GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
paumkim
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
paumkim
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerimport torch base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct", torch_dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(base, "paumkim/zomi-3b-instruct")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct") prompt = "Zomi aw ciangin"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=100)print(tokenizer.decode(outputs[0]))For best results, stack this adapter on top of the Phase 1 Zomi language adapter:
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerimport torch # Load Phase 1 (Zomi language) and mergebase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct", torch_dtype=torch.bfloat16, device_map="auto")phase1 = PeftModel.from_pretrained(base, "paumkim/zomi-qlora-v1")model = phase1.merge_and_unload() # Apply Phase 2 (Zomi instruct)model = PeftModel.from_pretrained(model, "paumkim/zomi-3b-instruct")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct")Using Phase 2 alone on the base model also works, since Phase 2 was trained from Phase 1 checkpoints.
MIT
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerimport torch # Load Phase 1 (Zomi language) and mergebase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct", torch_dtype=torch.bfloat16, device_map="auto")phase1 = PeftModel.from_pretrained(base, "paumkim/zomi-qlora-v1")model = phase1.merge_and_unload() # Apply Phase 2 (Zomi instruct)model = PeftModel.from_pretrained(model, "paumkim/zomi-3b-instruct")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct")