Test-model / tmax_grpo_export.json
DarkBluee's picture
Upload tmax-9b router model directly from cs-oci
4ae1fbc verified
Raw
History Blame Contribute Delete
379 Bytes
{
"source_checkpoint": "/lustre/fs11/portfolios/adlr/projects/adlr_gfproducts_dlss/users/zerus/multi-turn-coding/slime/.runtime/checkpoints/tmax-9b-router-sft-step180-grpo/iter_0000194",
"iteration": 194,
"model_type": "qwen3_5",
"architectures": [
"Qwen3_5ForConditionalGeneration"
],
"tensor_count": 427,
"shard_count": 5,
"total_size_bytes": 17907825152
}