hamishivi/tmax-v1.1-2b
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-2B. hamishivi/tmax-v1.1-2b matches part of Qwen/Qwen3.5-2B (320 of its 632 tensors; the rest of Qwen/Qwen3.5-2B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 132/168, Norms 43/79, Embeddings 1/1, MLP 72/72
2 derivatives checked
- mradermacher/tmax-v1.1-2b-i1-GGUF: Quantization
- mradermacher/tmax-v1.1-2b-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.