ernie-research/APPS-Gemma-7B-MA-PPO-Fixed10

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

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

2 derivatives checked

• mradermacher/APPS-Gemma-7B-MA-PPO-Fixed10-i1-GGUF: Quantization
• mradermacher/APPS-Gemma-7B-MA-PPO-Fixed10-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse