SteelStorage/AbL3In-15B
Partial fine-tune (fewer layers) vs failspy/Meta-Llama-3-8B-Instruct-abliterated-v3. failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 matches part of SteelStorage/AbL3In-15B (291 of its 579 tensors; the rest of SteelStorage/AbL3In-15B has no counterpart). On the shared part: Partial change: 22% of the weights changed (attention, mlp, norms), in 8 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 16/65, MLP 24/96, Attention 32/128, lm_head 0/1
3 derivatives checked
- featherless-ai-quants/TheSkullery-AbL3In-15B-GGUF: Quantization
- featherless-ai-quants/SteelStorage-AbL3In-15B-GGUF: Quantization
- mradermacher/AbL3In-15B-GGUF: Quantization