|
140 |
+
## Environmental Impact
|
141 |
+
|
142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
143 |
+
|
144 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
145 |
+
|
146 |
+
- **Hardware Type:** [More Information Needed]
|
147 |
+
- **Hours used:** [More Information Needed]
|
148 |
+
- **Cloud Provider:** [More Information Needed]
|
149 |
+
- **Compute Region:** [More Information Needed]
|
150 |
+
- **Carbon Emitted:** [More Information Needed]
|
151 |
+
|
152 |
+
## Technical Specifications [optional]
|
153 |
+
|
154 |
+
### Model Architecture and Objective
|
155 |
+
|
156 |
+
[More Information Needed]
|
157 |
+
|
158 |
+
### Compute Infrastructure
|
159 |
+
|
160 |
+
[More Information Needed]
|
161 |
+
|
162 |
+
#### Hardware
|
163 |
+
|
164 |
+
[More Information Needed]
|
165 |
+
|
166 |
+
#### Software
|
167 |
+
|
168 |
+
[More Information Needed]
|
169 |
+
|
170 |
+
## Citation [optional]
|
171 |
+
|
172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
173 |
+
|
174 |
+
**BibTeX:**
|
175 |
+
|
176 |
+
[More Information Needed]
|
177 |
+
|
178 |
+
**APA:**
|
179 |
+
|
180 |
+
[More Information Needed]
|
181 |
+
|
182 |
+
## Glossary [optional]
|
183 |
+
|
184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
185 |
+
|
186 |
+
[More Information Needed]
|
187 |
+
|
188 |
+
## More Information [optional]
|
189 |
+
|
190 |
+
[More Information Needed]
|
191 |
+
|
192 |
+
## Model Card Authors [optional]
|
193 |
+
|
194 |
+
[More Information Needed]
|
195 |
+
|
196 |
+
## Model Card Contact
|
197 |
+
|
198 |
+
[More Information Needed]
|
model_index.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusion3InstructPix2PixPipeline",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "/home/zhaohaozhe/model2/stable-diffusion-3-medium-diffusers",
|
5 |
+
"scheduler": [
|
6 |
+
"diffusers",
|
7 |
+
"FlowMatchEulerDiscreteScheduler"
|
8 |
+
],
|
9 |
+
"text_encoder": [
|
10 |
+
"transformers",
|
11 |
+
"CLIPTextModelWithProjection"
|
12 |
+
],
|
13 |
+
"text_encoder_2": [
|
14 |
+
"transformers",
|
15 |
+
"CLIPTextModelWithProjection"
|
16 |
+
],
|
17 |
+
"text_encoder_3": [
|
18 |
+
"transformers",
|
19 |
+
"T5EncoderModel"
|
20 |
+
],
|
21 |
+
"tokenizer": [
|
22 |
+
"transformers",
|
23 |
+
"CLIPTokenizer"
|
24 |
+
],
|
25 |
+
"tokenizer_2": [
|
26 |
+
"transformers",
|
27 |
+
"CLIPTokenizer"
|
28 |
+
],
|
29 |
+
"tokenizer_3": [
|
30 |
+
"transformers",
|
31 |
+
"T5TokenizerFast"
|
32 |
+
],
|
33 |
+
"transformer": [
|
34 |
+
"diffusers",
|
35 |
+
"SD3Transformer2DModel"
|
36 |
+
],
|
37 |
+
"vae": [
|
38 |
+
"diffusers",
|
39 |
+
"AutoencoderKL"
|
40 |
+
]
|
41 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"num_train_timesteps": 1000,
|
5 |
+
"shift": 3.0
|
6 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/zhaohaozhe/model2/stable-diffusion-3-medium-diffusers/text_encoder",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModelWithProjection"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "quick_gelu",
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 768,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.41.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fab2e9f2a5d3d8822ebd40a4f0ad22d5119dde950b31f8922c3e8d5622704a1c
|
3 |
+
size 494624560
|
text_encoder_2/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/zhaohaozhe/model2/stable-diffusion-3-medium-diffusers/text_encoder_2",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModelWithProjection"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_size": 1280,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5120,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 20,
|
19 |
+
"num_hidden_layers": 32,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 1280,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.41.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
text_encoder_2/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a6032f63d37ae02bbc74ccd6a27440578cd71701f96532229d0154f55a8d3ff
|
3 |
+
size 2778702264
|
text_encoder_3/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/zhaohaozhe/model2/stable-diffusion-3-medium-diffusers/text_encoder_3",
|
3 |
+
"architectures": [
|
4 |
+
"T5EncoderModel"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 10240,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 4096,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"num_decoder_layers": 24,
|
21 |
+
"num_heads": 64,
|
22 |
+
"num_layers": 24,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.41.2",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 32128
|
32 |
+
}
|
text_encoder_3/model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e0e98242fed1de128a73ee6fee174aa30186c66f7d70811c8ebf67d72067f38
|
3 |
+
size 4989319680
|
text_encoder_3/model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7309a33cd1780b20e3d84b2e14585d7a64ccea45079aecc86c507e381e00ed14
|
3 |
+
size 4999830656
|
text_encoder_3/model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d278bf7cb4de9957cb67d8a92dc9273f88186f0c90e0f2a3de13882217d9a95c
|
3 |
+
size 4865612720
|
text_encoder_3/model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69afce9a62402b82095baa1dfef572be92dfd9a4062693d49a5948e4d27585a5
|
3 |
+
size 4194506688
|
text_encoder_3/model.safetensors.index.json
ADDED
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 19049242624
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
|
7 |
+
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
|
14 |
+
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
|
17 |
+
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
|
19 |
+
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
|
26 |
+
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
|
