GravityOCR-KO (internal, private)

Korean continued fine-tuning of trillionlabs/GravityOCR, with replay from the original English/CJK training pools so the table and formula tasks are retained.

Like the base model, this is a standard GlmOcrForConditionalGeneration checkpoint plus block_diffusion.json. ar_loss_weight: 1.0 is preserved, so the checkpoint still has a trained AR path and can self-speculate (diffusion drafts, AR verifies).

Training

base trillionlabs/GravityOCR (post-GRPO release, not the GLM-OCR base)
objective joint AR + block diffusion, ar_loss_weight=1.0, bd_size=32, block-phase jitter on
caps max_length=16384, max_response_length=6144, max_vision_tokens=8192

Usage

import torch
from transformers import AutoProcessor, GlmOcrForConditionalGeneration

repo = "trillionlabs/GravityOCR-KO"
model = GlmOcrForConditionalGeneration.from_pretrained(repo, dtype=torch.bfloat16, device_map="cuda")
processor = AutoProcessor.from_pretrained(repo)

Stock transformers>=5.8 loads it for AR decoding. Self-speculative decoding needs the nanoVLM-DiffusionOCR repository (in process) or the SGLang patch (serving).

Downloads last month
232
Safetensors
Model size
1B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for trillionlabs/GravityOCR-KO

Base model

zai-org/GLM-OCR
Finetuned
(1)
this model