|
|
--- |
|
|
license: llama2 |
|
|
library_name: transformers |
|
|
tags: |
|
|
- code |
|
|
model-index: |
|
|
- name: Code Millenials |
|
|
results: |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
type: openai_humaneval |
|
|
name: HumanEval |
|
|
metrics: |
|
|
- name: pass@1 |
|
|
type: pass@1 |
|
|
value: 0.8048 |
|
|
verified: false |
|
|
quantized_by: bartowski |
|
|
pipeline_tag: text-generation |
|
|
--- |
|
|
|
|
|
## Exllama v2 Quantizations of code-millenials-34b |
|
|
|
|
|
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.12">turboderp's ExLlamaV2 v0.0.12</a> for quantization. |
|
|
|
|
|
## The "main" branch only contains the measurement.json, download one of the other branches for the model (see below) |
|
|
|
|
|
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions. |
|
|
|
|
|
Conversion was done using the default 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/budecosystem/code-millenials-34b |
|
|
|
|
|
|
|
|
<a href="https://huggingface.co/bartowski/code-millenials-34b-exl2/tree/6_5">6.5 bits per weight</a> |
|
|
|
|
|
<a href="https://huggingface.co/bartowski/code-millenials-34b-exl2/tree/5_0">5.0 bits per weight</a> |
|
|
|
|
|
<a href="https://huggingface.co/bartowski/code-millenials-34b-exl2/tree/4_25">4.25 bits per weight</a> |
|
|
|
|
|
<a href="https://huggingface.co/bartowski/code-millenials-34b-exl2/tree/3_75">3.75 bits per weight</a> |
|
|
|
|
|
<a href="https://huggingface.co/bartowski/code-millenials-34b-exl2/tree/3_0">3.0 bits per weight</a> |
|
|
|
|
|
## Download instructions |
|
|
|
|
|
With git: |
|
|
|
|
|
```shell |
|
|
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/code-millenials-34b-exl2 |
|
|
``` |
|
|
|
|
|
With huggingface hub (credit to TheBloke for instructions): |
|
|
|
|
|
```shell |
|
|
pip3 install huggingface-hub |
|
|
``` |
|
|
|
|
|
To download the `main` (only useful if you only care about measurement.json) branch to a folder called `code-millenials-34b-exl2`: |
|
|
|
|
|
```shell |
|
|
mkdir code-millenials-34b-exl2 |
|
|
huggingface-cli download bartowski/code-millenials-34b-exl2 --local-dir code-millenials-34b-exl2 --local-dir-use-symlinks False |
|
|
``` |
|
|
|
|
|
To download from a different branch, add the `--revision` parameter: |
|
|
|
|
|
Linux: |
|
|
|
|
|
```shell |
|
|
mkdir code-millenials-34b-exl2-6_5 |
|
|
huggingface-cli download bartowski/code-millenials-34b-exl2 --revision 6_5 --local-dir code-millenials-34b-exl2-6_5 --local-dir-use-symlinks False |
|
|
``` |
|
|
|
|
|
Windows (which apparently doesn't like _ in folders sometimes?): |
|
|
|
|
|
```shell |
|
|
mkdir code-millenials-34b-exl2-6.5 |
|
|
huggingface-cli download bartowski/code-millenials-34b-exl2 --revision 6_5 --local-dir code-millenials-34b-exl2-6.5 --local-dir-use-symlinks False |
|
|
``` |
