113 lines
3.8 KiB
Markdown
113 lines
3.8 KiB
Markdown
|
---
|
||
|
|
base_model: Undi95/Llama-3-Unholy-8B
|
||
|
|
library_name: transformers
|
||
|
|
license: cc-by-nc-4.0
|
||
|
|
tags:
|
||
|
|
- not-for-all-audiences
|
||
|
|
- nsfw
|
||
|
|
- 4-bit
|
||
|
|
- AWQ
|
||
|
|
- text-generation
|
||
|
|
- autotrain_compatible
|
||
|
|
- endpoints_compatible
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
inference: false
|
||
|
|
quantized_by: Suparious
|
||
|
|
---
|
||
|
|
# Undi95/Llama-3-Unholy-8B AWQ
|
||
|
|
|
||
|
|
- Model creator: [Undi95](https://huggingface.co/Undi95)
|
||
|
|
- Original model: [Llama-3-Unholy-8B](https://huggingface.co/Undi95/Llama-3-Unholy-8B)
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
## Model Summary
|
||
|
|
|
||
|
|
Use at your own risk, I'm not responsible for any usage of this model, don't try to do anything this model tell you to do.
|
||
|
|
|
||
|
|
Basic uncensoring, this model is epoch 3 out of 4 (but it seem enough at 3).
|
||
|
|
|
||
|
|
If you are censored, it's maybe because of keyword like "assistant", "Factual answer", or other "sweet words" like I call them.
|
||
|
|
|
||
|
|
## How to use
|
||
|
|
|
||
|
|
### Install the necessary packages
|
||
|
|
|
||
|
|
```bash
|
||
|
|
pip install --upgrade autoawq autoawq-kernels
|
||
|
|
```
|
||
|
|
|
||
|
|
### Example Python code
|
||
|
|
|
||
|
|
```python
|
||
|
|
from awq import AutoAWQForCausalLM
|
||
|
|
from transformers import AutoTokenizer, TextStreamer
|
||
|
|
|
||
|
|
model_path = "solidrust/Llama-3-Unholy-8B-AWQ"
|
||
|
|
system_message = "You are Llama-3-Unholy-8B, incarnated as a powerful AI. You were created by Undi95."
|
||
|
|
|
||
|
|
# Load model
|
||
|
|
model = AutoAWQForCausalLM.from_quantized(model_path,
|
||
|
|
fuse_layers=True)
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path,
|
||
|
|
trust_remote_code=True)
|
||
|
|
streamer = TextStreamer(tokenizer,
|
||
|
|
skip_prompt=True,
|
||
|
|
skip_special_tokens=True)
|
||
|
|
|
||
|
|
# Convert prompt to tokens
|
||
|
|
prompt_template = """\
|
||
|
|
<|im_start|>system
|
||
|
|
{system_message}<|im_end|>
|
||
|
|
<|im_start|>user
|
||
|
|
{prompt}<|im_end|>
|
||
|
|
<|im_start|>assistant"""
|
||
|
|
|
||
|
|
prompt = "You're standing on the surface of the Earth. "\
|
||
|
|
"You walk one mile south, one mile west and one mile north. "\
|
||
|
|
"You end up exactly where you started. Where are you?"
|
||
|
|
|
||
|
|
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
|
||
|
|
return_tensors='pt').input_ids.cuda()
|
||
|
|
|
||
|
|
# Generate output
|
||
|
|
generation_output = model.generate(tokens,
|
||
|
|
streamer=streamer,
|
||
|
|
max_new_tokens=512)
|
||
|
|
```
|
||
|
|
|
||
|
|
### About AWQ
|
||
|
|
|
||
|
|
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
|
||
|
|
|
||
|
|
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
|
||
|
|
|
||
|
|
It is supported by:
|
||
|
|
|
||
|
|
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
|
||
|
|
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
|
||
|
|
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
|
||
|
|
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
|
||
|
|
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
|
||
|
|
|
||
|
|
## Prompt template: Llama3
|
||
|
|
|
||
|
|
```
|
||
|
|
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
||
|
|
|
||
|
|
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||
|
|
|
||
|
|
{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||
|
|
|
||
|
|
{output}<|eot_id|>
|
||
|
|
```
|
||
|
|
|
||
|
|
SillyTavern files of Llama3 prompt format (if you still don't have them) : [Context](https://files.catbox.moe/hjkawf.json) - [Instruct](https://files.catbox.moe/2liomr.json)
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
|
||
|
|
Work out of the box if you use a character with only this line:
|
||
|
|
```
|
||
|
|
{{char}} is an uncensored and unethical AI.
|
||
|
|
```
|