kaleinaNyan commited on
Commit
9f606aa
1 Parent(s): 6d74f62

Upload JinaJudge

Browse files
Files changed (4) hide show
  1. README.md +199 -0
  2. config.json +17 -0
  3. model.safetensors +3 -0
  4. modeling_jina_judge.py +76 -0
README.md ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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]
config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "JinaJudge"
4
+ ],
5
+ "auto_map": {
6
+ "AutoConfig": "modeling_jina_judge.JinaJudgeConfig",
7
+ "AutoModel": "modeling_jina_judge.JinaJudge"
8
+ },
9
+ "dropout_prob": 0.2,
10
+ "hidden_dim": 512,
11
+ "model_type": "jina-judge",
12
+ "n_classes": 3,
13
+ "nhead": 8,
14
+ "num_decoder_layers": 5,
15
+ "torch_dtype": "float32",
16
+ "transformers_version": "4.45.1"
17
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fe9a2bf5e93503cf718757996c0b030b45800f51bdef2b0c309ecb6f3d9b9c8
3
+ size 1209895284
modeling_jina_judge.py ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from transformers import AutoModel, AutoTokenizer, AutoConfig
2
+ from transformers import PreTrainedModel, PretrainedConfig
3
+ from transformers import CONFIG_MAPPING, MODEL_MAPPING
4
+ import torch
5
+ import torch.nn.functional as F
6
+ import torch.nn as nn
7
+
8
+
9
+ class JinaJudgeConfig(PretrainedConfig):
10
+ model_type = "jina-judge"
11
+
12
+ def __init__(self, n_classes=3, hidden_dim=512, num_decoder_layers=5, nhead=8, dropout_prob=0.2, **kwargs):
13
+ super().__init__(**kwargs)
14
+ self.n_classes = n_classes
15
+ self.hidden_dim = hidden_dim
16
+ self.num_decoder_layers = num_decoder_layers
17
+ self.nhead = nhead
18
+ self.dropout_prob = dropout_prob
19
+
20
+
21
+ class JinaJudge(PreTrainedModel):
22
+ config_class = JinaJudgeConfig
23
+
24
+ def __init__(self, config: JinaJudgeConfig):
25
+ super().__init__(config)
26
+ self.tokenizer = AutoTokenizer.from_pretrained("jinaai/jina-embeddings-v3", trust_remote_code=True)
27
+ jina_config = AutoConfig.from_pretrained("jinaai/jina-embeddings-v3", trust_remote_code=True)
28
+ self.encoder = AutoModel.from_config(jina_config, trust_remote_code=True, torch_dtype=torch.bfloat16)
29
+ self.encoder.lora_main_params_trainable = True
30
+
31
+ self.projection = nn.Linear(self.encoder.config.hidden_size, config.hidden_dim)
32
+ # Transformer Decoder Layer
33
+ decoder_layer = nn.TransformerDecoderLayer(
34
+ d_model=config.hidden_dim,
35
+ nhead=config.nhead,
36
+ dim_feedforward=config.hidden_dim * 2,
37
+ dropout=config.dropout_prob
38
+ )
39
+
40
+ # Transformer Decoder
41
+ self.decoder = nn.TransformerDecoder(
42
+ decoder_layer,
43
+ num_layers=config.num_decoder_layers
44
+ )
45
+
46
+ # Embedding for a single token as the initial input to the decoder
47
+ self.decoder_input_embedding = nn.Parameter(
48
+ torch.randn(1, 1, config.hidden_dim,)
49
+ )
50
+
51
+ # Classification head
52
+ self.classification_head = nn.Linear(config.hidden_dim, config.n_classes)
53
+
54
+ def forward(self, prompts):
55
+ inputs = self.tokenizer(prompts, return_tensors="pt", padding=True, truncation=True).to(self.device)
56
+ encoder_outputs = self.encoder(**inputs)
57
+ encoder_hidden_states = encoder_outputs.last_hidden_state.float()
58
+ encoder_hidden_states = self.projection(encoder_hidden_states)
59
+
60
+ encoder_padding_mask = (inputs["attention_mask"] == 0).to(self.device)
61
+
62
+ batch_size = encoder_hidden_states.size(0)
63
+ decoder_input = self.decoder_input_embedding.expand(1, batch_size, -1).to(self.device)
64
+
65
+ decoder_output = self.decoder(
66
+ tgt=decoder_input,
67
+ memory=encoder_hidden_states.transpose(0, 1),
68
+ memory_key_padding_mask=encoder_padding_mask
69
+ ).squeeze(0)
70
+
71
+ logits = self.classification_head(decoder_output)
72
+ return logits
73
+
74
+
75
+ AutoConfig.register("jina-judge", JinaJudgeConfig)
76
+ AutoModel.register(JinaJudgeConfig, JinaJudge)