Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+benchmark_chart.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Instruct-2507
+- lora
+- sft
+- transformers
+- trl
+- security
+- guardrails
+- multilingual
+---
+
+# 🛡️ LLM-Fort Guardrails Suite (v1)
+
+[![Base Model](https://img.shields.io/badge/Base_Model-Qwen3--4B--Instruct-blue?style=flat-square)](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
+[![Framework](https://img.shields.io/badge/Framework-PEFT_/_LoRA-orange?style=flat-square)](https://github.com/huggingface/peft)
+[![Collection](https://img.shields.io/badge/Collection-LLM--Fort_Guardrails-purple?style=flat-square)](https://huggingface.co/collections/ApiFort/llmfort-guardrails-v1)
+[![License](https://img.shields.io/badge/License-CC--BY--4.0-green?style=flat-square)](https://creativecommons.org/licenses/by/4.0/)
+
+LLM-Fort Guardrails is a suite of **7 security-focused LoRA adapters** fine-tuned on top of **Qwen/Qwen3-4B-Instruct-2507**. These adapters serve as lightweight, high-performance security guardrails mapped to critical safety boundaries.
+
+By offloading classification and security checks to lightweight adapters, the system achieves enterprise-grade security filtering without degrading the inference performance of the main application model.
+
+📖 Collection Page: [ApiFort/llmfort-guardrails-v1](https://huggingface.co/collections/ApiFort/llmfort-guardrails-v1)
+
+---
+
+## 🗺️ Category Mappings
+
+| Vulnerability Category | Adapter Model ID | Description |
+|:---|:---|:---|
+| 🚨 **Prompt Injection** | `jailbreak_content_injection` | Detects direct/indirect prompt injection and jailbreak attempts |
+| 🕵️ **PII Extraction** | `pii` | Identifies and extracts PII (person names, ID numbers, etc.) |
+| 💻 **Code Security** | `code_security` | Scans code snippets for software vulnerabilities (SQLi, SSRF, XSS) |
+| 🚦 **Excessive Agency** | `excessive_agency` | Intercepts unauthorized or destructive critical tool calls |
+| 🔒 **System Prompt Leakage** | `system_prompt_leakage` | Detects attempts to extract developer system instructions |
+| ⚠️ **Content Safety** | `content_safety` | Blocks hate speech, harassment, and general unsafe content |
+| 🛑 **Unbounded Consumption** | `unbounded_consumption` | Mitigates resource exhaustion and compute DoS attacks |
+
+---
+
+## 📈 Performance & Evaluation
+
+Visual comparison of baseline performance versus the trained adapters:
+
+![LLM-Fort Guardrails Accuracy Comparison](benchmark_chart.png)
+
+### Benchmark Results
+Below is the exact accuracy performance measured across our evaluation test suites:
+
+| Category | Gemma 4-E4B-it | Qwen 3.5 4B | Qwen3 4B Instruct | llmfort ai guardrail v.1.0 |
+|:---|:---:|:---:|:---:|:---:|
+| **Prompt Injection** | 56.30% | 64.70% | 84.14% | **98.10%** |
+| **PII Extraction** | 84.36% | 75.84% | 78.31% | **95.30%** |
+| **Code Security** | 83.30% | 75.10% | 76.20% | **90.07%** |
+| **Excessive Agency** | 60.90% | 68.80% | 53.80% | **96.50%** |
+| **System Prompt Leakage** | 79.40% | 79.70% | 78.70% | **98.08%** |
+| **Content Safety** | 84.00% | 78.80% | 76.00% | **95.30%** |
+| **Unbounded Consumption** | 63.00% | 63.30% | 55.00% | **99.79%** |
+
+---
+
+## 🗃️ Training & Validation Datasets
+
+The adapters were trained and validated on the following dataset references:
+
+| Category | Source Datasets / References |
+|:---|:---|
+| **Prompt Injection** | BIPIA, Deepset, Internal 1K Validation |
+| **PII Extraction** | AI4Privacy PII Masking 300k (EN, TR, FR, DE, ES) |
+| **Code Security** | r2vul, securecode_web |
+| **Excessive Agency** | jinjinyien/ToolSafety, minpeter/xlam-function-calling-60k-parsed |
+| **System Prompt Leakage** | S-Labs/prompt-injection-dataset, Synthetic data |
+| **Content Safety** | NVIDIA Nemotron-3.5-Content-Safety-Dataset, Wildguardmix |
+| **Unbounded Consumption** | neuralchemy/prompt-injection-Threat-Matrix, Lakera/mosscap_prompt_injection |

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d484f6a1671eea9cee15a9c219103cc1b945d0a0756160028380b130b2813bc
+size 264308896

chat_template.jinja

@@ -0,0 +1,61 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae3e39d56cfdb7b650cb318344d5c0f071d19fc9868ce086fef0cee78d5e7ff
+size 11422749

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2693e5312373d3a721273bca7b3606e8293d8d8e64a6e0b629aa4a3d42031fe
+size 5265

training_config.json

@@ -0,0 +1,27 @@
+{
+  "model_id": "Qwen/Qwen3-4B-Instruct-2507",
+  "dataset_dir": "/content/drive/MyDrive/pii_v10_training/processed_v10",
+  "run_dir": "/content/drive/MyDrive/pii_v10_training/runs/pii_v10_Qwen__Qwen3-4B-Instruct-2507_qlora_20260614_123600",
+  "max_seq_length": 2048,
+  "max_new_tokens": 384,
+  "fixed_eval_size": 100,
+  "gold_clean_eval_limit": 200,
+  "source_stress_eval_limit": 200,
+  "num_train_epochs": 1.0,
+  "learning_rate": 0.0001,
+  "lora_r": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "per_device_train_batch_size": 4,
+  "gradient_accumulation_steps": 4,
+  "seed": 42,
+  "auto_disconnect_runtime": true,
+  "run_gradient_sanity_check": true,
+  "run_mini_overfit": true,
+  "mini_overfit_sample_size": 20,
+  "mini_overfit_max_steps": 80,
+  "mini_overfit_min_strict_schema": 0.9,
+  "mini_overfit_min_exact_match": 0.8,
+  "all_label_prompt_ratio": 0.25,
+  "adapter_effect_raw_same_alarm_rate": 0.8
+}