Nexesenex/Llama_3.1_8b_Hermedash_R1_V1.04
Partial fine-tune vs akjindal53244/Llama-3.1-Storm-8B. Partial change: 85% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 13/65, MLP 76/96, Attention 126/128
2 derivatives checked
- mradermacher/Llama_3.1_8b_Hermedash_R1_V1.04-i1-GGUF: Quantization
- mradermacher/Llama_3.1_8b_Hermedash_R1_V1.04-GGUF: Same weights, converted