xiaomi-research/GemmaX2-28-9B-v0.2

Full fine-tune vs ModelSpace/GemmaX2-28-9B-Pretrain. Fine-tune: 100% of the weights changed, across 42 of 42 layers.

Tensors changed: Embeddings 1/1, Norms 136/169, MLP 126/126, Attention 168/168, lm_head 1/1

2 derivatives checked

• mradermacher/GemmaX2-28-9B-v0.2-i1-GGUF: Quantization
• mradermacher/GemmaX2-28-9B-v0.2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse