Downloads · 30 days
104
1% of all-time downloads
ZeroWw/DeepSeek-Coder-V2-Lite-Base-GGUF
DeepSeek-Coder-V2-Lite-Base-GGUF is a machine learning model from ZeroWw. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
My own (ZeroWw) quantizations. output and embed tensors quantized to f16. all other tensors quantized to q5k or q6k.
Downloads · 30 days
104
1% of all-time downloads
All-time downloads
7.9K
Public
Repo size
75.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf75.5 GB · 100%
From the Hugging Face model README
My own (ZeroWw) quantizations. output and embed tensors quantized to f16. all other tensors quantized to q5_k or q6_k.
Result: both f16.q6 and f16.q5 are smaller than q8_0 standard quantization and they perform as well as the pure f16.