---
license: mit
license_link: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE

language:
- multilingual
pipeline_tag: text-generation
tags:
- nlp
- code
inference:
  parameters:
    temperature: 0.7
widget:
  - messages:
      - role: user
        content: Can you provide ways to eat combinations of bananas and dragonfruits?
quantized_by: bartowski
---

## Exllama v2 Quantizations of Phi-3-medium-128k-instruct

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.21">turboderp's ExLlamaV2 v0.0.21</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/microsoft/Phi-3-medium-128k-instruct

## Prompt format

```
<|user|> {prompt}<|end|><|assistant|><|end|>
```

## Available sizes

| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-exl2/tree/8_0) | 8.0  | 8.0 | 14.0 GB | 16.4 GB | Max quality that ExLlamaV2 can produce, **recommended**. |
| [6_5](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-exl2/tree/6_5) | 6.5  | 8.0 | 12.5 GB | 14.9 GB | Near unquantized performance at vastly reduced size, **recommended**. |
| [5_0](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-exl2/tree/5_0) | 5.0  | 6.0 | 10.0 GB | 12.4 GB | Slightly lower quality vs 6.5. |
| [4_25](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-exl2/tree/4_25) | 4.25 | 6.0 | 8.8 GB | 11.2 GB | GPTQ equivalent bits per weight. |
| [3_5](https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-exl2/tree/3_5) | 3.5  | 6.0 | 7.6 GB | 10.0 GB | Lower quality, not recommended. |

## Download instructions

With git:

```shell
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-exl2 Phi-3-medium-128k-instruct-exl2-6_5
```

With huggingface hub (credit to TheBloke for instructions):

```shell
pip3 install huggingface-hub
```

To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:

Linux:

```shell
huggingface-cli download bartowski/Phi-3-medium-128k-instruct-exl2 --revision 6_5 --local-dir Phi-3-medium-128k-instruct-exl2-6_5
```

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

```shell
huggingface-cli download bartowski/Phi-3-medium-128k-instruct-exl2 --revision 6_5 --local-dir Phi-3-medium-128k-instruct-exl2-6.5
```

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