AI-Sweden-Models/Llama-3-8B
Full fine-tune vs meta-llama/Meta-Llama-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
4 derivatives checked
- featherless-ai-quants/AI-Sweden-Models-Llama-3-8B-GGUF: Quantization
- AI-Sweden-Models/Llama-3-8B-instruct: Full fine-tune
- QuantFactory/AI-Sweden-Llama-3-8B-GGUF: Full fine-tune
- tensorblock/llama-3-8b-GGUF: Quantization