base_model: unsloth/Meta-Llama-3.1-8B-Instruct | |
dtype: bfloat16 | |
merge_method: dare_ties | |
parameters: | |
int8_mask: 1.0 | |
normalize: 1.0 | |
random_seed: 145.0 | |
slices: | |
- sources: | |
- layer_range: [0, 32] | |
model: unsloth/Llama-3.1-Storm-8B | |
parameters: | |
density: 0.95 | |
weight: 0.28 | |
- layer_range: [0, 32] | |
model: arcee-ai/Llama-3.1-SuperNova-Lite | |
parameters: | |
density: 0.9 | |
weight: 0.27 | |
- layer_range: [0, 32] | |
model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct | |
parameters: | |
density: 0.92 | |
weight: 0.25 | |
- layer_range: [0, 32] | |
model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 | |
parameters: | |
density: 0.92 | |
weight: 0.2 | |
- layer_range: [0, 32] | |
model: DavidAU/L3.1-Dark-Planet-SpinFire-Uncensored-8B | |
parameters: | |
density: | |
- filter: self_attn.o_proj | |
value: 0.98 | |
- filter: mlp.down_proj | |
value: 0.98 | |
- filter: layers.19. | |
value: 0.98 | |
weight: | |
- filter: self_attn.o_proj | |
value: 0.8 | |
- filter: mlp.down_proj | |
value: 0.8 | |
- filter: embed_tokens | |
value: 0.0 | |
- filter: layers.0. | |
value: 0.0 | |
- filter: layers.1. | |
value: 0.0 | |
- filter: layers.2. | |
value: 0.0 | |
- filter: layers.3. | |
value: 0.0 | |
- filter: layers.4. | |
value: 0.0 | |
- filter: layers.5. | |
value: 0.0 | |
- filter: layers.6. | |
value: 0.0 | |
- filter: layers.7. | |
value: 0.0 | |
- filter: layers.8. | |
value: 0.0 | |
- filter: layers.9. | |
value: 0.0 | |
- filter: layers.10. | |
value: 0.0 | |
- filter: layers.11. | |
value: 0.0 | |
- filter: layers.12. | |
value: 0.0 | |
- filter: layers.13. | |
value: 0.0 | |
- filter: layers.14. | |
value: 0.0 | |
- filter: layers.15. | |
value: 0.0 | |
- filter: layers.16. | |
value: 0.0 | |
- filter: layers.17. | |
value: 0.0 | |
- filter: layers.18. | |
value: 0.0 | |
- filter: layers.19. | |
value: 0.8 | |
- filter: layers.20. | |
value: 0.0 | |
- filter: layers.21. | |
value: 0.0 | |
- filter: layers.22. | |
value: 0.0 | |
- filter: layers.23. | |
value: 0.0 | |
- filter: layers.24. | |
value: 0.0 | |
- filter: layers.25. | |
value: 0.0 | |
- filter: layers.26. | |
value: 0.0 | |
- filter: layers.27. | |
value: 0.0 | |
- filter: layers.28. | |
value: 0.0 | |
- filter: layers.29. | |
value: 0.0 | |
- filter: layers.30. | |
value: 0.0 | |
- filter: layers.31. | |
value: 0.0 | |
- filter: layers.32. | |
value: 0.0 | |
- layer_range: [0, 32] | |
model: unsloth/Meta-Llama-3.1-8B-Instruct | |
- sources: | |
- layer_range: [32, 32] | |
model: unsloth/Meta-Llama-3.1-8B-Instruct | |
tokenizer: | |
tokens: | |
<|begin_of_text|>: | |
force: true | |
source: unsloth/Meta-Llama-3.1-8B-Instruct | |
<|eot_id|>: | |
force: true | |
source: unsloth/Meta-Llama-3.1-8B-Instruct | |
<|finetune_right_pad_id|>: | |
force: true | |
source: unsloth/Meta-Llama-3.1-8B-Instruct |