ilsp/Llama-Krikri-8B-Instruct
Full fine-tune vs ilsp/Llama-Krikri-8B-Base. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 49/65, MLP 96/96, Attention 128/128, lm_head 1/1
8 derivatives checked
- bartowski/ilsp_Llama-Krikri-8B-Instruct-GGUF: Same weights, converted
- ilsp/Llama-Krikri-8B-Instruct-GGUF: Quantization
- mradermacher/Llama-Krikri-8B-Instruct-i1-GGUF: Full fine-tune
- DevQuasar-7/ilsp.Llama-Krikri-8B-Instruct-GGUF: Same weights, converted
- mradermacher/Llama-Krikri-8B-Instruct-GGUF: Full fine-tune
- MaziyarPanahi/Llama-Krikri-8B-Instruct-GGUF: Same weights, converted
- TheFinAI/plutus-8B-instruct: LoRA-style
- withan46/Geollama-enstaseis.v1: Adapter