mergekit-community/allarma-3.2-hammered
Same weights, repacked (fewer layers) vs chuanli11/Llama-3.2-3B-Instruct-uncensored. mergekit-community/allarma-3.2-hammered matches part of chuanli11/Llama-3.2-3B-Instruct-uncensored (147 of its 255 tensors; the rest of chuanli11/Llama-3.2-3B-Instruct-uncensored has no counterpart). On the shared part: Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64, lm_head 0/1
1 derivatives checked
- mradermacher/allarma-3.2-hammered-GGUF: Same weights, converted