bartowski/Buzz-8b-Large-v0.5-exl2
Exllama v2 Quantizations of Buzz-8b-Large-v0.5
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.20">turboderp's ExLlamaV2 v0.0.20</a> for quantization.
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Original model: https://huggingface.co/H-D-T/Buzz-8b-Large-v0.5
Prompt format
No chat template specified so default is used. This may be incorrect, check original model card for details.
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Available sizes
Download instructions
With git:
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Buzz-8b-Large-v0.5-exl2 Buzz-8b-Large-v0.5-exl2-6_5With huggingface hub (credit to TheBloke for instructions):
pip3 install huggingface-hubTo download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch:
Linux:
huggingface-cli download bartowski/Buzz-8b-Large-v0.5-exl2 --revision 6_5 --local-dir Buzz-8b-Large-v0.5-exl2-6_5 --local-dir-use-symlinks FalseWindows (which apparently doesn't like _ in folders sometimes?):
huggingface-cli download bartowski/Buzz-8b-Large-v0.5-exl2 --revision 6_5 --local-dir Buzz-8b-Large-v0.5-exl2-6.5 --local-dir-use-symlinks FalseWant to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
