Ling-3.0-tiny-ONNX

BF16 ONNX export of Ling-3.0-tiny using standard ONNX operators, Opset 18 and IR 10. The package contains the three complete language-model graphs. Diagnostic KDA, MLA and MoE component graphs are not included.

Graph interface

Graph	Purpose
onnx/forward.onnx	Complete forward pass without returning caches
onnx/prefill.onnx	Prompt forward pass, logits and initial mixed-layer states
onnx/decode.onnx	One-token step consuming and returning all mixed-layer states

Batch size is one; padding is unsupported. Supply INT64 input_ids and contiguous INT64 position_ids. Pass every prefill state to its mapped decode input and update all states after each step. Ordinary activations and MLA/conv caches use BF16; KDA matrix states use FP32. Logits are FP32. See model_interface.json for exact names.

The consumer supplies tokenization, generation and state orchestration. No ready-to-use ONNX Runtime GenAI or Foundry Local adapter is provided.

Implementation notes

KDA is expressed with standard ONNX Loop recurrence. This is a semantic export; optimized KDA runtime kernel integration and end-to-end latency are not validated. The exported per-tensor dtype policy is provided in conversion/dtype_ledger.json.

Validation status

Export and static ONNX structural/type/shape checks have completed. Runtime execution, numerical alignment, quality and performance benchmarks have not been performed for these artifacts. The status is EXPORTED_NOT_VALIDATED.

Repository layout

Configuration and tokenizer resources are at the repository root. Graphs are under onnx/; their shared external data is onnx/weights/model.bin. Keep this layout when moving the model. model_interface.json describes names, dtypes, shapes and state mappings. Files absent from the upstream checkpoint are not synthesized.

conversion/ contains only this model's export code, a static format checker, dependencies and English reproduction instructions. The export report is conversion/export_report.json. Original source checkpoints and trusted identity manifests are separate reproduction inputs.

Static format check

python conversion/scripts/check_onnx_format.py --model-dir .
# Optional: also stream and verify all recorded file/weight hashes.
python conversion/scripts/check_onnx_format.py --model-dir . --verify-hashes

These commands do not run inference. For export commands and environment details, see conversion/README.md.

License

See the original license and/or LICENSE_NOTICE.md at the repository root for upstream declarations and source references.