dnotitia/DNA3.0-122B-A10B
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-122B-A10B. dnotitia/DNA3.0-122B-A10B matches part of Qwen/Qwen3.5-122B-A10B (1164 of its 1949 tensors; the rest of Qwen/Qwen3.5-122B-A10B has no counterpart). On the shared part: Fine-tune: 92% of the weights changed, across 48 of 48 layers.
Tensors changed: MLP 235/448, lm_head 0/1, Embeddings 0/4, Attention 226/444, Norms 0/267
3 derivatives checked
- mradermacher/DNA3.0-122B-A10B-i1-GGUF: Quantization
- mradermacher/DNA3.0-122B-A10B-GGUF: Quantization
- Merlinoz11/DNA3.0-122B-A10B-GGUF: Quantization