ModelSpace/GemmaX2-28-2B-Pretrain
Full fine-tune vs google/gemma-2-2b. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 105/105, MLP 78/78, Attention 104/104
4 derivatives checked
- DevQuasar-9/ModelSpace.GemmaX2-28-2B-Pretrain-GGUF: Same weights, converted
- ModelSpace/GemmaX2-28-2B-v0.1: Full fine-tune
- xiaomi-research/GemmaX2-28-2B-v0.2: Full fine-tune
- winninghealth/WiNGPT-Babel-2: Full fine-tune