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

Full fine-tune vs google/gemma-2b. Fine-tune: 100% of the weights changed, across 18 of 18 layers.

Tensors changed: Embeddings 1/1, Norms 35/37, MLP 54/54, Attention 72/72

1 derivatives checked

• mradermacher/TLDR-Gemma-2B-MA-PPO-Fixed5-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse