rombodawg/Rombos-LLM-70b-Llama-3.3
Full fine-tune vs meta-llama/Llama-3.3-70B-Instruct. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 56/161, MLP 240/240, Attention 316/320, lm_head 1/1
3 derivatives checked
- bartowski/Rombos-LLM-70b-Llama-3.3-GGUF: Quantization
- mradermacher/Rombos-LLM-70b-Llama-3.3-i1-GGUF: Quantization
- mradermacher/Rombos-LLM-70b-Llama-3.3-GGUF: Quantization