---
language:
- en
library_name: transformers
pipeline_tag: text-generation
datasets:
- jondurbin/airoboros-2.2
- Open-Orca/OpenOrca
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_V2_196k
- TokenBender/python_eval_instruct_51k
tags:
- code
license: apache-2.0
model-index:
- name: SpeechlessCoder
  results:
  - task:
      type: text-generation
    dataset:
      type: openai_humaneval
      name: HumanEval
    metrics:
    - name: pass@1
      type: pass@1
      value: 
      verified: false
quantized_by: bartowski
---

## Exllama v2 Quantizations of speechless-instruct-mistral-7b-v0.2

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/uukuguy/speechless-instruct-mistral-7b-v0.2

## Prompt format

No chat template specified so default is used. This may be incorrect, check original model card for details.

```
<s> [INST] <<SYS>>
{system_prompt}
<</SYS>>

{prompt} [/INST]  </s>
```

## Available sizes


| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/bartowski/speechless-instruct-mistral-7b-v0.2-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/speechless-instruct-mistral-7b-v0.2-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/speechless-instruct-mistral-7b-v0.2-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/speechless-instruct-mistral-7b-v0.2-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/speechless-instruct-mistral-7b-v0.2-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/speechless-instruct-mistral-7b-v0.2-exl2 speechless-instruct-mistral-7b-v0.2-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/speechless-instruct-mistral-7b-v0.2-exl2 --revision 6_5 --local-dir speechless-instruct-mistral-7b-v0.2-exl2-6_5
```

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

```shell
huggingface-cli download bartowski/speechless-instruct-mistral-7b-v0.2-exl2 --revision 6_5 --local-dir speechless-instruct-mistral-7b-v0.2-exl2-6.5
```

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