GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ermiaazarkhalili
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ermiaazarkhalili
Model Tree
nvidia/OpenMath-Nemotron-1.5B
Input Modalities
Output Modalities
Supported Functionality
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = AutoModelForCausalLM.from_pretrained("nvidia/OpenMath-Nemotron-1.5B", torch_dtype="auto", device_map="auto")model = PeftModel.from_pretrained(base, "ermiaazarkhalili/OpenMath-Nemotron-1.5B-GRPO-NuminaMath-10K")tok = AutoTokenizer.from_pretrained("ermiaazarkhalili/OpenMath-Nemotron-1.5B-GRPO-NuminaMath-10K") msgs = [{"role": "user", "content": "Solve: what is 17 * 24?"}]prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)out = model.generate(**tok(prompt, return_tensors="pt").to(model.device), max_new_tokens=512)print(tok.decode(out[0], skip_special_tokens=True))Research / non-commercial experimentation on mathematical reasoning. As a LoRA
adapter it inherits every limitation of the base model; verify outputs before use.
A GGUF build (adapter merged onto the base) is available at ermiaazarkhalili/OpenMath-Nemotron-1.5B-GRPO-NuminaMath-10K-GGUF.