GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
uzairkhn
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
uzairkhn
Model Tree
google/gemma-3-4b-it
Input Modalities
Output Modalities
Supported Functionality
Because this model is a fully merged standalone architecture, you can load it directly using standard Hugging Face transformers libraries without needing any separate adapter configurations.
python
import torchfrom transformers import AutoProcessor, AutoModelForImageTextToText, BitsAndBytesConfig # Direct repository IDmodel_id = "uzairkhn/Almas-Pashto-AI" print("Loading processor...")processor = AutoProcessor.from_pretrained(model_id) print("Configuring 4-bit quantization...")bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16) print("Loading Almas Pashto AI...")model = AutoModelForImageTextToText.from_pretrained( model_id, quantization_config=bnb_config, device_map="auto") # Example Inferencetest_prompt = "مصنوعي مصنوعي ځیرکتیا څه شی دی؟" messages = [ {"role": "user", "content": [{"type": "text", "text": test_prompt}]}] text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[text], return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=512, temperature=0.7, do_sample=True, repetition_penalty=1.1 ) generated_text = processor.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)print(generated_text)import torchfrom transformers import AutoProcessor, AutoModelForImageTextToText, BitsAndBytesConfig # Direct repository IDmodel_id = "uzairkhn/Almas-Pashto-AI" print("Loading processor...")processor = AutoProcessor.from_pretrained(model_id) print("Configuring 4-bit quantization...")bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16) print("Loading Almas Pashto AI...")model = AutoModelForImageTextToText.from_pretrained( model_id, quantization_config=bnb_config, device_map="auto") # Example Inferencetest_prompt = "مصنوعي مصنوعي ځیرکتیا څه شی دی؟" messages = [ {"role": "user", "content": [{"type": "text", "text": test_prompt}]}] text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = processor(text=[text], return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=512, temperature=0.7, do_sample=True, repetition_penalty=1.1 ) generated_text = processor.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)print(generated_text)