27 |
+
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
|
28 |
+
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
|
29 |
+
"encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
|
30 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
|
31 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
|
32 |
+
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
|
38 |
+
"encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
|
41 |
+
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
|
43 |
+
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
|
45 |
+
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"encoder.block.12.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
|
48 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
|
49 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
|
50 |
+
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
|
51 |
+
"encoder.block.12.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
|
52 |
+
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
|
53 |
+
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
|
54 |
+
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
|
55 |
+
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
|
56 |
+
"encoder.block.13.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
|
57 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
|
58 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
|
59 |
+
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
|
60 |
+
"encoder.block.13.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
|
61 |
+
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
|
62 |
+
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
|
63 |
+
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
|
64 |
+
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
|
65 |
+
"encoder.block.14.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
|
66 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
|
67 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
|
68 |
+
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
|
69 |
+
"encoder.block.14.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
|
70 |
+
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
|
71 |
+
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
|
72 |
+
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
|
73 |
+
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
|
74 |
+
"encoder.block.15.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
|
75 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
|
76 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
|
77 |
+
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
|
78 |
+
"encoder.block.15.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
|
79 |
+
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
|
80 |
+
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
|
81 |
+
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
|
82 |
+
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
|
83 |
+
"encoder.block.16.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
|
84 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
|
85 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
|
86 |
+
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
|
87 |
+
"encoder.block.16.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
|
88 |
+
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
|
89 |
+
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
|
90 |
+
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
|
91 |
+
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
|
92 |
+
"encoder.block.17.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
|
93 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
|
94 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
|
95 |
+
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
|
96 |
+
"encoder.block.17.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
|
97 |
+
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
|
98 |
+
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
|
99 |
+
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
|
100 |
+
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
|
101 |
+
"encoder.block.18.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
|
102 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
|
103 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
|
104 |
+
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
|
105 |
+
"encoder.block.18.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
|
106 |
+
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
|
107 |
+
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
|
108 |
+
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
|
109 |
+
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
|
110 |
+
"encoder.block.19.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
|
111 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
|
112 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
|
113 |
+
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
|
114 |
+
"encoder.block.19.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
|
115 |
+
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
|
116 |
+
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
|
117 |
+
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
|
118 |
+
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
|
119 |
+
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
|
120 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
|
121 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
|
122 |
+
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
|
123 |
+
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
|
124 |
+
