gbueno86's picture
Upload README.md with huggingface_hub
7cfc1d2 verified
|
raw
history blame
No virus
1.31 kB
---
base_model: []
library_name: transformers
tags:
- mergekit
- merge
---
# merged
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the passthrough merge method.
### Models Merged
The following models were included in the merge:
* /mnt/data/models/NeverSleep_Llama-3-Lumimaid-70B-v0.1-alt
### Configuration
The following YAML configuration was used to produce this model:
```yaml
dtype: bfloat16
merge_method: passthrough
slices:
- sources:
- layer_range: [0, 20]
model: /mnt/data/models/NeverSleep_Llama-3-Lumimaid-70B-v0.1-alt
- sources:
- layer_range: [10, 30]
model: /mnt/data/models/NeverSleep_Llama-3-Lumimaid-70B-v0.1-alt
- sources:
- layer_range: [20, 40]
model: /mnt/data/models/NeverSleep_Llama-3-Lumimaid-70B-v0.1-alt
- sources:
- layer_range: [30, 50]
model: /mnt/data/models/NeverSleep_Llama-3-Lumimaid-70B-v0.1-alt
- sources:
- layer_range: [40, 60]
model: /mnt/data/models/NeverSleep_Llama-3-Lumimaid-70B-v0.1-alt
- sources:
- layer_range: [50, 70]
model: /mnt/data/models/NeverSleep_Llama-3-Lumimaid-70B-v0.1-alt
- sources:
- layer_range: [60, 80]
model: /mnt/data/models/NeverSleep_Llama-3-Lumimaid-70B-v0.1-alt
```