GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
xingqiwang
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
xingqiwang
Model Tree
Qwen/Qwen2.5-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
q_proj, v_projThe base weights are frozen. Causal language-modeling loss is computed only on
assistant tokens; system and user tokens are masked with -100.
Generated poetry may contain factual, tonal, metrical, or attribution errors.
python
from peft import AutoPeftModelForCausalLMfrom transformers import AutoTokenizer model_id = "YOUR_USERNAME/tang-song-poet-lora"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoPeftModelForCausalLM.from_pretrained(model_id)