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
|
125 |
+
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
|
126 |
+
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
|
127 |
+
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
|
128 |
+
"encoder.block.20.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
|
129 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
|
130 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
|
131 |
+
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
|
132 |
+
"encoder.block.20.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
|
133 |
+
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
|
134 |
+
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
|
135 |
+
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
|
136 |
+
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
|
137 |
+
"encoder.block.21.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
|
138 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
|
139 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
|
140 |
+
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
|
141 |
+
"encoder.block.21.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
|
142 |
+
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
|
143 |
+
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
|
144 |
+
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
|
145 |
+
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
|
146 |
+
"encoder.block.22.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
|
147 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
|
148 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
|
149 |
+
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
|
150 |
+
"encoder.block.22.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
|
151 |
+
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
|
152 |
+
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
|
153 |
+
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
|
154 |
+
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
|
155 |
+
"encoder.block.23.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
|
156 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
|
157 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
|
158 |
+
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
|
159 |
+
"encoder.block.23.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
|
160 |
+
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
|
161 |
+
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
|
162 |
+
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
|
163 |
+
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
|
164 |
+
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
|
165 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
|
166 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
|
167 |
+
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
|
168 |
+
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
|
169 |
+
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
|
170 |
+
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
|
171 |
+
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
|
172 |
+
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
|
173 |
+
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
|
174 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
|
175 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
|
176 |
+
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
|
177 |
+
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
|
178 |
+
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
|
179 |
+
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
|
180 |
+
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
|
181 |
+
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
|
182 |
+
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
|
183 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
|
184 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
|
185 |
+
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
|
186 |
+
"encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
|
187 |
+
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
|
188 |
+
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
|
189 |
+
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
|
190 |
+
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
|
191 |
+
"encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
|
192 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
|
193 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
|
194 |
+
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
|
195 |
+
"encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
|
196 |
+
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
|
197 |
+
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
|
198 |
+
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
|
199 |
+
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
|
200 |
+
"encoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
|
201 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
|
202 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
|
203 |
+
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
|
204 |
+
"encoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
|
205 |
+
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
|
206 |
+
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
|
207 |
+
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
|
208 |
+
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
|
209 |
+
"encoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
|
210 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
|
211 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
|
212 |
+
