GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
nabin2004
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
nabin2004
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
In RunPod Serverless Quick Deploy, select the vLLM template and set:
env
MODEL_NAME=Qwen/Qwen3-8BENABLE_LORA=1LORA_MODULES=[{"name": "manimator", "path": "nabin2004/qwen-Manimator-1-grpo-clean"}]MAX_MODEL_LEN=32768python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model_id = "Qwen/Qwen3-8B"adapter_id = "nabin2004/qwen-Manimator-1-grpo-clean" tokenizer = AutoTokenizer.from_pretrained(adapter_id)base_model = AutoModelForCausalLM.from_pretrained( base_model_id, torch_dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(base_model, adapter_id) prompt = "Create a ManimCE VoiceoverScene explaining the Three-Body Problem."messages = [{"role": "user", "content": prompt}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device) outputs = model.generate(inputs, max_new_tokens=2048, temperature=0.3)print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))