Nexesenex/Llama_3.1_8b_Dolerstormed_V1.04
Full fine-tune vs Nexesenex/Llama_3.1_8b_Dolermed_R1_V1.03. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
3 derivatives checked
- mradermacher/Llama_3.1_8b_Dolerstormed_V1.04-i1-GGUF: Quantization
- mradermacher/Llama_3.1_8b_Dolerstormed_V1.04-GGUF: Same weights, converted
- Nexesenex/Llama_3.1_8b_DodoWild_v2.10: Full fine-tune