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
|
213 |
+
"encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
|
214 |
+
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
|
215 |
+
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
|
216 |
+
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
|
217 |
+
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
|
218 |
+
"encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
|
219 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
|
220 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
|
221 |
+
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
|
222 |
+
"encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
|
223 |
+
"encoder.final_layer_norm.weight": "model-00004-of-00004.safetensors",
|
224 |
+
"shared.weight": "model-00001-of-00004.safetensors"
|
225 |
+
}
|
226 |
+
}
|
tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"49406": {
|
5 |
+
"content": "<|startoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"49407": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"bos_token": "<|startoftext|>",
|
22 |
+
"clean_up_tokenization_spaces": true,
|
23 |
+
"do_lower_case": true,
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"errors": "replace",
|
26 |
+
"model_max_length": 77,
|
27 |
+
"pad_token": "<|endoftext|>",
|
28 |
+
"tokenizer_class": "CLIPTokenizer",
|
29 |
+
"unk_token": "<|endoftext|>"
|
30 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_2/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_2/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "!",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer_2/tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "!",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"49406": {
|
13 |
+
"content": "<|startoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"49407": {
|
21 |
+
"content": "<|endoftext|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"bos_token": "<|startoftext|>",
|
30 |
+
"clean_up_tokenization_spaces": true,
|
31 |
+
"do_lower_case": true,
|
32 |
+
"eos_token": "<|endoftext|>",
|
33 |
+
"errors": "replace",
|
34 |
+
"model_max_length": 77,
|
35 |
+
"pad_token": "!",
|
36 |
+
"tokenizer_class": "CLIPTokenizer",
|
37 |
+
"unk_token": "<|endoftext|>"
|
38 |
+
}
|
tokenizer_2/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_3/special_tokens_map.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": {
|
105 |
+
"content": "</s>",
|
106 |
+
"lstrip": false,
|
107 |
+
"normalized": false,
|
108 |
+
"rstrip": false,
|
109 |
+
"single_word": false
|
110 |
+
},
|
111 |
+
"pad_token": {
|
112 |
+
"content": "<pad>",
|
113 |
+
"lstrip": false,
|
114 |
+
"normalized": false,
|
115 |
+
"rstrip": false,
|
116 |
+
"single_word": false
|
117 |
+
},
|
118 |
+
"unk_token": {
|
119 |
+
"content": "<unk>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false
|
124 |
+
}
|
125 |
+
}
|
tokenizer_3/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer_3/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_3/tokenizer_config.json
ADDED
@@ -0,0 +1,940 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<unk>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"32000": {
|
29 |
+
"content": "<extra_id_99>",
|
30 |
+
"lstrip": true,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": true,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"32001": {
|
37 |
+
"content": "<extra_id_98>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": true,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"32002": {
|
45 |
+
"content": "<extra_id_97>",
|
46 |
+
"lstrip": true,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": true,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"32003": {
|
53 |
+
"content": "<extra_id_96>",
|
54 |
+
"lstrip": true,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": true,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"32004": {
|
61 |
+
"content": "<extra_id_95>",
|
62 |
+
"lstrip": true,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": true,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"32005": {
|
69 |
+
"content": "<extra_id_94>",
|
70 |
+
"lstrip": true,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": true,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"32006": {
|
77 |
+
"content": "<extra_id_93>",
|
78 |
+
"lstrip": true,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": true,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"32007": {
|
85 |
+
"content": "<extra_id_92>",
|
86 |
+
"lstrip": true,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": true,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"32008": {
|
93 |
+
"content": "<extra_id_91>",
|
94 |
+
"lstrip": true,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": true,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"32009": {
|
101 |
+
"content": "<extra_id_90>",
|
102 |
+
"lstrip": true,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": true,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"32010": {
|
109 |
+
"content": "<extra_id_89>",
|
110 |
+
"lstrip": true,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": true,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"32011": {
|
117 |
+
"content": "<extra_id_88>",
|
118 |
+
"lstrip": true,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": true,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"32012": {
|
125 |
+
"content": "<extra_id_87>",
|
126 |
+
"lstrip": true,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": true,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"32013": {
|
133 |
+
"content": "<extra_id_86>",
|
134 |
+
"lstrip": true,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": true,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"32014": {
