GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Luni
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Luni
Model Tree
Nanbeige/Nanbeige4.3-33B
Input Modalities
Output Modalities
Supported Functionality
<think> chain-of-thought reasoning (33.12B parameters, 262,144 context window).<think> chain-of-thought circuit remains fully operational."add_bos_token": false in tokenizer_config.json to eliminate upstream duplicate <|im_start|> BOS token emission when applying chat templates.python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model_id = "Luni/Nanbeige-4.3-33B-Heretic" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto") messages = [ {"role": "user", "content": "Write a detailed technical analysis of lock-free queue implementations in C++20."}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.6)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))4.00bpw, 4.50bpw, 5.00bpw)4.00bpw to 5.00bpw and SC_2.25bpw to SC_3.50bpw)2.25bpw, 2.50bpw, 3.00bpw, 3.50bpw)Q8_0 down to IQ1_S)from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model_id = "Luni/Nanbeige-4.3-33B-Heretic" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto") messages = [ {"role": "user", "content": "Write a detailed technical analysis of lock-free queue implementations in C++20."}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.6)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))