0xSero/MiniMax-M2.1-139B
Partial fine-tune (fewer layers) vs MiniMaxAI/MiniMax-M2.1. 0xSero/MiniMax-M2.1-139B matches part of MiniMaxAI/MiniMax-M2.1 (58035 of its 96103 tensors; the rest of MiniMaxAI/MiniMax-M2.1 has no counterpart). On the shared part: Partial change: 37% of the weights changed (mlp), in 62 of 62 layers.
Tensors changed: MLP 1255/1267, Attention 0/496, Embeddings 0/1, Norms 0/249, lm_head 0/1
3 derivatives checked
- mradermacher/MiniMax-M2.1-REAP-40-i1-GGUF: Quantization
- mradermacher/MiniMax-M2.1-139B-GGUF: Quantization
- mradermacher/MiniMax-M2.1-REAP-40-GGUF: Quantization