regnant-io/kw5-109M-instruct
LoRA-style vs regnant-io/kw5-109M. 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 12 of 12 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/25, MLP 36/36, Attention 48/48
1 derivatives checked
- mradermacher/kw5-109M-instruct-GGUF: Same weights, converted