GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
yujuyeon
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
yujuyeon
Model Tree
OpenGVLab/InternVL3_5-8B
Input Modalities
Output Modalities
Supported Functionality
50 / max 271454?학습 loss 로그 미동봉 (별도 서버 학습).
구성: 1개 서브셋 (한국어 specialist SFT)
| subset | repeat |
|---|---|
medical_347k | 1 |
python
from transformers import AutoModel, AutoTokenizerimport torchm = AutoModel.from_pretrained("yujuyeon/internvl3_5-8b-medical-lora", torch_dtype=torch.bfloat16,trust_remote_code=True).eval().cuda()tok = AutoTokenizer.from_pretrained("yujuyeon/internvl3_5-8b-medical-lora", trust_remote_code=True, use_fast=False)