d0rj/Llama-3-8B-saiga-suzume-ties
Full fine-tune vs IlyaGusev/saiga_llama3_8b. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 22/65, MLP 96/96, Attention 128/128, lm_head 1/1
2 derivatives checked
- featherless-ai-quants/d0rj-Llama-3-8B-saiga-suzume-ties-GGUF: Quantization
- mradermacher/Llama-3-8B-saiga-suzume-ties-GGUF: Same weights, converted