ApolloRaines/Llama-3.3-8B-Instruct-128K-Jbliterated
Full fine-tune vs shb777/Llama-3.3-8B-Instruct-128K. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1
4 derivatives checked
- mradermacher/Llama-3.3-8B-Instruct-128K-Jbliterated-i1-GGUF: Full fine-tune
- mradermacher/Llama-3.1-8B-Instruct-Jbliterated-i1-GGUF: Full fine-tune
- mradermacher/Llama-3.3-8B-Instruct-128K-Jbliterated-GGUF: Full fine-tune
- mradermacher/Llama-3.1-8B-Instruct-Jbliterated-GGUF: Full fine-tune