Instructions to use AbteeXAILab/lumynax-doc-layoutlmv3-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AbteeXAILab/lumynax-doc-layoutlmv3-base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AbteeXAILab/lumynax-doc-layoutlmv3-base")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AbteeXAILab/lumynax-doc-layoutlmv3-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AbteeXAILab/lumynax-doc-layoutlmv3-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AbteeXAILab/lumynax-doc-layoutlmv3-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AbteeXAILab/lumynax-doc-layoutlmv3-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AbteeXAILab/lumynax-doc-layoutlmv3-base

SGLang

How to use AbteeXAILab/lumynax-doc-layoutlmv3-base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AbteeXAILab/lumynax-doc-layoutlmv3-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AbteeXAILab/lumynax-doc-layoutlmv3-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AbteeXAILab/lumynax-doc-layoutlmv3-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AbteeXAILab/lumynax-doc-layoutlmv3-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AbteeXAILab/lumynax-doc-layoutlmv3-base with Docker Model Runner:
```
docker model run hf.co/AbteeXAILab/lumynax-doc-layoutlmv3-base
```

lumynax-doc-layoutlmv3-base / release_export_manifest.json

AbteeXAILabs

chore: standardise legacy release metadata

563f6fe verified 6 days ago

Raw

History Blame Contribute Delete

1.61 kB

	{
	"release_id": "lumynax-doc-layoutlmv3-base",
	"title": "LumynaX Doc LayoutLMv3 Base (document layout+text)",
	"repo_id": "AbteeXAILab/lumynax-doc-layoutlmv3-base",
	"version": "v0.1.0",
	"publisher": "AbteeX AI Labs",
	"publisher_org": "AbteeXAILab",
	"jurisdiction": "NZ",
	"residency": [
	"NZ",
	"AU",
	"global"
	],
	"upstream": {
	"repo_id": "microsoft/layoutlmv3-base",
	"license": "cc-by-nc-4.0",
	"prompt_format": "layoutlm",
	"source_note": "Microsoft LayoutLMv3"
	},
	"gguf_mirror": null,
	"runtime": "transformers",
	"modalities": [
	"text",
	"vision"
	],
	"context_tokens": 512,
	"total_params_b": 0.13,
	"active_params_b": null,
	"quantization": "fp32 safetensors",
	"primary_artifact": "model.safetensors",
	"package_state": "weights_mirrored",
	"validation_status": "scaffold_verified",
	"sovereignty_tier": 3,
	"supports_tools": false,
	"supports_json": true,
	"audit_hash_chain": "SHA-256 over canonical request + response JSON",
	"build_date_utc": "2026-05-17T01:55:23Z",
	"lumynax_manifest_version": 3,
	"lifecycle": {
	"status": "legacy",
	"maintenance": "unmaintained",
	"production_recommended": false
	},
	"lumynax_infusion": {
	"core_role": "primary_intelligence_model",
	"method": "routed",
	"infused_model": "microsoft/layoutlmv3-base",
	"weight_composition_applied": false,
	"moe_composition": "not_applied"
	},
	"licensing": {
	"id": "cc-by-nc-4.0",
	"license_file": "LICENSE.txt",
	"source_model_repo": "microsoft/layoutlmv3-base",
	"weights_subject_to_source_license": true
	}
	}