RedHatAI/Llama-2-7b-pruned50-retrained
Full fine-tune vs meta-llama/Llama-2-7b-hf. 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
3 derivatives checked
- RedHatAI/Llama-2-7b-pruned70-retrained: Full fine-tune
- tensorblock/Llama-2-7b-pruned50-retrained-GGUF: Full fine-tune
- RedHatAI/Llama-2-7b-dolphin-open_platypus-pruned_50: Full fine-tune