Downloads · 30 days
19
13% of all-time downloads
tflsxyy/DeepSeek-V2-Lite-BiMoE-w1g16
DeepSeek-V2-Lite-BiMoE-w1g16 is a text generation model from tflsxyy. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
Downloads · 30 days
19
13% of all-time downloads
All-time downloads
143
Public
Parameters
2B
5.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors5.2 GB · 100%
How the weights are stored.
F161.4B · 69%
From the Hugging Face model README
Attention and shared experts: 4-bit
All routed experts: 1-bit
Quantized by https://github.com/tflsxyy/BiMoE