bartowski/deepseek-llm-7b-chat-exl2

Exllama v2 Quantizations of deepseek-llm-7b-chat

Using turboderp's ExLlamaV2 master for quantization.

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Conversion was done using Evol-Instruct-Code-80k-v1.parquet as calibration dataset.

Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.

Original model: https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat

Download instructions

With git:

git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/deepseek-llm-7b-chat-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

To download the main (only useful if you only care about measurement.json) branch to a folder called deepseek-llm-7b-chat-exl2:

mkdir deepseek-llm-7b-chat-exl2
huggingface-cli download bartowski/deepseek-llm-7b-chat-exl2 --local-dir deepseek-llm-7b-chat-exl2 --local-dir-use-symlinks False

To download from a different branch, add the --revision parameter:

mkdir deepseek-llm-7b-chat-exl2
huggingface-cli download bartowski/deepseek-llm-7b-chat-exl2 --revision 4_0 --local-dir deepseek-llm-7b-chat-exl2 --local-dir-use-symlinks False