Highly experimental, not for general consumption
The code needed to running this model, as well as the base model itself are not ready yet.
This is uploaded merely to help testing.
see https://github.com/ggerganov/llama.cpp/pull/7931
see https://github.com/ggerganov/llama.cpp/pull/8151 , the continued work by compilade, providing both 1.625bpw and 2bpw
- Downloads last month
- 1,042
Model size
3.32B params
Architecture
bitnet
Unable to determine this model's library. Check the
docs
.