---
license: llama2
base_model:
- codellama/CodeLlama-7b-Python-hf
datasets:
- nvidia/OpenMathInstruct-1
language:
- en
tags:
- nvidia
- code
- math
quantized_by: bartowski
pipeline_tag: text-generation
---

## Exllama v2 Quantizations of OpenMath-CodeLlama-7b-Python-hf

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.13">turboderp's ExLlamaV2 v0.0.13</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/nvidia/OpenMath-CodeLlama-7b-Python-hf

No GQA - VRAM requirements will be higher

| Branch                                                         | Bits | lm_head bits | Size (4k) | Size (16k) | Description |
| -------------------------------------------------------------- | ---- | ------------ | --------- | ---------- | ----------- |
| [8_0](https://huggingface.co/bartowski/OpenMath-CodeLlama-7b-Python-hf-exl2/tree/8_0) | 8.0 | 8.0 | 9.4 GB | 15.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/bartowski/OpenMath-CodeLlama-7b-Python-hf-exl2/tree/6_5) | 6.5  | 8.0 | 8.6 GB | 14.8 GB | Near unquantized performance at vastly reduced size, **recommended**. |
| [5_0](https://huggingface.co/bartowski/OpenMath-CodeLlama-7b-Python-hf-exl2/tree/5_0) | 5.0  | 6.0 | 7.2 GB | 13.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards with 4k context. |
| [4_25](https://huggingface.co/bartowski/OpenMath-CodeLlama-7b-Python-hf-exl2/tree/4_25) | 4.25 | 6.0 | 6.5 GB | 12.7 GB | GPTQ equivalent bits per weight. |
| [3_5](https://huggingface.co/bartowski/OpenMath-CodeLlama-7b-Python-hf-exl2/tree/3_5) | 3.5 | 6.0 | 5.9 GB | 12.1 GB | Lower quality, not recommended. |

## Download instructions

With git:

```shell
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/OpenMath-CodeLlama-7b-Python-hf-exl2 OpenMath-CodeLlama-7b-Python-hf-exl2-6_5
```

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 `OpenMath-CodeLlama-7b-Python-hf-exl2`:

```shell
mkdir OpenMath-CodeLlama-7b-Python-hf-exl2
huggingface-cli download bartowski/OpenMath-CodeLlama-7b-Python-hf-exl2 --local-dir OpenMath-CodeLlama-7b-Python-hf-exl2 --local-dir-use-symlinks False
```

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

Linux:

```shell
mkdir OpenMath-CodeLlama-7b-Python-hf-exl2-6_5
huggingface-cli download bartowski/OpenMath-CodeLlama-7b-Python-hf-exl2 --revision 6_5 --local-dir OpenMath-CodeLlama-7b-Python-hf-exl2-6_5 --local-dir-use-symlinks False
```

Windows (which apparently doesn't like _ in folders sometimes?):

```shell
mkdir OpenMath-CodeLlama-7b-Python-hf-exl2-6.5
huggingface-cli download bartowski/OpenMath-CodeLlama-7b-Python-hf-exl2 --revision 6_5 --local-dir OpenMath-CodeLlama-7b-Python-hf-exl2-6.5 --local-dir-use-symlinks False
```

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski