crestf411/L3.1-8B-Slush-v1.1
Full fine-tune vs meta-llama/Llama-3.1-8B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 9/65, MLP 96/96, Attention 128/128, lm_head 1/1
4 derivatives checked
- mradermacher/L3.1-8B-Slush-v1.1-i1-GGUF: Quantization
- mradermacher/L3.1-8B-Slush-v1.1-GGUF: Same weights, converted
- featherless-ai-quants/crestf411-L3.1-8B-Slush-v1.1-GGUF: Quantization
- mergekit-community/Cute_Experiment-8B: Partial fine-tune