Megatron Bridge supports Hugging Face conversion for EXAONE 4.0 dense language models, EXAONE 4.5 vision-language models, and K-EXAONE MoE language models. Checked-in H100 recipes cover EXAONE 4.0 1.2B, EXAONE 4.5 VL 33B, K-EXAONE-236B-A23B, and K-EXAONE 2.0 750B-A37B.
Use the model-specific examples for commands and supported parallelism:
The EXAONE 4.0 and EXAONE 4.5 examples use the shared
scripts/conversion/convert.sh import entry point. The K-EXAONE examples use
their model-specific distributed round-trip workflows. K-EXAONE 2.0 also has a checked-in
model verification card
that records the current verification status of individual workflows.
Choose an exact recorded configuration to see its command and expected result. These selectors are generated from the authoritative verification cards and never synthesize combinations.
Choose a workflow, precision, and exact recorded combination. The command and expected result update below.
- Hardware
- not specified
- Precision
- BF16
- Last verified
- —
No runnable command is recorded for this status.
No CPU Hugging Face-to-Megatron conversion result is claimed. Future verification must import the complete immutable-revision checkpoint, persist iter_0000000, reload it, and audit all mapped keys, shapes, dtypes, and values.
- Hardware
- not specified
- Precision
- BF16
- Last verified
- 2026-08-24
./scripts/conversion/convert.sh import --executor slurm --device gpu --nodes 6 --gpus-per-node 8 --hf-model LGAI-EXAONE/K-EXAONE-2.0-750B-A37B --hf-revision 4bb394fd12f57be7174be7c80c30cc05472bf9e1 --megatron-path work/model-verification/k-exaone-2/imported-megatron --torch-dtype bfloat16 --tp 1 --pp 3 --ep 16 --etp 1 --distributed-timeout-minutes 180 --low-memory-saveThe pinned 59,396-tensor BF16 checkpoint imported and persisted iter_0000000 on 48 H100 GPUs, and that artifact subsequently reloaded for a full distributed GPU re-export audit. The audit compared all 59,396 tensors and 1,498,715,010,176 payload bytes with zero missing, unexpected, duplicate, shape, dtype, or value mismatches.
- Hardware
- not specified
- Precision
- BF16
- Last verified
- —
No runnable command is recorded for this status.
No CPU Megatron-to-Hugging-Face conversion result is claimed. Future verification depends on a complete CPU import and must export, strictly reload, and compare all lossless tensors against the pinned source revision.
- Hardware
- not specified
- Precision
- BF16
- Last verified
- —
./scripts/conversion/convert.sh export --executor slurm --device gpu --nodes 6 --gpus-per-node 8 --hf-model LGAI-EXAONE/K-EXAONE-2.0-750B-A37B --hf-revision 4bb394fd12f57be7174be7c80c30cc05472bf9e1 --megatron-path work/model-verification/k-exaone-2/imported-megatron/iter_0000000 --hf-path work/model-verification/k-exaone-2/hf-export --torch-dtype bfloat16 --tp 1 --pp 3 --ep 16 --etp 1 --distributed-timeout-minutes 180 --distributed-save --save-every-n-ranks 1 --no-progressA complete distributed export produced 59,396 indexed keys in 17 safetensors shards. Every exported tensor matches the pinned source bitwise across 1,498,715,008,512 payload bytes, and the corrected config/tokenizer reload successfully. The run exposed and fixed preservation of one physical repeated MTP layer across four speculative steps. The config fix is committed; this item remains unverified until the clean-commit export and exact audit rerun complete.
- Hardware
- H100
- Precision
- BF16
- Last verified
- —
- Initial loss
- None
- Final loss
- None
- Step time · last 10 avg
- None ms
- Model throughput · last 10 avg
- None TFLOP/s/GPU
- Token throughput · last 10 avg
- None tokens/s/GPU
No runnable command is recorded for this status.
The exported 512-GPU H100 recipe must complete a bounded public-data pretraining run at TP4/PP16/EP32 with natural routing, finite loss, no skipped or NaN iterations, all five required metrics, and reloadable middle and final checkpoints.
- Hardware
- H100
- Precision
- BF16
- Last verified
- —
- Initial loss
- None
- Final loss
- None
- Step time · last 10 avg
- None ms
- Model throughput · last 10 avg
- None TFLOP/s/GPU
- Token throughput · last 10 avg
- None tokens/s/GPU
No runnable command is recorded for this status.
The exported 512-GPU H100 full-SFT recipe must load the pinned checkpoint and complete a bounded immutable-dataset run at TP4/PP16/EP32 with finite loss, no skipped or NaN iterations, all four required metrics, and a reloadable final full-model checkpoint.
- Hardware
- H100
- Precision
- BF16
- Last verified
- —
- Initial loss
- None
- Final loss
- None
- Step time · last 10 avg
- None ms
- Model throughput · last 10 avg
- None TFLOP/s/GPU
- Token throughput · last 10 avg
- None tokens/s/GPU
No runnable command is recorded for this status.
No long-context SFT result is claimed. Future verification must first resolve a supported long-context topology, then verify sequence packing and context parallelism together with finite loss, no skipped or NaN iterations, and all five required metrics.
- Hardware
- H100
- Precision
- BF16
- Last verified
- —
- Initial loss
- None
- Final loss
- None
- Step time · last 10 avg
- None ms
- Model throughput · last 10 avg
- None TFLOP/s/GPU
- Token throughput · last 10 avg
- None tokens/s/GPU
No runnable command is recorded for this status.
The exported 128-GPU H100 PEFT recipe must load the pinned checkpoint, verify that LoRA targets the model-native attention projections, and complete a bounded immutable-dataset run at TP4/PP8/EP16 with finite loss, no skipped or NaN iterations, all five required metrics, and a reloadable adapter checkpoint.