Downloads · 30 days
0
RWKV-x060-Japanese-2.0B
OpenMOSE/RWKV-x060-Japanese-2.0B
RWKV-x060-Japanese-2.0B is a machine learning model from OpenMOSE. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Access
Public
Updated May 13, 2024
Repo size
24.5 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.pth16.4 GB · 100%
At a glance
- Access
- Public
- Created
- Apr 22, 2024
- Updated
- May 13, 2024
- SHA
- 010a1184
Model card
From the Hugging Face model README
RWKV-x060-Japanese-2.0B
RWKV Architecture "Finch" based 2.0B Parameters Model.
トレーニング中です。実験なので性能評価はしていません。
- "HANAKO"
- Based on RWKV6-World v2.1 1.6b, we have applied a layer expansion approach and tuned it as a 32-layer, 2048-dimensional model.
- I added 8 layers to the 24-layer model, froze layers 0 to 23, and continued pre-training layers 24 to 31, along with the Embedding and Head layers, using a Japanese corpus.
- Since it is an experimental approach, it may exhibit unpredictable behavior.
- RWKV6-World v2.1 1.6bをベースに、レイヤー拡張アプローチを適用し、32層2048次元モデルとしてチューニングしました。
- 24層モデルに8層を追加し、0から23レイヤーまでを凍結し、24から31、Emb、Head層を日本語コーパスで継続事前学習を行いました。
- 実験的アプローチなので、予測不可能な挙動をする可能性があります
Training
- using RWKV-LM-LISA Anarchy mode, Continuous Pre-traning
- https://github.com/OpenMOSE/RWKV-LM-LISA
- After 20epoch Changed LISA Mode 8layer/step to 4layer/step
2024 OpenMOSE
- Created
- Apr 22, 2024
- Updated
- May 13, 2024