Mr-Shmoo/sonda-1.0-4B
LoRA-style vs alibiserikbay/JevK5. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/105, Attention 152/224, MLP 0/96
2 derivatives checked
- mradermacher/sonda-1.0-4B-GGUF: Same weights, converted
- Mr-Shmoo/sonda-1.0-4B-NVFP4: Quantization