GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
azherali
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
azherali
Model Tree
unsloth/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "azherali/Riazi-8B-CPT" # load the tokenizer and the modeltokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto") # prepare the model inputprompt = "پاکستان کی ثقافت کے بارے میں مختصر وضاحت کریں۔"messages = [ {"role": "user", "content": prompt}] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) # conduct text completiongenerated_ids = model.generate( **model_inputs, max_new_tokens=2048) output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() try: # rindex finding 151668 (</think>) index = len(output_ids) - output_ids[::-1].index(151668)except ValueError: index = 0 content = tokenizer.decode( output_ids[index:], skip_special_tokens=True).strip("\n") print("content:", content)from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "azherali/Riazi-8B-CPT" # load the tokenizer and the modeltokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto") # prepare the model inputprompt = "پاکستان کی ثقافت کے بارے میں مختصر وضاحت کریں۔"messages = [ {"role": "user", "content": prompt}] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) # conduct text completiongenerated_ids = model.generate( **model_inputs, max_new_tokens=2048) output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() try: # rindex finding 151668 (</think>) index = len(output_ids) - output_ids[::-1].index(151668)except ValueError: index = 0 content = tokenizer.decode( output_ids[index:], skip_special_tokens=True).strip("\n") print("content:", content)