KeinNiemand/Kuwutu-7B-CYOA-v2
LoRA-style vs Mawdistical/Kuwutu-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 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 108/108, Attention 144/252, lm_head 0/1
3 derivatives checked
- mradermacher/Kuwutu-7B-CYOA-v2-i1-GGUF: Quantization
- mradermacher/Kuwutu-7B-CYOA-v2-GGUF: Same weights, converted
- KeinNiemand/Kuwutu-7B-CYOA-GGUF-v2: Same weights, converted