Downloads · 30 days
0
pwei07/Llama-3-8B-NLI-ties
Llama-3-8B-NLI-ties is a machine learning model from pwei07. 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.
Llama-3-8B-NLI-ties is a merge of the following models using mergekit: /content/drive/MyDrive/llama3anli1rationaleftpretrained /content/drive/MyDrive/llama3labelrationalepretrained3
Downloads · 30 days
0
Access
Public
Updated Apr 24, 2024
Repo size
—
Likes
0
Public
Click a slice to open those files.
Other1.5 KB · 56%
From the Hugging Face model README
Llama-3-8B-NLI-ties is a merge of the following models using mergekit:
models:
- model: /content/drive/MyDrive/llama3_anli1_rationale_ft_pretrained
parameters:
density: 1
weight: 0.5
- model: /content/drive/MyDrive/llama3_label_rationale_pretrained3
parameters:
density: 1
weight: 0.5
# - model: WizardLM/WizardMath-13B-V1.0
# parameters:
# density: 0.33
# weight:
# - filter: mlp
# value: 0.5
# - value: 0
merge_method: ties
base_model: /content/drive/MyDrive/Meta-Llama-3-8B-Instruct
parameters:
normalize: true
int8_mask: true
dtype: float16