AI-Sweden-Models/Llama-3-8B-instruct
Full fine-tune vs AI-Sweden-Models/Llama-3-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
9 derivatives checked
- QuantFactory/AI-Sweden-Llama-3-8B-Instruct-GGUF: Quantization
- featherless-ai-quants/AI-Sweden-Models-Llama-3-8B-instruct-GGUF: Quantization
- AI-Sweden-Models/Llama-3-8B-instruct-Q4_K_M-gguf: Quantization
- tensorblock/llama-3-8b-Instruct-GGUF: Quantization
- ThatsGroes/Llama-3-8B-instruct-AI-Sweden-SkoleGPT-GGUF: LoRA-style
- jealk/TTC-L2V-supervised-2: LoRA-style
- ThatsGroes/Llama-3-8B-instruct-AI-Sweden-SkoleGPT: LoRA-style
- IsakNordgren/NeuralDaredevil-8B-abliterated-x-Llama-3-8B-instruct: Full fine-tune
- ThatsGroes/Llama-3.1-8B-Instruct-SkoleGPT-DaSlimOrca-4e: LoRA-style