|
--- |
|
quantized_by: bartowski |
|
--- |
|
|
|
# Exllama v2 Quantizations of Llama-2-7b-chat-hf-function-calling-v3 at 3.5 bits per weight |
|
|
|
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</a> for quantization. |
|
|
|
Conversion was done using the default calibration dataset. |
|
|
|
Original model: https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v3 |
|
|
|
## Download instructions |
|
|
|
With git: |
|
|
|
```shell |
|
git clone --single-branch --branch 3.5 https://huggingface.co/bartowski/Llama-2-7b-chat-hf-function-calling-v3-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 Llama-2-7b-chat-hf-function-calling-v3-exl2 |
|
huggingface-cli download bartowski/Llama-2-7b-chat-hf-function-calling-v3-exl2 --revision 3_5 --local-dir Llama-2-7b-chat-hf-function-calling-v3-exl2 --local-dir-use-symlinks False |
|
``` |
|
|
