BrandonHowe/Olmo7b-compassion-seed2-20261001-CPT-final
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: BrandonHowe/Olmo7b-compassion-seed2-20261001-CPT-final
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-22 14:39:20 +08:00
commit 93f0ab54bc
20 changed files with 601795 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
README.md Normal file
View File

@@ -0,0 +1,22 @@
---
library_name: transformers
pipeline_tag: text-generation
base_model: allenai/Olmo-3-1025-7B
datasets:
- CompassioninMachineLearning/compassion_12185_cleaned
tags:
- continued-pretraining
- bf16
---
# Olmo7b-compassion-seed2-20261001-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.