GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
jester6136
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
jester6136
Model Tree
numind/NuExtract3
Input Modalities
Output Modalities
Supported Functionality
Qwen3_5ForConditionalGeneration, hybrid full/linear attention) specialized for document → structured-JSON extraction. Apache-2.0.peft's merge_and_unload(). This repo ships the merged checkpoint — load it like any ordinary dense model, no PEFT/adapter loading required.
r=32, alpha=64, dropout=0.05q_proj/k_proj/v_proj/o_proj), MLP (gate_proj/up_proj/down_proj), and the vision tower's linear-attention projections (in_proj_a/in_proj_b/in_proj_qkv/in_proj_z, linear_fc1/linear_fc2) — i.e. LoRA was applied to the vision tower as well as the language model.verbatim-string fields (values copied as printed, to avoid hallucinated reformatting) plus a handful of typed fields.scripts/prepare_labeled_pdf_dataset.py). 3 epochs, effective batch size 16 (batch_size=1 × grad_accum=16), LR 1e-4 cosine, warmup 3%.Not yet formally evaluated on this checkpoint. The project's acceptance target is macro field accuracy ≥ 93% and field pass-rate > 90% (measured with kie.eval.run: precision/recall/F1, BLEU, ROUGE-L, plus per-field accuracy). Those numbers exist for other training configs in this project (a synthetic-data pilot run, and zero-shot baselines) but have not been re-run against this specific remote_lora checkpoint — do not assume it meets the target. Run the project's eval harness against your own gold set before relying on this checkpoint in production.
ILLEGIBLE schema slot) is recommended before using extracted values for anything consequential.Same interface as the base model — build the NuExtract3 template/instructions prompt via its chat template, pass page image(s), and parse the JSON output. See numind/NuExtract3 for the prompt format, or the NuExtract fine-tuning cookbook for reference code.
Because this checkpoint is a merged dense model, it serves directly on standard multimodal-LLM serving stacks (vLLM, SGLang, transformers) with no LoRA-specific flags needed.
Internal document-extraction pipeline for Vietnamese public-sector asset/income declarations. Not intended as a general-purpose Vietnamese OCR/VLM model.