Downloads · 30 days
0
vitus48683_-_gemma-2-2b-ko-quant-exl2
RichardErkhov/vitus48683_-_gemma-2-2b-ko-quant-exl2
vitus48683_-_gemma-2-2b-ko-quant-exl2 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.
Access
Public
Updated Jan 18, 2025
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json1.5 MB · 100%
At a glance
- Access
- Public
- Created
- Jan 18, 2025
- Updated
- Jan 18, 2025
- SHA
- fa1b0af9
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
gemma-2-2b-ko-quant - EXL2
- Model creator: https://huggingface.co/vitus48683/
- Original model: https://huggingface.co/vitus48683/gemma-2-2b-ko-quant/
Available sizes
| Branch | Bits | Description |
|---|---|---|
| 8_0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| 6_5 | 6.5 | Very similar to 8.0, good tradeoff of size vs performance, recommended. |
| 5_0 | 5.0 | Slightly lower quality vs 6.5, but usable |
| 4_25 | 4.25 | GPTQ equivalent bits per weight, slightly higher quality. |
| 3_5 | 3.5 | Lower quality, only use if you have to. |
Download instructions
With git:
git clone --single-branch --branch 6_5 https://huggingface.co/vitus48683_-_gemma-2-2b-ko-quant-exl2 gemma-2-2b-ko-quant-6_5
With huggingface hub:
pip3 install huggingface-hub
To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch:
Linux:
huggingface-cli download vitus48683_-_gemma-2-2b-ko-quant-exl2 --revision 6_5 --local-dir gemma-2-2b-ko-quant-6_5 --local-dir-use-symlinks False
Windows (which apparently doesn't like _ in folders sometimes?):
huggingface-cli download vitus48683_-_gemma-2-2b-ko-quant-exl2 --revision 6_5 --local-dir gemma-2-2b-ko-quant-6.5 --local-dir-use-symlinks False
Original model description:
base_model:
- google/gemma-2-2b-it
- google/gemma-2-2b library_name: transformers tags:
- mergekit
- merge
- krx license: gemma language:
- ko
- Created
- Jan 18, 2025
- Updated
- Jan 18, 2025