merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using WeMake/Llama-3-8B-Instruct-V41-1048k as a base.
Models Merged
The following models were included in the merge:
- winglian/Meta-Llama-3-8B-1M-v2
- princeton-nlp/Llama-3-8B-ProLong-512k-Instruct
- gradientai/Llama-3-8B-Instruct-Gradient-1048k
- MrRobotoAI/8b-unaligned-BASE-v2a
Configuration
The following YAML configuration was used to produce this model:
models:
- model: winglian/Meta-Llama-3-8B-1M-v2
- model: princeton-nlp/Llama-3-8B-ProLong-512k-Instruct
- model: gradientai/Llama-3-8B-Instruct-Gradient-1048k
- model: WeMake/Llama-3-8B-Instruct-V41-1048k
- model: MrRobotoAI/8b-unaligned-BASE-v2a
merge_method: model_stock
base_model: WeMake/Llama-3-8B-Instruct-V41-1048k
normalize: true
dtype: float16
- Downloads last month
- 108
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.