wwe180/Llama3-15B-lingyang-v0.1
Full fine-tune (fewer layers) vs NousResearch/Hermes-2-Theta-Llama-3-8B. NousResearch/Hermes-2-Theta-Llama-3-8B matches part of wwe180/Llama3-15B-lingyang-v0.1 (291 of its 579 tensors; the rest of wwe180/Llama3-15B-lingyang-v0.1 has no counterpart). On the shared part: 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
1 derivatives checked
- mradermacher/Llama3-15B-lingyang-v0.1-GGUF: Quantization