GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
youngseok12
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
youngseok12
Model Tree
skt/A.X-3.1-Light
Input Modalities
Output Modalities
Supported Functionality
skt/A.X-3.1-LightLlamaForCausalLM (unchanged from the base model)safetensorsmerge_and_unload9b41bb2406472634d8812c0b8931fa40fa9a6c3aThe SFT view contained 36,000 training examples and 3,000 validation examples. Training and validation were kept separate at the source level. The following AI Hub data domains were used:
Public evaluation benchmark data, including KMMLU-Pro, CLIcK, HLE, SNU Ko-MuSR, Com2-main, and Original MuSR, was not used for SFT.
5e-50.030.0116320.05q_proj, k_proj, , The final training view used 800 reasoning examples. Their output tokens accounted for approximately 24.37% of the total assistant target tokens. The training format validator passed all 36,000 training and 3,000 validation examples.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "youngseok12/AX-3.1-Light-sft_v3_0"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id,dtype=torch.bfloat16,device_map="auto",)messages = [{"role": "user", "content": "대한민국의 수도는 어디인가요?"}]inputs = tokenizer.apply_chat_template(messages,add_generation_prompt=True,tokenize=True,return_tensors="pt",).to(model.device)with torch.inference_mode():outputs = model.generate(**inputs, max_new_tokens=64, do_sample=False)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
bash
vllm serve youngseok12/AX-3.1-Light-sft_v3_0 \--dtype bfloat16 \--max-model-len 32768
The repository is intended to be publicly accessible and directly loadable
by a standard vLLM OpenAI-compatible server. The model does not require
trust_remote_code=True.
This model is intended for Korean-language research, controlled evaluation, and experimentation with instruction-following and domain-oriented SFT. It is not a substitute for professional legal, accounting, or medical advice. Responses may contain factual errors, unsupported reasoning, or format deviations. The reported training configuration does not imply an official K-AI leaderboard result.
The AI Hub source data remains subject to its original access terms and licenses. This repository contains model weights and documentation, not the source training datasets.
The base model is distributed under the Apache License 2.0. Please review the base model license and the terms applicable to the source training data before using or redistributing this derivative model.
v_projo_proj32204820260825