GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Chandrudp29
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Chandrudp29
Model Tree
openai-community/gpt2
Input Modalities
Output Modalities
Supported Functionality
python
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel tokenizer = AutoTokenizer.from_pretrained("Chandrudp29/gpt2-lora-aisafety")base_model = AutoModelForCausalLM.from_pretrained("gpt2")model = PeftModel.from_pretrained(base_model, "Chandrudp29/gpt2-lora-aisafety")model.eval() prompt = "AI alignment is the challenge of"inputs = tokenizer(prompt, return_tensors="pt") with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=80, temperature=0.7, do_sample=True, top_k=50, repetition_penalty=1.2, pad_token_id=tokenizer.eos_token_id, ) print(tokenizer.decode(output[0], skip_special_tokens=True))| Base model | gpt2 (117M params) |
| Adapter type | LoRA |
| LoRA rank | r=8 |
| lora_alpha | 16 |
| target_modules | c_attn, c_proj |
| Trainable params | 811,008 (0.65%) |
| Training examples | 30 AI safety texts |
| Epochs | 20 |
| Learning rate | 2e-4 |
| Hardware | NVIDIA T4 (16GB) |
| Training time | 18 seconds |
| Adapter size | 3.25 MB |
The model was fine-tuned on short texts covering:
text
AI alignment is the challenge of...Mechanistic interpretability seeks to...Constitutional AI is a method for...Corrigibility refers to an AI system that...The risks of advanced AI include...Training code: chandrudp29/lora-finetune
LoRA freezes pre-trained model weights and injects trainable low-rank matrices into each transformer layer. Instead of training all 125M parameters, only the two small adapter matrices (A × B where rank=8) are updated — reducing trainable parameters by 99.35%.
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel tokenizer = AutoTokenizer.from_pretrained("Chandrudp29/gpt2-lora-aisafety")base_model = AutoModelForCausalLM.from_pretrained("gpt2")model = PeftModel.from_pretrained(base_model, "Chandrudp29/gpt2-lora-aisafety")model.eval() prompt = "AI alignment is the challenge of"inputs = tokenizer(prompt, return_tensors="pt") with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=80, temperature=0.7, do_sample=True, top_k=50, repetition_penalty=1.2, pad_token_id=tokenizer.eos_token_id, ) print(tokenizer.decode(output[0], skip_special_tokens=True))AI alignment is the challenge of...Mechanistic interpretability seeks to...Constitutional AI is a method for...Corrigibility refers to an AI system that...The risks of advanced AI include...