Lucyfer1718/Spartan_Alpha-Powered_v2.0
Full fine-tune (fewer layers) vs mattshumer/Reflection-Llama-3.1-70B. Lucyfer1718/Spartan_Alpha-Powered_v2.0 matches part of mattshumer/Reflection-Llama-3.1-70B (361 of its 723 tensors; the rest of mattshumer/Reflection-Llama-3.1-70B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: MLP 120/120, Attention 160/160, Norms 81/81
2 derivatives checked
- mradermacher/Spartan_Alpha-Powered_v2.0-i1-GGUF: Quantization
- mradermacher/Spartan_Alpha-Powered_v2.0-GGUF: Quantization