GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ehzawad
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
ehzawad
Model Tree
Qwen/Qwen3-1.7B
Input Modalities
Output Modalities
Supported Functionality
You can use this model by loading the base model and applying this PEFT adapter. Here is a standalone code snippet:
!pip install --upgrade torchao !pip install -U bitsandbytes>=0.46.1
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModel base_model_id = "Qwen/Qwen3-1.7B"adapter_id = "ehzawad/qwen3-1.7b-gsm8k-grpo" bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16,) base_model = AutoModelForCausalLM.from_pretrained( base_model_id, quantization_config=bnb_config, device_map="auto",) tokenizer = AutoTokenizer.from_pretrained(adapter_id)hf_model = PeftModel.from_pretrained(base_model, adapter_id, is_trainable=False)hf_model.eval() prompt = "Janet has 3 bags with 4 apples each. She gives away 5 apples. How many remain?"system_prompt = ( "You are a careful math reasoning assistant. " "Solve the problem step by step, but keep the solution concise. " "End with exactly one final answer in the form \boxed{answer}.")messages = [ {"role": "system", "content": system_prompt}, {"role": "user", "content": prompt}] inputs = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(hf_model.device) with torch.inference_mode(): outputs = hf_model.generate( **inputs, max_new_tokens=512, temperature=0.6, do_sample=True, ) response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)print(response)import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModel base_model_id = "Qwen/Qwen3-1.7B"adapter_id = "ehzawad/qwen3-1.7b-gsm8k-grpo" bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16,) base_model = AutoModelForCausalLM.from_pretrained( base_model_id, quantization_config=bnb_config, device_map="auto",) tokenizer = AutoTokenizer.from_pretrained(adapter_id)hf_model = PeftModel.from_pretrained(base_model, adapter_id, is_trainable=False)hf_model.eval() prompt = "Janet has 3 bags with 4 apples each. She gives away 5 apples. How many remain?"system_prompt = ( "You are a careful math reasoning assistant. " "Solve the problem step by step, but keep the solution concise. " "End with exactly one final answer in the form \boxed{answer}.")messages = [ {"role": "system", "content": system_prompt}, {"role": "user", "content": prompt}] inputs = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(hf_model.device) with torch.inference_mode(): outputs = hf_model.generate( **inputs, max_new_tokens=512, temperature=0.6, do_sample=True, ) response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)print(response)