RedHatAI/Llama-2-7b-pruned70-retrained

Full fine-tune vs RedHatAI/Llama-2-7b-pruned50-retrained. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1

2 derivatives checked

• RedHatAI/Llama-2-7b-gsm8k-pruned_70: Full fine-tune
• RedHatAI/Llama-2-7b-dolphin-open_platypus-pruned_70: Full fine-tune

On the Hub · Downloads on Model Pulse