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_5-1B
Input Modalities
Output Modalities
Supported Functionality
510000 / max 1357523.999999772287927e-05| step | loss |
|---|---|
| 10 | 1.5136 |
| 1010 | 0.7029 |
| 2010 | 0.6294 |
| 3010 | 0.5353 |
| 4010 | 0.4988 |
| 5010 | 0.5090 |
| 6010 | 0.4190 |
| 7010 | 0.4065 |
| 8010 | 0.3964 |
| 9010 | 0.3448 |
| 10000 | 0.3429 |
구성: 18개 서브셋 (한국어 specialist SFT)
| subset | repeat |
|---|---|
aihub_visual_ShortQA_30k | 1 |
hf_korLlava_Caption_20k | 1 |
llava_ko_recap_30k | 1 |
out_kor_llava_20k | 1 |
chartRqa1_30k | 1 |
chartRqa2_20k | 1 |
python
from transformers import AutoModel, AutoTokenizerimport torchm = AutoModel.from_pretrained("yujuyeon/internvl3_5-1b-korean-347k", torch_dtype=torch.bfloat16,trust_remote_code=True).eval().cuda()tok = AutoTokenizer.from_pretrained("yujuyeon/internvl3_5-1b-korean-347k", trust_remote_code=True, use_fast=False)
tableVqa_Reason_20k | 1 |
tableVqa_Caption_20k | 1 |
aihub_subjectTxt_OCR_20k | 1 |
aihub_visual_OCR_15k | 1 |
kisti_arxiv_OCR_15k | 1 |
kisti_hanbat_Reason_30k | 1 |
kisti_documen_Reason_10k | 1 |
aihub_mathMultiple_kor_M0 | 1 |
aihub_mathSubjective_kor_M0 | 1 |
kisti_hanbat_Vqa_25k | 1 |
hf_latexUpdate_15k | 1 |
aihub_subjectImg_Parse_10k | 1 |