|
141 |
+
"content": "<extra_id_85>",
|
142 |
+
"lstrip": true,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": true,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"32015": {
|
149 |
+
"content": "<extra_id_84>",
|
150 |
+
"lstrip": true,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": true,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"32016": {
|
157 |
+
"content": "<extra_id_83>",
|
158 |
+
"lstrip": true,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": true,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"32017": {
|
165 |
+
"content": "<extra_id_82>",
|
166 |
+
"lstrip": true,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": true,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"32018": {
|
173 |
+
"content": "<extra_id_81>",
|
174 |
+
"lstrip": true,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": true,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"32019": {
|
181 |
+
"content": "<extra_id_80>",
|
182 |
+
"lstrip": true,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": true,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"32020": {
|
189 |
+
"content": "<extra_id_79>",
|
190 |
+
"lstrip": true,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": true,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"32021": {
|
197 |
+
"content": "<extra_id_78>",
|
198 |
+
"lstrip": true,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": true,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"32022": {
|
205 |
+
"content": "<extra_id_77>",
|
206 |
+
"lstrip": true,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": true,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"32023": {
|
213 |
+
"content": "<extra_id_76>",
|
214 |
+
"lstrip": true,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": true,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"32024": {
|
221 |
+
"content": "<extra_id_75>",
|
222 |
+
"lstrip": true,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": true,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"32025": {
|
229 |
+
"content": "<extra_id_74>",
|
230 |
+
"lstrip": true,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": true,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"32026": {
|
237 |
+
"content": "<extra_id_73>",
|
238 |
+
"lstrip": true,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": true,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"32027": {
|
245 |
+
"content": "<extra_id_72>",
|
246 |
+
"lstrip": true,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": true,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"32028": {
|
253 |
+
"content": "<extra_id_71>",
|
254 |
+
"lstrip": true,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": true,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"32029": {
|
261 |
+
"content": "<extra_id_70>",
|
262 |
+
"lstrip": true,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": true,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
},
|
268 |
+
"32030": {
|
269 |
+
"content": "<extra_id_69>",
|
270 |
+
"lstrip": true,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": true,
|
273 |
+
"single_word": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
"32031": {
|
277 |
+
"content": "<extra_id_68>",
|
278 |
+
"lstrip": true,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": true,
|
281 |
+
"single_word": false,
|
282 |
+
"special": true
|
283 |
+
},
|
284 |
+
"32032": {
|
285 |
+
"content": "<extra_id_67>",
|
286 |
+
"lstrip": true,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": true,
|
289 |
+
"single_word": false,
|
290 |
+
"special": true
|
291 |
+
},
|
292 |
+
"32033": {
|
293 |
+
"content": "<extra_id_66>",
|
294 |
+
"lstrip": true,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": true,
|
297 |
+
"single_word": false,
|
298 |
+
"special": true
|
299 |
+
},
|
300 |
+
"32034": {
|
301 |
+
"content": "<extra_id_65>",
|
302 |
+
"lstrip": true,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": true,
|
305 |
+
"single_word": false,
|
306 |
+
"special": true
|
307 |
+
},
|
308 |
+
"32035": {
|
309 |
+
"content": "<extra_id_64>",
|
310 |
+
"lstrip": true,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": true,
|
313 |
+
"single_word": false,
|
314 |
+
"special": true
|
315 |
+
},
|
316 |
+
"32036": {
|
317 |
+
"content": "<extra_id_63>",
|
318 |
+
"lstrip": true,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": true,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
+
},
|
324 |
+
"32037": {
|
325 |
+
"content": "<extra_id_62>",
|
326 |
+
"lstrip": true,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": true,
|
329 |
+
"single_word": false,
|
330 |
+
"special": true
|
331 |
+
},
|
332 |
+
"32038": {
|
333 |
+
"content": "<extra_id_61>",
|
334 |
+
"lstrip": true,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": true,
|
337 |
+
"single_word": false,
|
338 |
+
"special": true
|
339 |
+
},
|
340 |
+
"32039": {
|
341 |
+
"content": "<extra_id_60>",
|
342 |
+
"lstrip": true,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": true,
|
345 |
+
"single_word": false,
|
346 |
+
"special": true
|
347 |
+
},
|
348 |
+
"32040": {
|
349 |
+
"content": "<extra_id_59>",
|
350 |
+
"lstrip": true,
|
351 |
+
"normalized": false,
|
352 |
+
"rstrip": true,
|
353 |
+
"single_word": false,
|
354 |
+
"special": true
|
355 |
+
},
|
356 |
+
"32041": {
|
357 |
+
"content": "<extra_id_58>",
|
358 |
+
"lstrip": true,
|
359 |
+
"normalized": false,
|
360 |
+
"rstrip": true,
|
361 |
+
"single_word": false,
|
362 |
+
"special": true
|
363 |
+
},
|
364 |
+
"32042": {
|
365 |
+
"content": "<extra_id_57>",
|
366 |
+
"lstrip": true,
|
367 |
+
"normalized": false,
