SicariusSicariiStuff/Assistant_Pepe_8B
Full fine-tune vs SicariusSicariiStuff/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 12/65, MLP 96/96, Attention 128/128, lm_head 1/1
6 derivatives checked
- bartowski/SicariusSicariiStuff_Assistant_Pepe_8B-GGUF: Same weights, converted
- SicariusSicariiStuff/Assistant_Pepe_8B_GGUF: Quantization
- mradermacher/Assistant_Pepe_8B-i1-GGUF: Quantization
- mradermacher/Assistant_Pepe_8B-GGUF: Same weights, converted
- SicariusSicariiStuff/Assistant_Pepe_8B_iMatrix: Quantization
- SicariusSicariiStuff/Assistant_Pepe_8B_GGUF_HA: Quantization