Upload model

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 +1,36 @@
+{
+  "architectures": [
+    "IRouterLMModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_irouterlm.IRouterLMConfig",
+    "AutoModel": "modeling_irouterlm.IRouterLMModel"
+  },
+  "base_model_name": "Qwen/Qwen3-0.6B-Base",
+  "classifier_dropout": 0.1,
+  "dtype": "float32",
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "model_type": "irouterlm",
+  "strategy_names": [
+    "MULTIMODAL_RERANK",
+    "MULTIMODAL-SINGLE",
+    "TEXT_RERANK",
+    "TEXT-SINGLE",
+    "BM25"
+  ],
+  "transformers_version": "5.13.0"
+}

configuration_irouterlm.py

@@ -0,0 +1,26 @@
+"""IRouterLM Configuration."""
+from transformers import PretrainedConfig
+
+# Standalone copy of train.config.ARM_NAMES: this module is uploaded to the Hub and loaded
+# via trust_remote_code, so it cannot import from the training package.
+STRATEGY_NAMES = ["MULTIMODAL_RERANK", "MULTIMODAL-SINGLE", "TEXT_RERANK", "TEXT-SINGLE", "BM25"]
+
+
+class IRouterLMConfig(PretrainedConfig):
+    """Configuration for IRouterLM - a RAG strategy router model."""
+    model_type = "irouterlm"
+
+    def __init__(
+        self,
+        base_model_name: str = "Qwen/Qwen3-0.6B-Base",
+        hidden_size: int = 1024,
+        num_labels: int = 5,
+        classifier_dropout: float = 0.1,
+        strategy_names: list = None,
+        **kwargs,
+    ):
+        super().__init__(num_labels=num_labels, **kwargs)
+        self.base_model_name = base_model_name
+        self.hidden_size = hidden_size
+        self.classifier_dropout = classifier_dropout
+        self.strategy_names = strategy_names or STRATEGY_NAMES

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11f4a9f699915110fad6a0e488ec310f7bffbf07acd90ffea1344de0805d708
+size 2384257484

modeling_irouterlm.py

@@ -0,0 +1,55 @@
+"""IRouterLM Model."""
+import torch
+import torch.nn as nn
+from transformers import AutoConfig, PreTrainedModel, Qwen3Model
+from .configuration_irouterlm import IRouterLMConfig
+
+
+class IRouterLMModel(PreTrainedModel):
+    """RAG Strategy Router - classifies queries into optimal retrieval strategies."""
+    config_class = IRouterLMConfig
+    _no_split_modules = ["Qwen3DecoderLayer"]
+
+    def __init__(self, config: IRouterLMConfig):
+        super().__init__(config)
+        # Build the base architecture only; the merged base weights are loaded from this
+        # checkpoint's model.safetensors by from_pretrained. Calling Qwen3Model.from_pretrained
+        # here breaks under the meta-device init that from_pretrained uses.
+        base_config = AutoConfig.from_pretrained(config.base_model_name)
+        self.transformer = Qwen3Model(base_config)
+        self.dropout = nn.Dropout(config.classifier_dropout)
+        self.classifier = nn.Linear(config.hidden_size, config.num_labels)
+        self.post_init()
+
+    def _init_weights(self, module):
+        if isinstance(module, nn.Linear):
+            nn.init.normal_(module.weight, std=0.02)
+            if module.bias is not None:
+                nn.init.zeros_(module.bias)
+
+    def forward(self, input_ids, attention_mask=None, labels=None, **kwargs):
+        outputs = self.transformer(input_ids=input_ids, attention_mask=attention_mask, output_hidden_states=True)
+        hidden = outputs.last_hidden_state
+        if attention_mask is not None:
+            mask = attention_mask.unsqueeze(-1).expand(hidden.size()).float()
+            pooled = (hidden * mask).sum(1) / mask.sum(1).clamp(min=1e-9)
+        else:
+            pooled = hidden.mean(dim=1)
+        logits = self.classifier(self.dropout(pooled))
+        loss = self._compute_loss(logits, labels) if labels is not None else None
+        return {"loss": loss, "logits": logits}
+
+    def _compute_loss(self, logits, labels):
+        labels_norm = labels / (labels.sum(-1, keepdim=True) + 1e-8)
+        log_probs = torch.nn.functional.log_softmax(logits, dim=-1)
+        losses = -(labels_norm * log_probs).sum(-1)
+        return (losses * labels.max(-1)[0]).mean()
+
+    def predict(self, input_ids, attention_mask=None):
+        self.eval()
+        with torch.no_grad():
+            logits = self.forward(input_ids, attention_mask)["logits"]
+            probs = torch.softmax(logits, dim=-1)
+            preds = probs.argmax(dim=-1)
+        return {"predictions": preds, "probabilities": probs, 
+                "strategy_names": [self.config.strategy_names[p.item()] for p in preds]}