---
license: mit
base_model: ZhangShenao/SELM-Llama-3-8B-Instruct-iter-2
tags:
- alignment-handbook
- dpo
- trl
- selm
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: SELM-Llama-3-8B-Instruct-iter-3
results: []
quantized_by: bartowski
pipeline_tag: text-generation
---
## Exllama v2 Quantizations of SELM-Llama-3-8B-Instruct-iter-3
Using turboderp's ExLlamaV2 v0.1.4 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.
Original model: https://huggingface.co/ZhangShenao/SELM-Llama-3-8B-Instruct-iter-3
## Prompt format
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Available sizes
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (8K) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/bartowski/SELM-Llama-3-8B-Instruct-iter-3-exl2/tree/8_0) | 8.0 | 8.0 | 10.1 GB | 10.5 GB | 11.5 GB | 13.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/bartowski/SELM-Llama-3-8B-Instruct-iter-3-exl2/tree/6_5) | 6.5 | 8.0 | 8.9 GB | 9.3 GB | 10.3 GB | 12.4 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
| [5_0](https://huggingface.co/bartowski/SELM-Llama-3-8B-Instruct-iter-3-exl2/tree/5_0) | 5.0 | 6.0 | 7.7 GB | 8.1 GB | 9.1 GB | 11.2 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
| [4_25](https://huggingface.co/bartowski/SELM-Llama-3-8B-Instruct-iter-3-exl2/tree/4_25) | 4.25 | 6.0 | 7.0 GB | 7.4 GB | 8.4 GB | 10.5 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| [3_5](https://huggingface.co/bartowski/SELM-Llama-3-8B-Instruct-iter-3-exl2/tree/3_5) | 3.5 | 6.0 | 6.4 GB | 6.8 GB | 7.8 GB | 9.9 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/SELM-Llama-3-8B-Instruct-iter-3-exl2 SELM-Llama-3-8B-Instruct-iter-3-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/SELM-Llama-3-8B-Instruct-iter-3-exl2 --revision 6_5 --local-dir SELM-Llama-3-8B-Instruct-iter-3-exl2-6_5
```
Windows (which apparently doesn't like _ in folders sometimes?):
```shell
huggingface-cli download bartowski/SELM-Llama-3-8B-Instruct-iter-3-exl2 --revision 6_5 --local-dir SELM-Llama-3-8B-Instruct-iter-3-exl2-6.5
```
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski