GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ayjays132
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ayjays132
Model Tree
Input Modalities
Output Modalities
Supported Functionality
tokenizer = AutoTokenizer.from_pretrained("ayjays132/PhillNet-1") tokenizer.add_special_tokens({'pad_token': '[PAD]'})
model = AutoModelForCausalLM.from_pretrained("ayjays132/PhillNet-1")
conversation_history = [ "Hello, how are you?", "I'm doing well, thank you! How about you?", "I'm good too. What's new with you?", "Working on innovative neuroevolution techniques—what about you?" ]
conversation_text = " ".join(conversation_history) input_ids = tokenizer.encode(conversation_text, return_tensors="pt", padding=True, truncation=True) output_ids = model.generate(input_ids, max_length=150, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id) generated_response = tokenizer.decode(output_ids[0], skip_special_tokens=True) print("Generated Response:", generated_response)
logging.basicConfig(level=logging.INFO) logger = logging.getLogger(name)
def load_custom_model(model_name, device): try: model = AutoModelForCausalLM.from_pretrained(model_name).to(device) logger.info(f"Model loaded successfully from {model_name}") return model except Exception as e: logger.error(f"An error occurred: {e}") raise
def load_tokenizer(tokenizer_name): try: tokenizer = AutoTokenizer.from_pretrained(tokenizer_name) logger.info(f"Tokenizer loaded successfully from {tokenizer_name}") return tokenizer except Exception as e: logger.error(f"An error occurred: {e}") raise
if name == "main": device = torch.device("cuda" if torch.cuda.is_available() else "cpu") model_name = "ayjays132/PhillNet-1" tokenizer = load_tokenizer(model_name) model = load_custom_model(model_name, device) print("Custom model and tokenizer loaded successfully.")