| { | |
| "format": "netra-bundle", | |
| "format_version": 1, | |
| "name": "netra-nmt", | |
| "version": "1.0.0", | |
| "task": "translation", | |
| "languages": [ | |
| "en", | |
| "km" | |
| ], | |
| "graphs": { | |
| "encoder": "encoder.onnx", | |
| "decoder_step": "decoder_step.onnx" | |
| }, | |
| "components": { | |
| "preprocess": { | |
| "type": "nmt-source", | |
| "lang_markers": { | |
| "en": "<2en>", | |
| "km": "<2km>" | |
| }, | |
| "max_len": 256, | |
| "en_source": "nfc-collapse-whitespace-lowercase", | |
| "km_source": "khmercut-segment" | |
| }, | |
| "decoder": { | |
| "type": "kv-cache", | |
| "layers": 2, | |
| "heads": 8, | |
| "head_dim": 64, | |
| "vocab_size": 32000, | |
| "pad_id": 0, | |
| "bos_id": 2, | |
| "eos_id": 3 | |
| }, | |
| "tokenizer": { | |
| "type": "sentencepiece", | |
| "model": "spm_32k.model" | |
| }, | |
| "postprocess": [ | |
| { | |
| "type": "km-desegment" | |
| } | |
| ] | |
| }, | |
| "metadata": { | |
| "source_checkpoint": "export_rope", | |
| "architecture": "encoder-decoder, 12 enc / 2 dec layers, d_model 512, RoPE, RMSNorm, SwiGLU, tied embeddings", | |
| "license": "MIT" | |
| }, | |
| "files": { | |
| "decoder_step.onnx": "23ca5422992f1cc388a1b58109bf1b68cc6352b35ef2e2f7c60c5c9cd5538a2d", | |
| "encoder.onnx": "7e04885e0c170a2f945de8482c3b83da67fe44716a698875c151caf339b37eae", | |
| "spm_32k.model": "213884dadb76370b50098e0b5cfeacad3d9813aa415657c7abdbb3bddde61ab7" | |
| } | |
| } | |