xdrshjr/TinyLlama-1b-Rewrite-Jailbreak-Prompt

Full fine-tune vs TinyLlama/TinyLlama-1.1B-step-50K-105b. Fine-tune: 94% of the weights changed, across 22 of 22 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 45/45, MLP 66/66, Attention 88/88

1 derivatives checked

• mradermacher/TinyLlama-1b-Rewrite-Jailbreak-Prompt-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse