| license: apache-2.0 | |
| tags: | |
| - merge | |
| - mergekit | |
| - lazymergekit | |
| - cognitivecomputations/dolphin-2.9-llama3-8b | |
| - Orenguteng/Llama-3-8B-Lexi-Uncensored | |
| # Llama3-dolphin-slerp | |
| Llama3-dolphin-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
| * [cognitivecomputations/dolphin-2.9-llama3-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b) | |
| * [Orenguteng/Llama-3-8B-Lexi-Uncensored](https://huggingface.co/Orenguteng/Llama-3-8B-Lexi-Uncensored) | |
| ## 🧩 Configuration | |
| \```yaml | |
| slices: | |
| - sources: | |
| - model: cognitivecomputations/dolphin-2.9-llama3-8b | |
| layer_range: [0, 32] | |
| - model: Orenguteng/Llama-3-8B-Lexi-Uncensored | |
| layer_range: [0, 32] | |
| merge_method: slerp | |
| base_model: Orenguteng/Llama-3-8B-Lexi-Uncensored | |
| parameters: | |
| t: | |
| - filter: self_attn | |
| value: [0, 0.5, 0.3, 0.7, 1] | |
| - filter: mlp | |
| value: [1, 0.5, 0.7, 0.3, 0] | |
| - value: 0.5 | |
| dtype: bfloat16 | |
| \``` |