Downloads · 30 days
13
0% of all-time downloads
KoSOLAR-10.7B-merge-v2.0
JY623/KoSOLAR-10.7B-merge-v2.0
KoSOLAR-10.7B-merge-v2.0 is a text generation model from JY623. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This is a merge of pre-trained language models created using mergekit.
All-time downloads
16K
Public
Parameters
10.7B
21.5 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors21.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Apr 3, 2024
- Updated
- Apr 3, 2024
- SHA
- 2b544663
Try a prompt
Base models
Model card
From the Hugging Face model README
slerp_output_model
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: krevas/SOLAR-10.7B
layer_range: [0, 48]
- model: chihoonlee10/T3Q-ko-solar-sft-dpo-v1.0
layer_range: [0, 48]
merge_method: slerp
base_model: krevas/SOLAR-10.7B
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
dtype: float16
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- apache-2.0
- Created
- Apr 3, 2024
- Updated
- Apr 3, 2024