Upload lora_jailbreak_classifier_roberta-base_model LoRA model

README.md

@@ -0,0 +1,96 @@
+---
+license: apache-2.0
+base_model: roberta-base
+tags:
+- lora
+- semantic-router
+- classification-classification
+- text-classification
+- candle
+- rust
+language:
+- en
+pipeline_tag: text-classification
+library_name: candle
+---
+
+# lora_jailbreak_classifier_roberta-base_model
+
+## Model Description
+
+This is a LoRA (Low-Rank Adaptation) fine-tuned model based on **roberta-base** for Multi-task classification.
+
+This model is part of the [semantic-router](https://github.com/vllm-project/semantic-router) project and is optimized for use with the Candle framework in Rust.
+
+## Model Details
+
+- **Base Model**: roberta-base
+- **Task**: Classification Classification
+- **Framework**: Candle (Rust)
+- **Model Size**: ~476MB
+- **LoRA Rank**: 16
+- **LoRA Alpha**: 16
+- **Target Modules**: attention.self.query, attention.self.value, attention.output.dense, intermediate.dense, output.dense
+
+## Usage
+
+### With semantic-router (Recommended)
+
+```python
+from semantic_router import SemanticRouter
+
+# The model will be automatically downloaded and used
+router = SemanticRouter()
+results = router.classify_batch(["Your text here"])
+```
+
+### With Candle (Rust)
+
+```rust
+use candle_core::{Device, Tensor};
+use candle_transformers::models::bert::BertModel;
+
+// Load the model using Candle
+let device = Device::Cpu;
+let model = BertModel::load(&device, &config, &weights)?;
+```
+
+## Training Details
+
+This model was fine-tuned using LoRA (Low-Rank Adaptation) technique:
+
+- **Rank**: 16
+- **Alpha**: 16 
+- **Dropout**: 0.1
+- **Target Modules**: attention.self.query, attention.self.value, attention.output.dense, intermediate.dense, output.dense
+
+## Performance
+
+Multi-task classification
+
+For detailed performance metrics, see the [training results](https://github.com/vllm-project/semantic-router/blob/main/training-result.md).
+
+## Files
+
+- `model.safetensors`: LoRA adapter weights
+- `config.json`: Model configuration
+- `lora_config.json`: LoRA-specific configuration
+- `tokenizer.json`: Tokenizer configuration
+- `label_mapping.json`: Label mappings for classification
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{semantic-router-lora,
+  title={LoRA Fine-tuned Models for Semantic Router},
+  author={Semantic Router Team},
+  year={2025},
+  url={https://github.com/vllm-project/semantic-router}
+}
+```
+
+## License
+
+Apache 2.0

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265,
+  "id2label": {
+    "0": "benign",
+    "1": "jailbreak"
+  },
+  "label2id": {
+    "benign": 0,
+    "jailbreak": 1
+  }
+}

label_mapping.json

@@ -0,0 +1 @@
+{"label_to_id": {"benign": 0, "jailbreak": 1}, "id_to_label": {"0": "benign", "1": "jailbreak"}}

lora_config.json

@@ -0,0 +1 @@
+{"rank": 16, "alpha": 16, "dropout": 0.1, "target_modules": ["attention.self.query", "attention.self.value", "attention.output.dense", "intermediate.dense", "output.dense"]}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1680101501eca6ea6fc53c51eac03817637f01fe117645bbb932f55561f9dc63
+size 498612824

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}