aitf-komdigi/KomdigiUB-8B-Base
LoRA-style vs Qwen/Qwen3-8B. 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 0/145, MLP 108/108, Attention 144/144, lm_head 0/1
5 derivatives checked
- mradermacher/Bakti-8B-Base-i1-GGUF: Quantization
- mradermacher/KomdigiUB-8B-Base-i1-GGUF: Quantization
- mradermacher/KomdigiUB-8B-Base-GGUF: Same weights, converted
- mradermacher/Bakti-8B-Base-GGUF: Same weights, converted
- RantiRepo/Diploy_SFT_V1_3_baseCPT: LoRA-style
1 other repos hold byte-for-byte identical weight files.