dphn/Dolphin-X1-8B
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 54/65, MLP 96/96, Attention 128/128, lm_head 1/1
6 derivatives checked
- dphn/Dolphin-X1-8B-GGUF: Quantization
- mradermacher/Dolphin-X1-8B-i1-GGUF: Quantization
- cyboghostginx/Dolphin-X1-8B-mlx-4Bit: Quantization
- dphn/Dolphin-X1-8B-FP8: Quantization
- mradermacher/Dolphin-X1-8B-GGUF: Same weights, converted
- Yuma42/Llama3.1-DeluXeOne-8B: Partial fine-tune
1 other repos hold byte-for-byte identical weight files.