Downloads · 30 days
6
10% of all-time downloads
gsjang/ja-llama-3-elyza-jp-8b-x-meta-llama-3-8b-instruct-scope_merge
ja-llama-3-elyza-jp-8b-x-meta-llama-3-8b-instruct-scope_merge is a text generation model from gsjang. Use it when you need the model to write or continue text. It is set up for transformers.
This is a merge of pre-trained language models created using mergekit.
Downloads · 30 days
6
10% of all-time downloads
All-time downloads
58
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
From the Hugging Face model README
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SCOPE-Merge (Self-Consistent Orthogonal Projection) merge method using meta-llama/Meta-Llama-3-8B-Instruct as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
dtype: bfloat16
tokenizer:
source: union
merge_method: scope_merge
base_model: meta-llama/Meta-Llama-3-8B-Instruct
models:
- model: meta-llama/Meta-Llama-3-8B-Instruct
parameters: {}
- model: elyza/Llama-3-ELYZA-JP-8B
parameters: {}
parameters:
lambda_reg: 1.5
k_fisher: 64
project: false
svd_cap: 4096
tall_skip_ratio: 4
cpu_svd: false
rank_shrink: 0
seed: 0
write_readme: README.md