---
base_model: qblocks/zephyr_7b_norobots
datasets:
- HuggingFaceH4/no_robots
inference: false
library_name: peft
license: apache-2.0
model_creator: MonsterAPI
model_name: Zephyr 7B Norobots
model_type: mistral
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
tags:
- code
- instruct
- zephyr
---
---
#### Prompt Structure
```
<|system|> <|endoftext|> <|user|> [USER PROMPT]<|endoftext|> <|assistant|> [ASSISTANT ANSWER] <|endoftext|>
```
#### Train loss :
quantized_by: bartowski
pipeline_tag: text-generation
---
## Exllama v2 Quantizations of zephyr_7b_norobots
Using turboderp's ExLlamaV2 v0.0.8 for quantization.
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Conversion was done using wikitext-103-raw-v1-test.parquet as calibration dataset.
Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
Original model: https://huggingface.co/TheBloke/zephyr_7b_norobots-fp16
4.0 bits per weight
6.0 bits per weight
8.0 bits per weight
## Download instructions
With git:
```shell
git clone --single-branch --branch 4_0 https://huggingface.co/bartowski/zephyr_7b_norobots-exl2
```
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 `zephyr_7b_norobots-exl2`:
```shell
mkdir zephyr_7b_norobots-exl2
huggingface-cli download bartowski/zephyr_7b_norobots-exl2 --local-dir zephyr_7b_norobots-exl2 --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir zephyr_7b_norobots-exl2
huggingface-cli download bartowski/zephyr_7b_norobots-exl2 --revision 4_0 --local-dir zephyr_7b_norobots-exl2 --local-dir-use-symlinks False
```