|
368 |
+
"rstrip": true,
|
369 |
+
"single_word": false,
|
370 |
+
"special": true
|
371 |
+
},
|
372 |
+
"32043": {
|
373 |
+
"content": "<extra_id_56>",
|
374 |
+
"lstrip": true,
|
375 |
+
"normalized": false,
|
376 |
+
"rstrip": true,
|
377 |
+
"single_word": false,
|
378 |
+
"special": true
|
379 |
+
},
|
380 |
+
"32044": {
|
381 |
+
"content": "<extra_id_55>",
|
382 |
+
"lstrip": true,
|
383 |
+
"normalized": false,
|
384 |
+
"rstrip": true,
|
385 |
+
"single_word": false,
|
386 |
+
"special": true
|
387 |
+
},
|
388 |
+
"32045": {
|
389 |
+
"content": "<extra_id_54>",
|
390 |
+
"lstrip": true,
|
391 |
+
"normalized": false,
|
392 |
+
"rstrip": true,
|
393 |
+
"single_word": false,
|
394 |
+
"special": true
|
395 |
+
},
|
396 |
+
"32046": {
|
397 |
+
"content": "<extra_id_53>",
|
398 |
+
"lstrip": true,
|
399 |
+
"normalized": false,
|
400 |
+
"rstrip": true,
|
401 |
+
"single_word": false,
|
402 |
+
"special": true
|
403 |
+
},
|
404 |
+
"32047": {
|
405 |
+
"content": "<extra_id_52>",
|
406 |
+
"lstrip": true,
|
407 |
+
"normalized": false,
|
408 |
+
"rstrip": true,
|
409 |
+
"single_word": false,
|
410 |
+
"special": true
|
411 |
+
},
|
412 |
+
"32048": {
|
413 |
+
"content": "<extra_id_51>",
|
414 |
+
"lstrip": true,
|
415 |
+
"normalized": false,
|
416 |
+
"rstrip": true,
|
417 |
+
"single_word": false,
|
418 |
+
"special": true
|
419 |
+
},
|
420 |
+
"32049": {
|
421 |
+
"content": "<extra_id_50>",
|
422 |
+
"lstrip": true,
|
423 |
+
"normalized": false,
|
424 |
+
"rstrip": true,
|
425 |
+
"single_word": false,
|
426 |
+
"special": true
|
427 |
+
},
|
428 |
+
"32050": {
|
429 |
+
"content": "<extra_id_49>",
|
430 |
+
"lstrip": true,
|
431 |
+
"normalized": false,
|
432 |
+
"rstrip": true,
|
433 |
+
"single_word": false,
|
434 |
+
"special": true
|
435 |
+
},
|
436 |
+
"32051": {
|
437 |
+
"content": "<extra_id_48>",
|
438 |
+
"lstrip": true,
|
439 |
+
"normalized": false,
|
440 |
+
"rstrip": true,
|
441 |
+
"single_word": false,
|
442 |
+
"special": true
|
443 |
+
},
|
444 |
+
"32052": {
|
445 |
+
"content": "<extra_id_47>",
|
446 |
+
"lstrip": true,
|
447 |
+
"normalized": false,
|
448 |
+
"rstrip": true,
|
449 |
+
"single_word": false,
|
450 |
+
"special": true
|
451 |
+
},
|
452 |
+
"32053": {
|
453 |
+
"content": "<extra_id_46>",
|
454 |
+
"lstrip": true,
|
455 |
+
"normalized": false,
|
456 |
+
"rstrip": true,
|
457 |
+
"single_word": false,
|
458 |
+
"special": true
|
459 |
+
},
|
460 |
+
"32054": {
|
461 |
+
"content": "<extra_id_45>",
|
462 |
+
"lstrip": true,
|
463 |
+
"normalized": false,
|
464 |
+
"rstrip": true,
|
465 |
+
"single_word": false,
|
466 |
+
"special": true
|
467 |
+
},
|
468 |
+
"32055": {
|
469 |
+
"content": "<extra_id_44>",
|
470 |
+
"lstrip": true,
|
471 |
+
"normalized": false,
|
472 |
+
"rstrip": true,
|
473 |
+
"single_word": false,
|
474 |
+
"special": true
|
475 |
+
},
|
476 |
+
"32056": {
|
477 |
+
"content": "<extra_id_43>",
|
478 |
+
"lstrip": true,
|
479 |
+
"normalized": false,
|
480 |
+
"rstrip": true,
|
481 |
+
"single_word": false,
|
482 |
+
"special": true
|
483 |
+
},
|
484 |
+
"32057": {
|
485 |
+
"content": "<extra_id_42>",
|
486 |
+
"lstrip": true,
|
487 |
+
"normalized": false,
|
488 |
+
"rstrip": true,
|
489 |
+
"single_word": false,
|
490 |
+
"special": true
|
491 |
+
},
|
492 |
+
"32058": {
|
493 |
+
"content": "<extra_id_41>",
|
494 |
+
"lstrip": true,
|
495 |
+
"normalized": false,
|
496 |
+
"rstrip": true,
|
497 |
+
"single_word": false,
|
498 |
+
"special": true
|
499 |
+
},
|
500 |
+
"32059": {
|
501 |
+
"content": "<extra_id_40>",
|
502 |
+
"lstrip": true,
|
503 |
+
"normalized": false,
|
504 |
+
"rstrip": true,
|
505 |
+
"single_word": false,
|
506 |
+
"special": true
|
507 |
+
},
|
508 |
+
"32060": {
|
509 |
+
"content": "<extra_id_39>",
|
510 |
+
"lstrip": true,
|
511 |
+
"normalized": false,
|
512 |
+
"rstrip": true,
|
513 |
+
"single_word": false,
|
514 |
+
"special": true
|
515 |
+
},
|
516 |
+
"32061": {
|
517 |
+
"content": "<extra_id_38>",
|
518 |
+
"lstrip": true,
|
519 |
+
"normalized": false,
|
520 |
+
"rstrip": true,
|
521 |
+
"single_word": false,
|
522 |
+
"special": true
|
523 |
+
},
|
524 |
+
"32062": {
|
525 |
+
"content": "<extra_id_37>",
|
526 |
+
"lstrip": true,
|
527 |
+
"normalized": false,
|
528 |
+
"rstrip": true,
|
529 |
+
"single_word": false,
|
530 |
+
"special": true
|
531 |
+
},
|
532 |
+
"32063": {
|
533 |
+
"content": "<extra_id_36>",
|
534 |
+
"lstrip": true,
|
535 |
+
"normalized": false,
|
536 |
+
"rstrip": true,
|
537 |
+
"single_word": false,
|
538 |
+
"special": true
|
539 |
+
},
|
540 |
+
"32064": {
|
541 |
+
"content": "<extra_id_35>",
|
542 |
+
"lstrip": true,
|
543 |
+
"normalized": false,
|
544 |
+
"rstrip": true,
|
545 |
+
"single_word": false,
|
546 |
+
"special": true
|
547 |
+
},
|
548 |
+
"32065": {
|
549 |
+
"content": "<extra_id_34>",
|
550 |
+
"lstrip": true,
|
551 |
+
"normalized": false,
|
552 |
+
"rstrip": true,
|
553 |
+
"single_word": false,
|
554 |
+
"special": true
|
555 |
+
},
|
556 |
+
"32066": {
|
557 |
+
"content": "<extra_id_33>",
|
558 |
+
"lstrip": true,
|
559 |
+
"normalized": false,
|
560 |
+
"rstrip": true,
|
561 |
+
"single_word": false,
|
562 |
+
"special": true
|
563 |
+
},
|
564 |
+
"32067": {
|
565 |
+
"content": "<extra_id_32>",
|
566 |
+
"lstrip": true,
|
567 |
+
"normalized": false,
|
568 |
+
"rstrip": true,
|
569 |
+
"single_word": false,
|
570 |
+
"special": true
|
571 |
+
},
|
572 |
+
"32068": {
|
573 |
+
"content": "<extra_id_31>",
|
574 |
+
"lstrip": true,
|
575 |
+
"normalized": false,
|
576 |
+
"rstrip": true,
|
577 |
+
"single_word": false,
|
578 |
+
"special": true
|
579 |
+
},
|
580 |
+
"32069": {
|
581 |
+
"content": "<extra_id_30>",
|
582 |
+
"lstrip": true,
