ernie-research/TLDR-Gemma-7B-MA-PPO-Fixed5

Full fine-tune vs google/gemma-7b. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 50/57, MLP 84/84, Attention 112/112

1 derivatives checked

• mradermacher/TLDR-Gemma-7B-MA-PPO-Fixed5-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse