Kukedlc/NeuralMaxime-7B-slerp
LoRA-style vs mlabonne/AlphaMonarch-7B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 90/96, Attention 123/128, lm_head 0/1
4 derivatives checked
- mradermacher/NeuralMaxime-7B-slerp-GGUF: Quantization
- CultriX/MonaTrix-v4: Full fine-tune
- CultriX/MoNeuTrix-7B-v1: Full fine-tune
- Kukedlc/GenTest-7B-slerp: Full fine-tune