|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered |
|
inference: false |
|
--- |
|
|
|
# WizardLM - uncensored: An Instruction-following LLM Using Evol-Instruct |
|
|
|
These files are GPTQ 4bit model files for [Eric Hartford's 'uncensored' version of WizardLM](https://huggingface.co/ehartford/WizardLM-7B-Uncensored). |
|
|
|
It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa). |
|
|
|
Eric did a fresh 7B training using the WizardLM method, on [a dataset edited to remove all the "I'm sorry.." type ChatGPT responses](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered). |
|
|
|
## Other repositories available |
|
|
|
* [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardLM-7B-uncensored-GPTQ) |
|
* [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/WizardLM-7B-uncensored-GGML) |
|
* [Eric's unquantised model in HF format](https://huggingface.co/ehartford/WizardLM-7B-Uncensored) |
|
|
|
## How to easily download and use this model in text-generation-webui |
|
|
|
Open the text-generation-webui UI as normal. |
|
|
|
1. Click the **Model tab**. |
|
2. Under **Download custom model or LoRA**, enter `TheBloke/WizardLM-7B-uncensored-GPTQ`. |
|
3. Click **Download**. |
|
4. Wait until it says it's finished downloading. |
|
5. Click the **Refresh** icon next to **Model** in the top left. |
|
6. In the **Model drop-down**: choose the model you just downloaded, `WizardLM-7B-uncensored-GPTQ`. |
|
7. If you see an error in the bottom right, ignore it - it's temporary. |
|
8. Fill out the `GPTQ parameters` on the right: `Bits = 4`, `Groupsize = 128`, `model_type = Llama` |
|
9. Click **Save settings for this model** in the top right. |
|
10. Click **Reload the Model** in the top right. |
|
11. Once it says it's loaded, click the **Text Generation tab** and enter a prompt! |
|
|
|
## Provided files |
|
|
|
**Compatible file - WizardLM-7B-uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors** |
|
|
|
In the `main` branch - the default one - you will find `WizardLM-7B-uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors` |
|
|
|
This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility |
|
|
|
It was created without the `--act-order` parameter. It may have slightly lower inference quality compared to the other file, but is guaranteed to work on all versions of GPTQ-for-LLaMa and text-generation-webui. |
|
|
|
* `wizard-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors` |
|
* Works with all versions of GPTQ-for-LLaMa code, both Triton and CUDA branches |
|
* Works with text-generation-webui one-click-installers |
|
* Parameters: Groupsize = 128g. No act-order. |
|
* Command used to create the GPTQ: |
|
``` |
|
python llama.py models/ehartford_WizardLM-7B-Uncensored c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors /workspace/eric-gptq/WizardLM-7B-uncensored-GPTQ-4bit-128g.compat.no-act-order.safetensors |
|
``` |
|
|
|
# Eric's original model card |
|
|
|
This is WizardLM trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA. |
|
|
|
Shout out to the open source AI/ML community, and everyone who helped me out, including Rohan, TheBloke, and Caseus |
|
|
|
# WizardLM's original model card |
|
|
|
Overview of Evol-Instruct |
|
Evol-Instruct is a novel method using LLMs instead of humans to automatically mass-produce open-domain instructions of various difficulty levels and skills range, to improve the performance of LLMs. |
|
|
|
 |
|
 |
