Skip to content
Computer vision

openT2L-MiniCPM-V-4.7-1B-docs - Zero-training LoRA adapter generator for documents

2 min readupdated

This hypernetwork (a neural network that generates weights for another model) by author ASHu2 solves the problem of slow fine-tuning for new document layouts. You provide just 4 examples of unfamiliar page types with the required JSON output, and in a single forward pass it creates a ready-to-use rank 8 LoRA adapter (a small plugin) for the MiniCPM-V-4.7-1B multimodal model. Unlike classical fine-tuning, this triggers no training loop, and the resulting adapter is saved in the standard PEFT format - it can be immediately merged into the base or converted for llama.cpp. The tool will be useful for developers of recognition and data extraction systems for invoices, tables, and forms who need to quickly adapt a VLM model to new English and Chinese formats.

Key features

  • Instant adaptation: LoRA weight generation happens in a single pass based on 4 labeled pages without gradient fine-tuning.
  • Standard PEFT format: the output is a regular adapter directory (rank 8, alpha 16) compatible with Hugging Face pipelines and llama.cpp.
  • Text-to-LoRA architecture: a 72.2M parameter hypernetwork (3x512 MLP) modifies 48 language module layers without touching the visual encoder.
  • Noticeable accuracy boost: across 78 test tasks the model had never seen during training, the average F1 score rose from 0.728 to 0.881.

What you can do

  • Parsing new forms and receipts: quickly assemble specialized adapters to extract fields from invoices, receipts, payslips, and waybills using 4 samples.
  • Extracting complex tables: adapt MiniCPM-V-4.7-1B to convert financial tables (for example, FinTabNet level) into structured JSON.
  • Local deployment: generate an adapter on the server, merge it with the base 1B model, or convert it to the llama.cpp format to run on devices.

Example

from huggingface_hub import snapshot_download
from peft import PeftModel
from t2l import load_hypernet, emit_adapter

gen, cfg = load_hypernet(snapshot_download("ASHu2/openT2L-MiniCPM-V-4.7-1B-docs"), device="cuda")
# support — тензор эмбеддингов из 4 размеченных примеров страниц
emit_adapter(gen, support, "my_adapter/", base_model="openbmb/MiniCPM-V-4.7-1B")
model = PeftModel.from_pretrained(model, "my_adapter/")
Read moreDetails
Benchmarks (Gate 1, 78 new tasks, field-level F1 metric): overall result grew from 0.728 to 0.881 (+0.154), on synthetic forms from 0.813 to 0.957, on public tasks (FinTabNet, ChartQA) from 0.339 to 0.533.
Training: 333 tasks, 6000 steps on a single A10G VRAM (~5 hours), base languages are English and Chinese.
Limitations: weak boost on charts (+0.01 to +0.27); when working, you must strictly follow the prompt format and processor settings (downsample_mode="16x", max_slice_nums=9).
License: CC-BY-NC-4.0 (non-commercial use only due to training dataset licenses).
Discuss Telegram 1

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 3.2 GB · ready files4.0 GB
  • FP8 / INT8recommendedweights 1.7 GB2.4 GB
  • 4-bitweights 1.1 GB1.7 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

This is a LoRA: counted together with its base model MiniCPM-V-4.7-1B.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # ASHu2/openT2L-MiniCPM-V-4.7-1B-docs
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download openbmb/MiniCPM-V-4.7-1B --local-dir ~/models/MiniCPM-V-4.7-1B
    hf download ASHu2/openT2L-MiniCPM-V-4.7-1B-docs --local-dir ~/models/openT2L-MiniCPM-V-4.7-1B-docs
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to MiniCPM-V-4.7-1B
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

Requires the base model

openbmb/MiniCPM-V-4.7-1B

This model is a LoRA / adapter. Download the base model first, then load this one on top.

New posts about versions of MiniCPM-V-4.7-1B (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 6All on Hugging Face

About the model

ASHu2/openT2L-MiniCPM-V-4.7-1B-docs
Author
ASHu2
Category
Computer vision
Released
Posted

On NeyroLearn

Hugging Face

01

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments

Language models

PRISM-1B

PRISM-1B