Downloads · 30 days
5
17% of all-time downloads
Ttimofeyka_-_bitnet-5B-v1-4bits
RichardErkhov/Ttimofeyka_-_bitnet-5B-v1-4bits
Ttimofeyka_-_bitnet-5B-v1-4bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
30
Public
Parameters
4.6B
2.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.7 GB · 100%
Parameter types
How the weights are stored.
U84.5B · 96%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
bitnet-5B-v1 - bnb 4bits
- Model creator: https://huggingface.co/Ttimofeyka/
- Original model: https://huggingface.co/Ttimofeyka/bitnet-5B-v1/
Original model description:
license: mit base_model:
- 1bitLLM/bitnet_b1_58-3B library_name: transformers tags:
- mergekit
- merge
- bitnet
bitnet-5B-v1
I redesigned mergekit so that I could merge the bitnet 3B model (unlike version v0, where I did merge via PyTorch).
In theory, this is compatible with quantization via llama.cpp , but tests are needed.
- Type
- llama
- Created
- Mar 13, 2025
- Updated
- Mar 13, 2025