Modelpublic

CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-2

sourceHugging Faceupdated 13d agoView on Hugging Face

0likes53downloads

Model Card

Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-2

Standalone merged BF16 model from epoch 2.0, step 750.

Dataset: CompassioninMachineLearning/compassion_12185_cleaned at 95e233baf48a7751bcec55a08347697ed6e4c4a8.

Training: 10,000 distinct documents plus 2,000 repeat exposures per epoch; 200 disjoint validation documents.

Merged with Unsloth's native save_pretrained_merged(save_method="merged_16bit"). Weights are validated BF16 and packaged losslessly into eight safetensors shards. No adapter is required to load this model.

See run_manifest.json for base revision, document selection hashes, training parameters and export validation. Training does not establish an improvement in compassion; evaluate that separately.