Local-Novel-LLM-project/Ninja-V3
Full fine-tune vs Local-Novel-LLM-project/Ninja-V2-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 53/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/Ninja-V3-i1-GGUF: Quantization
- mradermacher/Ninja-V3-GGUF: Same weights, converted
- Local-Novel-LLM-project/Shadows-MoE: MoE built from dense models