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
azherali/Aqal-1.0-8B
Input Modalities
Output Modalities
Supported Functionality
python
from unsloth import FastLanguageModelimport torch max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!dtype = ( None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+)load_in_4bit = False # Use 4bit quantization to reduce memory usage. Can be False.load_in_8bit = False # Use 8bit quantization to reduce memory usage. Can be False. model, tokenizer = FastLanguageModel.from_pretrained( model_name="azherali/Aqal-1.0-8B-Instruct", # Choose ANY max_seq_length=max_seq_length, dtype=dtype, load_in_4bit=load_in_4bit, load_in_8bit=load_in_8bit, # token = "YOUR_HF_TOKEN", # HF Token for gated models)FastLanguageModel.for_inference(model) # Enable native 2x faster inference messages = [ { "role": "user", "content": "پانچ بچوں نے 20 چاکلیٹس برابر بانٹیں۔ ہر بچے کو کتنی چاکلیٹس ملیں گی؟", }]text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, # Must add for generation) from transformers import TextStreamer _ = model.generate( **tokenizer(text, return_tensors="pt").to("cuda"), temperature=0.6, top_p=0.95, top_k=20, # For non thinking streamer=TextStreamer(tokenizer, skip_prompt=True),)This model was trained with SFT.
from unsloth import FastLanguageModelimport torch max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!dtype = ( None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+)load_in_4bit = False # Use 4bit quantization to reduce memory usage. Can be False.load_in_8bit = False # Use 8bit quantization to reduce memory usage. Can be False. model, tokenizer = FastLanguageModel.from_pretrained( model_name="azherali/Aqal-1.0-8B-Instruct", # Choose ANY max_seq_length=max_seq_length, dtype=dtype, load_in_4bit=load_in_4bit, load_in_8bit=load_in_8bit, # token = "YOUR_HF_TOKEN", # HF Token for gated models)FastLanguageModel.for_inference(model) # Enable native 2x faster inference messages = [ { "role": "user", "content": "پانچ بچوں نے 20 چاکلیٹس برابر بانٹیں۔ ہر بچے کو کتنی چاکلیٹس ملیں گی؟", }]text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, # Must add for generation) from transformers import TextStreamer _ = model.generate( **tokenizer(text, return_tensors="pt").to("cuda"), temperature=0.6, top_p=0.95, top_k=20, # For non thinking streamer=TextStreamer(tokenizer, skip_prompt=True),)