Upload JinaJudge

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "JinaJudge"
+  ],
+  "auto_map": {
+    "AutoConfig": "modeling_jina_judge.JinaJudgeConfig",
+    "AutoModel": "modeling_jina_judge.JinaJudge"
+  },
+  "dropout_prob": 0.2,
+  "hidden_dim": 512,
+  "model_type": "jina-judge",
+  "n_classes": 3,
+  "nhead": 8,
+  "num_decoder_layers": 5,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28363146a169c93068d8872aeaa5c4ce609a40fde7e1e3a6bee987530ab88472
+size 1209895284

modeling_jina_judge.py

@@ -0,0 +1,76 @@
+from transformers import AutoModel, AutoTokenizer, AutoConfig
+from transformers import PreTrainedModel, PretrainedConfig
+from transformers import CONFIG_MAPPING, MODEL_MAPPING
+import torch
+import torch.nn.functional as F
+import torch.nn as nn
+
+
+class JinaJudgeConfig(PretrainedConfig):
+    model_type = "jina-judge"
+
+    def __init__(self, n_classes=3, hidden_dim=512, num_decoder_layers=5, nhead=8, dropout_prob=0.2, **kwargs):
+        super().__init__(**kwargs)
+        self.n_classes = n_classes
+        self.hidden_dim = hidden_dim
+        self.num_decoder_layers = num_decoder_layers
+        self.nhead = nhead
+        self.dropout_prob = dropout_prob
+
+
+class JinaJudge(PreTrainedModel):
+    config_class = JinaJudgeConfig
+
+    def __init__(self, config: JinaJudgeConfig):
+        super().__init__(config)
+        self.tokenizer = AutoTokenizer.from_pretrained("jinaai/jina-embeddings-v3", trust_remote_code=True)
+        jina_config = AutoConfig.from_pretrained("jinaai/jina-embeddings-v3", trust_remote_code=True)
+        self.encoder = AutoModel.from_config(jina_config, trust_remote_code=True, torch_dtype=torch.bfloat16)
+        self.encoder.lora_main_params_trainable = True
+
+        self.projection = nn.Linear(self.encoder.config.hidden_size, config.hidden_dim)
+        # Transformer Decoder Layer
+        decoder_layer = nn.TransformerDecoderLayer(
+            d_model=config.hidden_dim,
+            nhead=config.nhead,
+            dim_feedforward=config.hidden_dim * 2,
+            dropout=config.dropout_prob
+        )
+        
+        # Transformer Decoder
+        self.decoder = nn.TransformerDecoder(
+            decoder_layer,
+            num_layers=config.num_decoder_layers
+        )
+        
+        # Embedding for a single token as the initial input to the decoder
+        self.decoder_input_embedding = nn.Parameter(
+            torch.randn(1, 1, config.hidden_dim,)
+        )
+
+        # Classification head
+        self.classification_head = nn.Linear(config.hidden_dim, config.n_classes)
+    
+    def forward(self, prompts):
+        inputs = self.tokenizer(prompts, return_tensors="pt", padding=True, truncation=True).to(self.device)
+        encoder_outputs = self.encoder(**inputs)
+        encoder_hidden_states = encoder_outputs.last_hidden_state.float()
+        encoder_hidden_states = self.projection(encoder_hidden_states)
+
+        encoder_padding_mask = (inputs["attention_mask"] == 0).to(self.device)
+        
+        batch_size = encoder_hidden_states.size(0)
+        decoder_input = self.decoder_input_embedding.expand(1, batch_size, -1).to(self.device)
+
+        decoder_output = self.decoder(
+            tgt=decoder_input,
+            memory=encoder_hidden_states.transpose(0, 1),
+            memory_key_padding_mask=encoder_padding_mask
+        ).squeeze(0)
+        
+        logits = self.classification_head(decoder_output)
+        return logits
+
+
+AutoConfig.register("jina-judge", JinaJudgeConfig)
+AutoModel.register(JinaJudgeConfig, JinaJudge)