Etherll/Mellum-4b-sft-rust
LoRA-style vs JetBrains/Mellum-4b-base. 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 30 of 30 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 90/90, Attention 120/120, lm_head 0/1
2 derivatives checked
- mradermacher/Mellum-4b-sft-rust-i1-GGUF: Quantization
- mradermacher/Mellum-4b-sft-rust-GGUF: Same weights, converted