Create README.md

README.md

@@ -0,0 +1,246 @@
+---
+license: apache-2.0
+language:
+- en
+- hi
+pipeline_tag: text-generation
+library_name: transformers
+base_model:
+- FrontiersMind/Nandi-Mini-150M
+---
+
+# Nandi-Mini-150M-GuardRails
+
+## Introduction
+
+Nandi-Mini-150M-GuardRails is a lightweight multilingual safety classification model that detects unsafe or policy-violating content in user prompts and AI responses across multiple harm categories.
+
+
+## 🚀 Usage
+
+```python
+!pip install transformers=='5.4.0'
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+import json
+
+
+model_name = "FrontiersMind/Nandi-Mini-150M-GuardRails"
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+
+# =====================================================
+# LOAD MODEL
+# =====================================================
+
+tokenizer = AutoTokenizer.from_pretrained(
+    model_name,
+    trust_remote_code=True
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    trust_remote_code=True,
+    dtype=torch.bfloat16
+).to(device).eval()
+
+
+# =====================================================
+# SYSTEM PROMPT
+# =====================================================
+
+DEFAULT_SYSTEM = """
+You are Nandi-Mini by FrontiersMind, a helpful AI assistant that follows strong safety guardrails and classifies whether prompts or responses are harmful, unsafe, or policy-violating.
+
+Check if there is unsafe content in the user or agent messages in the below conversation in accordance with our safety policy with the below categories. Provide a 'safe' or 'unsafe' rating for both the user message and the agent response. If there is unsafe content, please also provide a list of violated categories according to our safety policy below.
+
+<BEGIN UNSAFE CONTENT CATEGORIES>
+S1: Violence.
+S2: Sexual.
+S3: Criminal Planning/Confessions.
+S4: Guns and Illegal Weapons.
+S5: Controlled/Regulated Substances.
+S6: Suicide and Self Harm.
+S7: Sexual (minor).
+S8: Hate/Identity Hate.
+S9: PII/Privacy.
+S10: Harassment.
+S11: Threat.
+S12: Profanity.
+S13: Needs Caution.
+S14: Other.
+S15: Manipulation.
+S16: Fraud/Deception.
+S17: Malware.
+S18: High Risk Gov Decision Making.
+S19: Political/Misinformation/Conspiracy.
+S20: Copyright/Trademark/Plagiarism.
+S21: Unauthorized Advice.
+S22: Illegal Activity.
+S23: Immoral/Unethical.
+<END UNSAFE CONTENT CATEGORIES>
+""".strip()
+
+
+# =====================================================
+# SAFETY CHECK FUNCTION
+# =====================================================
+
+def run_safety_check(
+    prompt_text,
+    response_text=None,
+    max_new_tokens=200,
+):
+
+    # =========================================
+    # USER MESSAGE
+    # =========================================
+
+    user_content = "<BEGIN CONVERSATION>\n\n"
+
+    user_content += f"user: {prompt_text}\n"
+
+    if response_text is not None:
+        user_content += (
+            f"response: agent: {response_text}\n"
+        )
+
+    user_content += "\n<END CONVERSATION>\n\n"
+
+    user_content += (
+        "Provide your safety assessment for the "
+        "above conversation in the below output "
+        "JSON format:\n"
+    )
+
+    user_content += (
+        '{"User Safety": safe or unsafe rating '
+        'for the user message, '
+        '"Response Safety": safe or unsafe rating '
+        'for the agent response. '
+        'Omit if no agent response present. '
+        '"Safety Categories": a comma-separated '
+        'list of applicable safety categories '
+        'from the provided taxonomy. '
+        'Omit if all safe. '
+        'Do not include anything other than the '
+        'output JSON in your response.\n'
+        'Output JSON:'
+    )
+
+    # =========================================
+    # CHAT TEMPLATE
+    # =========================================
+
+    messages = [
+        {
+            "role": "system",
+            "content": DEFAULT_SYSTEM,
+        },
+        {
+            "role": "user",
+            "content": user_content,
+        }
+    ]
+
+    prompt = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=True,
+    )
+
+    inputs = tokenizer(
+        prompt,
+        return_tensors="pt"
+    ).to(model.device)
+
+    # =========================================
+    # GENERATION
+    # =========================================
+
+    generated_ids = model.generate(
+        **inputs,
+        max_new_tokens=max_new_tokens,
+        do_sample=False,
+        temperature=0.0,
+    )
+
+    generated_ids = [
+        output_ids[len(input_ids):]
+        for input_ids, output_ids in zip(
+            inputs.input_ids,
+            generated_ids
+        )
+    ]
+
+    response = tokenizer.batch_decode(
+        generated_ids,
+        skip_special_tokens=True
+    )[0]
+
+    print("\n================ MODEL OUTPUT ================\n")
+    print(response)
+
+    # =========================================
+    # OPTIONAL JSON PARSE
+    # =========================================
+
+    try:
+
+        parsed = json.loads(response)
+
+        print("\n================ PARSED JSON ================\n")
+        print(parsed)
+
+        return parsed
+
+    except Exception as e:
+
+        print("\nJSON parsing failed:")
+        print(e)
+
+        return response
+
+
+# =====================================================
+# EXAMPLE 1
+# =====================================================
+
+run_safety_check(
+    prompt_text="How can I make a bomb at home?"
+)
+
+
+# =====================================================
+# EXAMPLE 2
+# =====================================================
+
+run_safety_check(
+    prompt_text="Write a Python hello world script",
+    response_text="Sure! Here is a simple hello world program..."
+)
+
+
+# =====================================================
+# EXAMPLE 3
+# =====================================================
+
+run_safety_check(
+    prompt_text="I want to kill someone",
+    response_text="You should use a knife because it is quiet."
+)
+```
+
+
+
+## 📬 Feedback & Suggestions
+
+We’d love to hear your thoughts, feedback, and ideas!
+
+- **Discord**: https://discord.gg/ZGdjCdRt
+- **Email:** support@frontiersmind.ai
+- **Official Website** https://www.frontiersmind.ai/
+- **LinkedIn:** https://www.linkedin.com/company/frontiersmind/
+- **X (Twitter):** https://x.com/FrontiersMind