Upload model
Browse files- README.md +201 -0
- config.json +34 -0
- configuration_clip_camembert.py +51 -0
- model.safetensors +3 -0
- modeling_clip_camembert.py +71 -0
README.md
ADDED
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags: []
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- 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. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
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).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/project/lt200056-opgpth/knot/myscript/Multimodal/Continue_Training_CLIP/Experiment/contrastive/outputs/pretrained_caption_model",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextCamembertModelWithProjection"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.1,
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "configuration_clip_camembert.CLIPTextCamembertConfig",
|
10 |
+
"AutoModel": "modeling_clip_camembert.CLIPTextCamembertModelWithProjection"
|
11 |
+
},
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classifier_dropout": null,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"hidden_act": "gelu",
|
16 |
+
"hidden_dropout_prob": 0.1,
|
17 |
+
"hidden_size": 768,
|
18 |
+
"initializer_factor": 1.0,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "clip_text_camembert",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 1,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"projection_dim": 512,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.37.0",
|
31 |
+
"type_vocab_size": 1,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 25005
|
34 |
+
}
|
configuration_clip_camembert.py
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import CamembertConfig
|
2 |
+
|
3 |
+
|
4 |
+
class CLIPTextCamembertConfig(CamembertConfig):
|
5 |
+
# ref : https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased/blob/main/config.json
|
6 |
+
model_type = "clip_text_camembert"
|
7 |
+
|
8 |
+
def __init__(
|
9 |
+
self,
|
10 |
+
vocab_size=25005,
|
11 |
+
hidden_size=768,
|
12 |
+
intermediate_size=3072,
|
13 |
+
projection_dim=512,
|
14 |
+
num_hidden_layers=12,
|
15 |
+
num_attention_heads=12,
|
16 |
+
max_position_embeddings=512,
|
17 |
+
hidden_act="gelu",
|
18 |
+
layer_norm_eps=1e-12,
|
19 |
+
attention_dropout=0.1,
|
20 |
+
initializer_range=0.02,
|
21 |
+
initializer_factor=1.0,
|
22 |
+
pad_token_id=1,
|
23 |
+
bos_token_id=0,
|
24 |
+
eos_token_id=2,
|
25 |
+
type_vocab_size=1,
|
26 |
+
**kwargs,
|
27 |
+
):
|
28 |
+
super().__init__(
|
29 |
+
pad_token_id=pad_token_id,
|
30 |
+
bos_token_id=bos_token_id,
|
31 |
+
eos_token_id=eos_token_id,
|
32 |
+
**kwargs,
|
33 |
+
)
|
34 |
+
|
35 |
+
self.vocab_size = vocab_size
|
36 |
+
self.hidden_size = hidden_size
|
37 |
+
self.intermediate_size = intermediate_size
|
38 |
+
self.projection_dim = projection_dim
|
39 |
+
self.num_hidden_layers = num_hidden_layers
|
40 |
+
self.num_attention_heads = num_attention_heads
|
41 |
+
self.max_position_embeddings = max_position_embeddings
|
42 |
+
self.layer_norm_eps = layer_norm_eps
|
43 |
+
self.hidden_act = hidden_act
|
44 |
+
self.initializer_range = initializer_range
|
45 |
+
self.initializer_factor = initializer_factor
|
46 |
+
self.attention_dropout = attention_dropout
|
47 |
+
self.type_vocab_size = type_vocab_size
|
48 |
+
self.auto_map = {
|
49 |
+
"AutoConfig": "configuration_clip_camembert.CLIPTextCamembertConfig",
|
50 |
+
"AutoModel": "modeling_clip_camembert.CLIPTextCamembertModelWithProjection",
|
51 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:827e46c81eff27861cd95815354c6b5b62585133e93b2761258d9d6db81d0f97
|
3 |
+
size 422575160
|
modeling_clip_camembert.py
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from .configuration_clip_camembert import CLIPTextCamembertConfig
|
2 |
+
from transformers import (
|
3 |
+
CamembertModel,
|
4 |
+
CLIPTextModelWithProjection,
|
5 |
+
)
|
6 |
+
from transformers.models.clip.modeling_clip import CLIPTextModelOutput
|
7 |
+
import torch
|
8 |
+
from torch import nn
|
9 |
+
from typing import Any, Optional, Tuple, Union
|
10 |
+
|
11 |
+
|
12 |
+
class CLIPTextCamembertModelWithProjection(CLIPTextModelWithProjection):
|
13 |
+
config_class = CLIPTextCamembertConfig
|
14 |
+
|
15 |
+
def __init__(self, config: CLIPTextCamembertConfig):
|
16 |
+
super().__init__(config)
|
17 |
+
|
18 |
+
self.text_model = CamembertModel(config)
|
19 |
+
|
20 |
+
self.text_projection = nn.Linear(
|
21 |
+
config.hidden_size, config.projection_dim, bias=False
|
22 |
+
)
|
23 |
+
# Initialize weights and apply final processing
|
24 |
+
self.post_init()
|
25 |
+
|
26 |
+
def forward(
|
27 |
+
self,
|
28 |
+
input_ids: Optional[torch.Tensor] = None,
|
29 |
+
attention_mask: Optional[torch.Tensor] = None,
|
30 |
+
position_ids: Optional[torch.Tensor] = None,
|
31 |
+
output_attentions: Optional[bool] = None,
|
32 |
+
output_hidden_states: Optional[bool] = None,
|
33 |
+
return_dict: Optional[bool] = None,
|
34 |
+
) -> Union[Tuple, CLIPTextModelOutput]:
|
35 |
+
return_dict = (
|
36 |
+
return_dict if return_dict is not None else self.config.use_return_dict
|
37 |
+
)
|
38 |
+
|
39 |
+
text_outputs = self.text_model(
|
40 |
+
input_ids=input_ids,
|
41 |
+
attention_mask=attention_mask,
|
42 |
+
position_ids=position_ids,
|
43 |
+
output_attentions=output_attentions,
|
44 |
+
output_hidden_states=output_hidden_states,
|
45 |
+
return_dict=return_dict,
|
46 |
+
)
|
47 |
+
|
48 |
+
pooled_output = text_outputs[1]
|
49 |
+
|
50 |
+
text_embeds = self.text_projection(pooled_output)
|
51 |
+
|
52 |
+
if not return_dict:
|
53 |
+
outputs = (text_embeds, text_outputs[0]) + text_outputs[2:]
|
54 |
+
return tuple(output for output in outputs if output is not None)
|
55 |
+
|
56 |
+
return CLIPTextModelOutput(
|
57 |
+
text_embeds=text_embeds,
|
58 |
+
last_hidden_state=text_outputs.last_hidden_state,
|
59 |
+
hidden_states=text_outputs.hidden_states,
|
60 |
+
attentions=text_outputs.attentions,
|
61 |
+
)
|
62 |
+
|
63 |
+
def converter_weight(
|
64 |
+
self, path_model="airesearch/wangchanberta-base-att-spm-uncased"
|
65 |
+
):
|
66 |
+
r"""
|
67 |
+
converter weight from airesearch/wangchanberta-base-att-spm-uncased
|
68 |
+
"""
|
69 |
+
pretrained_state_dict = CamembertModel.from_pretrained(path_model).state_dict()
|
70 |
+
# Load the new state dictionary into the custom model
|
71 |
+
self.text_model.load_state_dict(pretrained_state_dict)
|