---
title: aixcoder-7b-base-exl2
canonical_url: "https://www.modelscope.cn/models/bartowski/aixcoder-7b-base-exl2"
md_url: "https://www.modelscope.cn/models/bartowski/aixcoder-7b-base-exl2.md"
repository: bartowski/aixcoder-7b-base-exl2
last_updated: 2024-11-18
pipeline_tag: text-generation
tasks:
  - text-generation
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 1174
stars: 0
---

# aixcoder-7b-base-exl2

> aixcoder-7b-base-exl2 - bartowski 在 ModelScope 开源的模型。Exllama v2 Quantizations of aixcoder-7b-base

- **Repository**: bartowski/aixcoder-7b-base-exl2
- **Tasks**: text-generation
- **Downloads**: 1174
- **Stars**: 0
- **Last updated**: 2024-11-18

Source: https://www.modelscope.cn/models/bartowski/aixcoder-7b-base-exl2

---

## Exllama v2 Quantizations of aixcoder-7b-base

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.18">turboderp's ExLlamaV2 v0.0.18</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/aiXcoder/aixcoder-7b-base

## Prompt format

No prompt format for base models.

## Available sizes


| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/bartowski/aixcoder-7b-base-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/bartowski/aixcoder-7b-base-exl2/tree/6_5) | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
| [5_0](https://huggingface.co/bartowski/aixcoder-7b-base-exl2/tree/5_0) | 5.0 | 6.0 | 6.0 GB | 7.4 GB |  9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
| [4_25](https://huggingface.co/bartowski/aixcoder-7b-base-exl2/tree/4_25) | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| [3_5](https://huggingface.co/bartowski/aixcoder-7b-base-exl2/tree/3_5) | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. |

## Download instructions

With git:

```shell
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/aixcoder-7b-base-exl2 aixcoder-7b-base-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 `aixcoder-7b-base-exl2`:

```shell
mkdir aixcoder-7b-base-exl2
huggingface-cli download bartowski/aixcoder-7b-base-exl2 --local-dir aixcoder-7b-base-exl2 --local-dir-use-symlinks False
```

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

Linux:

```shell
mkdir aixcoder-7b-base-exl2-6_5
huggingface-cli download bartowski/aixcoder-7b-base-exl2 --revision 6_5 --local-dir aixcoder-7b-base-exl2-6_5 --local-dir-use-symlinks False
```

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

```shell
mkdir aixcoder-7b-base-exl2-6.5
huggingface-cli download bartowski/aixcoder-7b-base-exl2 --revision 6_5 --local-dir aixcoder-7b-base-exl2-6.5 --local-dir-use-symlinks False
```

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