bartowski's picture
Add 8.0 link
e405930
|
raw
history blame
2.27 kB
---
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 :
![training loss](https://cdn-uploads.huggingface.co/production/uploads/63ba46aa0a9866b28cb19a14/EYUTlcPFz-2nXzNj5_gsW.png)
quantized_by: bartowski
pipeline_tag: text-generation
---
## Exllama v2 Quantizations of zephyr_7b_norobots
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.8">turboderp's ExLlamaV2 v0.0.8</a> 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
<a href="https://huggingface.co/bartowski/zephyr_7b_norobots-exl2/tree/8_0">8.0 bits per weight</a>
## 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
```