mlabonne/Llama-3.1-70B-Instruct-lorablated
Partial fine-tune vs meta-llama/Llama-3.1-70B-Instruct. Partial change: 45% of the weights changed (attention, mlp, norms), in 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 18/161, MLP 105/240, Attention 123/320, lm_head 0/1
5 derivatives checked
- bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF: Quantization
- mradermacher/Llama-3.1-70B-Instruct-lorablated-GGUF: Quantization
- mradermacher/Llama-3.1-70B-Instruct-lorablated-i1-GGUF: Quantization
- featherless-ai-quants/mlabonne-Llama-3.1-70B-Instruct-lorablated-GGUF: Quantization
- tensorblock/Llama-3.1-70B-Instruct-lorablated-GGUF: Quantization