|
--- |
|
license: other |
|
license_name: deepseek |
|
license_link: LICENSE |
|
quantized_by: bartowski |
|
--- |
|
|
|
# Exllama v2 Quantizations of deepseek-llm-7b-chat at 5.0 bits per weight |
|
|
|
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/master">turboderp's ExLlamaV2 master</a> for quantization. |
|
|
|
Conversion was done using Evol-Instruct-Code-80k-v1.parquet as calibration dataset. |
|
|
|
Original model: https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat |
|
|
|
## Download instructions |
|
|
|
With git: |
|
|
|
```shell |
|
git clone --single-branch --branch 5.0 https://huggingface.co/bartowski/deepseek-llm-7b-chat-exl2 |
|
``` |
|
|
|
With huggingface hub (credit to TheBloke for instructions): |
|
|
|
```shell |
|
pip3 install huggingface-hub |
|
``` |
|
|
|
To download from a different branch, add the `--revision` parameter: |
|
|
|
```shell |
|
mkdir deepseek-llm-7b-chat-exl2 |
|
huggingface-cli download bartowski/deepseek-llm-7b-chat-exl2 --revision 5_0 --local-dir deepseek-llm-7b-chat-exl2 --local-dir-use-symlinks False |
|
``` |
|
|
