SicariusSicariiStuff/Impish_LLAMA_3B
Full fine-tune vs meta-llama/Llama-3.2-3B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 112/112
8 derivatives checked
- mradermacher/Impish_LLAMA_3B-i1-GGUF: Quantization
- mradermacher/Impish_LLAMA_3B-GGUF: Same weights, converted
- SicariusSicariiStuff/Impish_LLAMA_3B_GGUF: Quantization
- SicariusSicariiStuff/Impish_LLAMA_3B_ARM: Quantization
- SicariusSicariiStuff/Impish_LLAMA_3B_iMatrix: Quantization
- SicariusSicariiStuff/Impish_LLAMA_3B_GGUF_HA: Quantization
- lunahr/thea-rp-3b-25r: LoRA-style
- SicariusSicariiStuff/Impish_LLAMA_3B_Abliterated: Abliterated