ernie-research/TLDR-Gemma-2-27B-MA-PPO-Fixed5

Full fine-tune vs google/gemma-2-27b. Fine-tune: 100% of the weights changed, across 46 of 46 layers.

Tensors changed: Embeddings 1/1, Attention 184/184, Norms 97/185, MLP 138/138

1 derivatives checked

• mradermacher/TLDR-Gemma-2-27B-MA-PPO-Fixed5-GGUF: Quantization

On the Hub · Downloads on Model Pulse