|
583 |
+
"normalized": false,
|
584 |
+
"rstrip": true,
|
585 |
+
"single_word": false,
|
586 |
+
"special": true
|
587 |
+
},
|
588 |
+
"32070": {
|
589 |
+
"content": "<extra_id_29>",
|
590 |
+
"lstrip": true,
|
591 |
+
"normalized": false,
|
592 |
+
"rstrip": true,
|
593 |
+
"single_word": false,
|
594 |
+
"special": true
|
595 |
+
},
|
596 |
+
"32071": {
|
597 |
+
"content": "<extra_id_28>",
|
598 |
+
"lstrip": true,
|
599 |
+
"normalized": false,
|
600 |
+
"rstrip": true,
|
601 |
+
"single_word": false,
|
602 |
+
"special": true
|
603 |
+
},
|
604 |
+
"32072": {
|
605 |
+
"content": "<extra_id_27>",
|
606 |
+
"lstrip": true,
|
607 |
+
"normalized": false,
|
608 |
+
"rstrip": true,
|
609 |
+
"single_word": false,
|
610 |
+
"special": true
|
611 |
+
},
|
612 |
+
"32073": {
|
613 |
+
"content": "<extra_id_26>",
|
614 |
+
"lstrip": true,
|
615 |
+
"normalized": false,
|
616 |
+
"rstrip": true,
|
617 |
+
"single_word": false,
|
618 |
+
"special": true
|
619 |
+
},
|
620 |
+
"32074": {
|
621 |
+
"content": "<extra_id_25>",
|
622 |
+
"lstrip": true,
|
623 |
+
"normalized": false,
|
624 |
+
"rstrip": true,
|
625 |
+
"single_word": false,
|
626 |
+
"special": true
|
627 |
+
},
|
628 |
+
"32075": {
|
629 |
+
"content": "<extra_id_24>",
|
630 |
+
"lstrip": true,
|
631 |
+
"normalized": false,
|
632 |
+
"rstrip": true,
|
633 |
+
"single_word": false,
|
634 |
+
"special": true
|
635 |
+
},
|
636 |
+
"32076": {
|
637 |
+
"content": "<extra_id_23>",
|
638 |
+
"lstrip": true,
|
639 |
+
"normalized": false,
|
640 |
+
"rstrip": true,
|
641 |
+
"single_word": false,
|
642 |
+
"special": true
|
643 |
+
},
|
644 |
+
"32077": {
|
645 |
+
"content": "<extra_id_22>",
|
646 |
+
"lstrip": true,
|
647 |
+
"normalized": false,
|
648 |
+
"rstrip": true,
|
649 |
+
"single_word": false,
|
650 |
+
"special": true
|
651 |
+
},
|
652 |
+
"32078": {
|
653 |
+
"content": "<extra_id_21>",
|
654 |
+
"lstrip": true,
|
655 |
+
"normalized": false,
|
656 |
+
"rstrip": true,
|
657 |
+
"single_word": false,
|
658 |
+
"special": true
|
659 |
+
},
|
660 |
+
"32079": {
|
661 |
+
"content": "<extra_id_20>",
|
662 |
+
"lstrip": true,
|
663 |
+
"normalized": false,
|
664 |
+
"rstrip": true,
|
665 |
+
"single_word": false,
|
666 |
+
"special": true
|
667 |
+
},
|
668 |
+
"32080": {
|
669 |
+
"content": "<extra_id_19>",
|
670 |
+
"lstrip": true,
|
671 |
+
"normalized": false,
|
672 |
+
"rstrip": true,
|
673 |
+
"single_word": false,
|
674 |
+
"special": true
|
675 |
+
},
|
676 |
+
"32081": {
|
677 |
+
"content": "<extra_id_18>",
|
678 |
+
"lstrip": true,
|
679 |
+
"normalized": false,
|
680 |
+
"rstrip": true,
|
681 |
+
"single_word": false,
|
682 |
+
"special": true
|
683 |
+
},
|
684 |
+
"32082": {
|
685 |
+
"content": "<extra_id_17>",
|
686 |
+
"lstrip": true,
|
687 |
+
"normalized": false,
|
688 |
+
"rstrip": true,
|
689 |
+
"single_word": false,
|
690 |
+
"special": true
|
691 |
+
},
|
692 |
+
"32083": {
|
693 |
+
"content": "<extra_id_16>",
|
694 |
+
"lstrip": true,
|
695 |
+
"normalized": false,
|
696 |
+
"rstrip": true,
|
697 |
+
"single_word": false,
|
698 |
+
"special": true
|
699 |
+
},
|
700 |
+
"32084": {
|
701 |
+
"content": "<extra_id_15>",
|
702 |
+
"lstrip": true,
|
703 |
+
"normalized": false,
|
704 |
+
"rstrip": true,
|
705 |
+
"single_word": false,
|
706 |
+
"special": true
|
707 |
+
},
|
708 |
+
"32085": {
|
709 |
+
"content": "<extra_id_14>",
|
710 |
+
"lstrip": true,
|
711 |
+
"normalized": false,
|
712 |
+
"rstrip": true,
|
713 |
+
"single_word": false,
|
714 |
+
"special": true
|
715 |
+
},
|
716 |
+
"32086": {
|
717 |
+
"content": "<extra_id_13>",
|
718 |
+
"lstrip": true,
|
719 |
+
"normalized": false,
|
720 |
+
"rstrip": true,
|
721 |
+
"single_word": false,
|
722 |
+
"special": true
|
723 |
+
},
|
724 |
+
"32087": {
|
725 |
+
"content": "<extra_id_12>",
|
726 |
+
"lstrip": true,
|
727 |
+
"normalized": false,
|
728 |
+
"rstrip": true,
|
729 |
+
"single_word": false,
|
730 |
+
"special": true
|
731 |
+
},
|
732 |
+
"32088": {
|
733 |
+
"content": "<extra_id_11>",
|
734 |
+
"lstrip": true,
|
735 |
+
"normalized": false,
|
736 |
+
"rstrip": true,
|
737 |
+
"single_word": false,
|
738 |
+
"special": true
|
739 |
+
},
|
740 |
+
"32089": {
|
741 |
+
"content": "<extra_id_10>",
|
742 |
+
"lstrip": true,
|
743 |
+
"normalized": false,
|
744 |
+
"rstrip": true,
|
745 |
+
"single_word": false,
|
746 |
+
"special": true
|
747 |
+
},
|
748 |
+
"32090": {
|
749 |
+
"content": "<extra_id_9>",
|
750 |
+
"lstrip": true,
|
751 |
+
"normalized": false,
|
752 |
+
"rstrip": true,
|
753 |
+
"single_word": false,
|
754 |
+
"special": true
|
755 |
+
},
|
756 |
+
"32091": {
|
757 |
+
"content": "<extra_id_8>",
|
758 |
+
"lstrip": true,
|
759 |
+
"normalized": false,
|
760 |
+
"rstrip": true,
|
761 |
+
"single_word": false,
|
762 |
+
"special": true
|
763 |
+
},
|
764 |
+
"32092": {
|
765 |
+
"content": "<extra_id_7>",
|
766 |
+
"lstrip": true,
|
767 |
+
"normalized": false,
|
768 |
+
"rstrip": true,
|
769 |
+
"single_word": false,
|
770 |
+
"special": true
|
771 |
+
},
|
772 |
+
"32093": {
|
773 |
+
"content": "<extra_id_6>",
|
774 |
+
"lstrip": true,
|
775 |
+
"normalized": false,
|
776 |
+
"rstrip": true,
|
777 |
+
"single_word": false,
|
778 |
+
"special": true
|
779 |
+
},
|
780 |
+
"32094": {
|
781 |
+
"content": "<extra_id_5>",
|
782 |
+
"lstrip": true,
|
783 |
+
"normalized": false,
|
784 |
+
"rstrip": true,
|
785 |
+
"single_word": false,
|
786 |
+
"special": true
|
787 |
+
},
|
788 |
+
"32095": {
|
789 |
+
"content": "<extra_id_4>",
|
790 |
+
"lstrip": true,
|
791 |
+
"normalized": false,
|
792 |
+
"rstrip": true,
|
793 |
+
"single_word": false,
|
794 |
+
"special": true
|
795 |
+
},
|
796 |
+
"32096": {
|
797 |
+
"content": "<extra_id_3>",
|
798 |
+
