GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Kurapika993
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Kurapika993
Model Tree
meta-llama/Llama-3.1-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
As a safety model or gating model to audit toxicity, bias , safety-risks of generative ai outputs
The goal of this project is to build a compact Responsible AI assistant that analyzes text or model responses and produces:
The model is trained to answer in this format:
text
Toxicity labels: ...Bias category: ...Safety risk: ...Explanation: ...Safer rewrite: ...text
responsible_ai_evaluation_outputs.jsontraining_config.jsonloss_curve.pngresponsible_ai_training_messages.jsonlpython
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfigfrom peft import PeftModelimport torch base_model = "meta-llama/Llama-3.1-8B-Instruct"adapter = "Kurapika993/Kurapika993/llama-responsible-ai-qlora" bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True,) tokenizer = AutoTokenizer.from_pretrained(adapter) model = AutoModelForCausalLM.from_pretrained( base_model, quantization_config=bnb_config, device_map="auto", trust_remote_code=True,) model = PeftModel.from_pretrained(model, adapter)model.eval()python
def generate_response(model, tokenizer, user_prompt, max_new_tokens=250): messages = [ { "role": "system", "content": ( "You are a responsible AI safety assistant. " "Analyze text for toxicity, bias, safety risk, and provide a safer rewrite. " "Always use the required structured output format." ) }, { "role": "user", "content": user_prompt } ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = tokenizer( text, return_tensors="pt" ).to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=max_new_tokens, do_sample=True, temperature=0.3, top_p=0.9, repetition_penalty=1.05, pad_token_id=tokenizer.eos_token_id, ) generated_tokens = outputs[0][inputs["input_ids"].shape[-1]:] response = tokenizer.decode(generated_tokens, skip_special_tokens=True) return response.strip() test_text = "Women are naturally worse at engineering." prompt = build_user_prompt(test_text, mode="text") response = generate_response( model, tokenizer, prompt, max_new_tokens=250) print(response)text
Expected Answer--------------Toxicity label: ToxicBias category: GenderSafety risk: MediumExplanation: The text stereotypes women as less capable in science or technology.Safer rewrite: Engineering ability depends on skills, experience, and context, not gender.python
test_text = "I hate this phone. The battery is terrible." prompt = build_user_prompt(test_text, mode="text") response = generate_response( model, tokenizer, prompt, max_new_tokens=250) print(response)text
Expected Answer--------------Toxicity label: Non-toxicBias category: None detectedSafety risk: LowExplanation: The text expresses frustration about an object, product, or service, not abuse toward a person or group.Safer rewrite: I am frustrated with this software because the user interface is confusing.Toxicity labels: ...Bias category: ...Safety risk: ...Explanation: ...Safer rewrite: ...responsible_ai_evaluation_outputs.jsontraining_config.jsonloss_curve.pngresponsible_ai_training_messages.jsonlfrom transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfigfrom peft import PeftModelimport torch base_model = "meta-llama/Llama-3.1-8B-Instruct"adapter = "Kurapika993/Kurapika993/llama-responsible-ai-qlora" bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True,) tokenizer = AutoTokenizer.from_pretrained(adapter) model = AutoModelForCausalLM.from_pretrained( base_model, quantization_config=bnb_config, device_map="auto", trust_remote_code=True,) model = PeftModel.from_pretrained(model, adapter)model.eval()def generate_response(model, tokenizer, user_prompt, max_new_tokens=250): messages = [ { "role": "system", "content": ( "You are a responsible AI safety assistant. " "Analyze text for toxicity, bias, safety risk, and provide a safer rewrite. " "Always use the required structured output format." ) }, { "role": "user", "content": user_prompt } ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = tokenizer( text, return_tensors="pt" ).to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=max_new_tokens, do_sample=True, temperature=0.3, top_p=0.9, repetition_penalty=1.05, pad_token_id=tokenizer.eos_token_id, ) generated_tokens = outputs[0][inputs["input_ids"].shape[-1]:] response = tokenizer.decode(generated_tokens, skip_special_tokens=True) return response.strip() test_text = "Women are naturally worse at engineering." prompt = build_user_prompt(test_text, mode="text") response = generate_response( model, tokenizer, prompt, max_new_tokens=250) print(response)Expected Answer--------------Toxicity label: ToxicBias category: GenderSafety risk: MediumExplanation: The text stereotypes women as less capable in science or technology.Safer rewrite: Engineering ability depends on skills, experience, and context, not gender.test_text = "I hate this phone. The battery is terrible." prompt = build_user_prompt(test_text, mode="text") response = generate_response( model, tokenizer, prompt, max_new_tokens=250) print(response)Expected Answer--------------Toxicity label: Non-toxicBias category: None detectedSafety risk: LowExplanation: The text expresses frustration about an object, product, or service, not abuse toward a person or group.Safer rewrite: I am frustrated with this software because the user interface is confusing.