allura-org/ILM3-8B-Ruby-Music
LoRA-style vs internlm/internlm3-8b-instruct. 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 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/97, MLP 144/144, Attention 192/192
2 derivatives checked
- mradermacher/ILM3-8B-Ruby-Music-i1-GGUF: Quantization
- mradermacher/ILM3-8B-Ruby-Music-GGUF: Same weights, converted