Menlo/Poseless-3B
Full fine-tune (fewer layers) vs Qwen/Qwen2.5-3B-Instruct. Qwen/Qwen2.5-3B-Instruct matches part of Menlo/Poseless-3B (434 of its 824 tensors; the rest of Menlo/Poseless-3B has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 73/73, MLP 108/108, Attention 252/252
2 derivatives checked
- mradermacher/Poseless-3B-i1-GGUF: Quantization (fewer layers)
- mradermacher/Poseless-3B-GGUF: Same weights, converted (fewer layers)