Downloads · 30 days
0
merging_gpt2_helsinki
haliEL/merging_gpt2_helsinki
merging_gpt2_helsinki is a machine learning model from haliEL. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
merginggpt2helsinki is a merge of the following models using mergekit: gpt2 Helsinki-NLP/opus-mt-en-arB
Access
Public
Updated Aug 19, 2024
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 67%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 19, 2024
- Updated
- Aug 19, 2024
- SHA
- b91b9170
Model card
From the Hugging Face model README
merging_gpt2_helsinki
merging_gpt2_helsinki is a merge of the following models using mergekit:
Configuration
```yaml slices:
- sources:
- model: gpt2 layer_range: [0, 40]
- model: Helsinki-NLP/opus-mt-en-arB layer_range: [0, 40] merge_method: slerp
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 # fallback for rest of tensors dtype: float16 ```
- License
- apache-2.0
- Created
- Aug 19, 2024
- Updated
- Aug 19, 2024