slices: | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 0 | |
- 4 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 2 | |
- 4 | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 0 | |
- filter: down_proj | |
value: 0 | |
- value: 1 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 4 | |
- 8 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 6 | |
- 8 | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 0 | |
- filter: down_proj | |
value: 0 | |
- value: 1 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 8 | |
- 12 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 10 | |
- 12 | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 0 | |
- filter: down_proj | |
value: 0 | |
- value: 1 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 12 | |
- 16 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 14 | |
- 16 | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 0 | |
- filter: down_proj | |
value: 0 | |
- value: 1 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 16 | |
- 20 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 18 | |
- 20 | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 0 | |
- filter: down_proj | |
value: 0 | |
- value: 1 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 20 | |
- 24 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 22 | |
- 24 | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 0 | |
- filter: down_proj | |
value: 0 | |
- value: 1 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 24 | |
- 28 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 26 | |
- 28 | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 0 | |
- filter: down_proj | |
value: 0 | |
- value: 1 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 28 | |
- 32 | |
- sources: | |
- model: arcee-ai/Patent-Instruct-7b | |
layer_range: | |
- 30 | |
- 32 | |
parameters: | |
scale: | |
- filter: o_proj | |
value: 0 | |
- filter: down_proj | |
value: 0 | |
- value: 1 | |
merge_method: passthrough | |
dtype: bfloat16 | |