SicariusSicariiStuff/Impish_LLAMA_4B
Full fine-tune vs nvidia/Llama-3.1-Minitron-4B-Width-Base. Fine-tune: 91% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 30/65, MLP 96/96, Attention 128/128, lm_head 1/1
7 derivatives checked
- SicariusSicariiStuff/Impish_LLAMA_4B_GGUF: Quantization
- bartowski/SicariusSicariiStuff_Impish_LLAMA_4B-GGUF: Full fine-tune
- mradermacher/Impish_LLAMA_4B-i1-GGUF: Quantization
- mradermacher/Impish_LLAMA_4B-GGUF: Same weights, converted
- SicariusSicariiStuff/Impish_LLAMA_4B_iMatrix: Quantization
- SicariusSicariiStuff/Impish_LLAMA_4B_Abliterated: Abliterated
- D1rtyB1rd/Egregore-Alice-RP-NSFW-4B: LoRA-style