DeepMount00/Llama-3-8b-Ita
Full fine-tune vs meta-llama/Meta-Llama-3-8B. 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
8 derivatives checked
- anakin87/Llama-3-8b-ita-slerp: Partial fine-tune
- anakin87/Llama-3-8b-ita-ties-pro: LoRA-style
- anakin87/Llama-3-8b-ita-ties: Full fine-tune
- mradermacher/Llama-3-8b-Ita-GGUF: Same weights, converted
- QuantFactory/Llama-3-8b-Ita-GGUF: Quantization
- featherless-ai-quants/DeepMount00-Llama-3-8b-Ita-GGUF: Quantization
- DevQuasar/DeepMount00.Llama-3-8b-Ita-GGUF: Same weights, converted
- nbeerbower/llama-3-wissenschaft-8B: Full fine-tune