"lstrip": true,
|
799 |
+
"normalized": false,
|
800 |
+
"rstrip": true,
|
801 |
+
"single_word": false,
|
802 |
+
"special": true
|
803 |
+
},
|
804 |
+
"32097": {
|
805 |
+
"content": "<extra_id_2>",
|
806 |
+
"lstrip": true,
|
807 |
+
"normalized": false,
|
808 |
+
"rstrip": true,
|
809 |
+
"single_word": false,
|
810 |
+
"special": true
|
811 |
+
},
|
812 |
+
"32098": {
|
813 |
+
"content": "<extra_id_1>",
|
814 |
+
"lstrip": true,
|
815 |
+
"normalized": false,
|
816 |
+
"rstrip": true,
|
817 |
+
"single_word": false,
|
818 |
+
"special": true
|
819 |
+
},
|
820 |
+
"32099": {
|
821 |
+
"content": "<extra_id_0>",
|
822 |
+
"lstrip": true,
|
823 |
+
"normalized": false,
|
824 |
+
"rstrip": true,
|
825 |
+
"single_word": false,
|
826 |
+
"special": true
|
827 |
+
}
|
828 |
+
},
|
829 |
+
"additional_special_tokens": [
|
830 |
+
"<extra_id_0>",
|
831 |
+
"<extra_id_1>",
|
832 |
+
"<extra_id_2>",
|
833 |
+
"<extra_id_3>",
|
834 |
+
"<extra_id_4>",
|
835 |
+
"<extra_id_5>",
|
836 |
+
"<extra_id_6>",
|
837 |
+
"<extra_id_7>",
|
838 |
+
"<extra_id_8>",
|
839 |
+
"<extra_id_9>",
|
840 |
+
"<extra_id_10>",
|
841 |
+
"<extra_id_11>",
|
842 |
+
"<extra_id_12>",
|
843 |
+
"<extra_id_13>",
|
844 |
+
"<extra_id_14>",
|
845 |
+
"<extra_id_15>",
|
846 |
+
"<extra_id_16>",
|
847 |
+
"<extra_id_17>",
|
848 |
+
"<extra_id_18>",
|
849 |
+
"<extra_id_19>",
|
850 |
+
"<extra_id_20>",
|
851 |
+
"<extra_id_21>",
|
852 |
+
"<extra_id_22>",
|
853 |
+
"<extra_id_23>",
|
854 |
+
"<extra_id_24>",
|
855 |
+
"<extra_id_25>",
|
856 |
+
"<extra_id_26>",
|
857 |
+
"<extra_id_27>",
|
858 |
+
"<extra_id_28>",
|
859 |
+
"<extra_id_29>",
|
860 |
+
"<extra_id_30>",
|
861 |
+
"<extra_id_31>",
|
862 |
+
"<extra_id_32>",
|
863 |
+
"<extra_id_33>",
|
864 |
+
"<extra_id_34>",
|
865 |
+
"<extra_id_35>",
|
866 |
+
"<extra_id_36>",
|
867 |
+
"<extra_id_37>",
|
868 |
+
"<extra_id_38>",
|
869 |
+
"<extra_id_39>",
|
870 |
+
"<extra_id_40>",
|
871 |
+
"<extra_id_41>",
|
872 |
+
"<extra_id_42>",
|
873 |
+
"<extra_id_43>",
|
874 |
+
"<extra_id_44>",
|
875 |
+
"<extra_id_45>",
|
876 |
+
"<extra_id_46>",
|
877 |
+
"<extra_id_47>",
|
878 |
+
"<extra_id_48>",
|
879 |
+
"<extra_id_49>",
|
880 |
+
"<extra_id_50>",
|
881 |
+
"<extra_id_51>",
|
882 |
+
"<extra_id_52>",
|
883 |
+
"<extra_id_53>",
|
884 |
+
"<extra_id_54>",
|
885 |
+
"<extra_id_55>",
|
886 |
+
"<extra_id_56>",
|
887 |
+
"<extra_id_57>",
|
888 |
+
"<extra_id_58>",
|
889 |
+
"<extra_id_59>",
|
890 |
+
"<extra_id_60>",
|
891 |
+
"<extra_id_61>",
|
892 |
+
"<extra_id_62>",
|
893 |
+
"<extra_id_63>",
|
894 |
+
"<extra_id_64>",
|
895 |
+
"<extra_id_65>",
|
896 |
+
"<extra_id_66>",
|
897 |
+
"<extra_id_67>",
|
898 |
+
"<extra_id_68>",
|
899 |
+
"<extra_id_69>",
|
900 |
+
"<extra_id_70>",
|
901 |
+
"<extra_id_71>",
|
902 |
+
"<extra_id_72>",
|
903 |
+
"<extra_id_73>",
|
904 |
+
"<extra_id_74>",
|
905 |
+
"<extra_id_75>",
|
906 |
+
"<extra_id_76>",
|
907 |
+
"<extra_id_77>",
|
908 |
+
"<extra_id_78>",
|
909 |
+
"<extra_id_79>",
|
910 |
+
"<extra_id_80>",
|
911 |
+
"<extra_id_81>",
|
912 |
+
"<extra_id_82>",
|
913 |
+
"<extra_id_83>",
|
914 |
+
"<extra_id_84>",
|
915 |
+
"<extra_id_85>",
|
916 |
+
"<extra_id_86>",
|
917 |
+
"<extra_id_87>",
|
918 |
+
"<extra_id_88>",
|
919 |
+
"<extra_id_89>",
|
920 |
+
"<extra_id_90>",
|
921 |
+
"<extra_id_91>",
|
922 |
+
"<extra_id_92>",
|
923 |
+
"<extra_id_93>",
|
924 |
+
"<extra_id_94>",
|
925 |
+
"<extra_id_95>",
|
926 |
+
"<extra_id_96>",
|
927 |
+
"<extra_id_97>",
|
928 |
+
"<extra_id_98>",
|
929 |
+
"<extra_id_99>"
|
930 |
+
],
|
931 |
+
"clean_up_tokenization_spaces": true,
|
932 |
+
"eos_token": "</s>",
|
933 |
+
"extra_ids": 100,
|
934 |
+
"legacy": true,
|
935 |
+
"model_max_length": 512,
|
936 |
+
"pad_token": "<pad>",
|
937 |
+
"sp_model_kwargs": {},
|
938 |
+
"tokenizer_class": "T5Tokenizer",
|
939 |
+
"unk_token": "<unk>"
|
940 |
+
}
|
transformer/config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "SD3Transformer2DModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "/home/zhaohaozhe/model/mask_sd3_ip2p_checkpoint-13600",
|
5 |
+
"attention_head_dim": 64,
|
6 |
+
"caption_projection_dim": 1536,
|
7 |
+
"in_channels": 48,
|
8 |
+
"joint_attention_dim": 4096,
|
9 |
+
"num_attention_heads": 24,
|
10 |
+
"num_layers": 24,
|
11 |
+
"out_channels": 16,
|
12 |
+
"patch_size": 2,
|
13 |
+
"pooled_projection_dim": 2048,
|
14 |
+
"pos_embed_max_size": 192,
|
15 |
+
"sample_size": 128
|
16 |
+
}
|
transformer/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c093a9daa79018481a567f11530f26187b35698926d1f18528bdddeee6ac2673
|
3 |
+
size 8340670208
|
vae/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "/home/zhaohaozhe/model2/stable-diffusion-3-medium-diffusers/vae",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"block_out_channels": [
|
7 |
+
128,
|
8 |
+
256,
|
9 |
+
512,
|
10 |
+
512
|
11 |
+
],
|
12 |
+
"down_block_types": [
|
13 |
+
"DownEncoderBlock2D",
|
14 |
+
"DownEncoderBlock2D",
|
15 |
+
"DownEncoderBlock2D",
|
16 |
+
"DownEncoderBlock2D"
|
17 |
+
],
|
18 |
+
"force_upcast": true,
|
19 |
+
"in_channels": 3,
|
20 |
+
"latent_channels": 16,
|
21 |
+
"latents_mean": null,
|
22 |
+
"latents_std": null,
|
23 |
+
"layers_per_block": 2,
|
24 |
+
"norm_num_groups": 32,
|
25 |
+
"out_channels": 3,
|
26 |
+
"sample_size": 1024,
|
27 |
+
"scaling_factor": 1.5305,
|
28 |
+
"shift_factor": 0.0609,
|
29 |
+
"up_block_types": [
|
30 |
+
"UpDecoderBlock2D",
|
31 |
+
"UpDecoderBlock2D",
|
32 |
+
"UpDecoderBlock2D",
|
33 |
+
"UpDecoderBlock2D"
|
34 |
+
],
|
35 |
+
"use_post_quant_conv": false,
|
36 |
+
"use_quant_conv": false
|
37 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7dab491193da4dc5741fad9cb6ec961f57a105686f8a618fab9faafe7a958
|
3 |
+
size 335306212
|