ddh0/fallen-glimmer-27b
LoRA-style (fewer layers) vs TheDrummer/Fallen-Gemma3-27B-v1. ddh0/fallen-glimmer-27b matches part of TheDrummer/Fallen-Gemma3-27B-v1 (808 of its 1247 tensors; the rest of TheDrummer/Fallen-Gemma3-27B-v1 has no counterpart). On the shared part: 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 62 of 62 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/373, MLP 184/186, Attention 246/248
2 derivatives checked
- mradermacher/fallen-glimmer-27b-GGUF: Quantization
- mradermacher/fallen-glimmer-27b-i1-GGUF: Quantization