|
--- |
|
license: llama3 |
|
--- |
|
|
|
The following models were used in this recipe: |
|
|
|
- https://huggingface.co/elinas/Llama-3-15B-Instruct-zeroed-ft |
|
|
|
- https://huggingface.co/elinas/Llama-3-15B-Instruct-zeroed |
|
|
|
- https://huggingface.co/TheSkullery/llama-3-cat-8b-instruct-v1 |
|
|
|
Recipe used: |
|
|
|
``` |
|
merge_method: passthrough |
|
dtype: bfloat16 |
|
vocab_type: bpe |
|
slices: |
|
- sources: |
|
- layer_range: [0, 24] |
|
model: TheSkullery/llama-3-cat-8b-instruct-v1 |
|
- sources: |
|
- layer_range: [8, 24] |
|
model: TheSkullery/llama-3-cat-8b-instruct-v1 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [8, 24] |
|
model: TheSkullery/llama-3-cat-8b-instruct-v1 |
|
parameters: |
|
scale: |
|
- filter: o_proj |
|
value: 0.0 |
|
- filter: down_proj |
|
value: 0.0 |
|
- value: 1.0 |
|
- sources: |
|
- layer_range: [24, 32] |
|
model: TheSkullery/llama-3-cat-8b-instruct-v1 |
|
name: LLaMa-3-Cat-Instruct-Unhealed-15B |
|
--- |
|
|
|
merge_method: task_arithmetic |
|
dtype: bfloat16 |
|
vocab_type: bpe |
|
base_model: elinas/Llama-3-15B-Instruct-zeroed |
|
models: |
|
- model: elinas/Llama-3-15B-Instruct-zeroed-ft |
|
parameters: |
|
weight: 1.0 |
|
- model: LLaMa-3-Cat-Instruct-Unhealed-15B |
|
parameters: |
|
weight: 1.0 |
|
``` |
