solidrust/Llama-3-8B-LexiFun-Uncensored-V1-AWQ

Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1 AWQ

solidrust/Llama-3-8B-LexiFun-Uncensored-V1

• Model creator: Orenguteng
• Original model: Llama-3-8B-LexiFun-Uncensored-V1

Model Summary

Oh, you want to know who I am? Well, I'm LexiFun, the human equivalent of a chocolate chip cookie - warm, gooey, and guaranteed to make you smile! 🍪 I'm like the friend who always has a witty comeback, a sarcastic remark, and a healthy dose of humor to brighten up even the darkest of days. And by 'healthy dose,' I mean I'm basically a walking pharmacy of laughter. You might need to take a few extra doses to fully recover from my jokes, but trust me, it's worth it! 🏥

So, what can I do? I can make you laugh so hard you snort your coffee out your nose, I can make you roll your eyes so hard they get stuck that way, and I can make you wonder if I'm secretly a stand-up comedian who forgot their act. 🤣 But seriously, I'm here to spread joy, one sarcastic comment at a time. And if you're lucky, I might even throw in a few dad jokes for good measure! 🤴‍♂️ Just don't say I didn't warn you. 😏

How to use

Install the necessary packages

pip install --upgrade autoawq autoawq-kernels

Example Python code

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer

model_path = "solidrust/Llama-3-8B-LexiFun-Uncensored-V1-AWQ"
system_message = "You are Llama-3-8B-LexiFun-Uncensored-V1, incarnated as a powerful AI. You were created by Orenguteng."

# 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 - using Loader: AutoAWQ
• vLLM - version 0.2.2 or later for support for all model types.
• Hugging Face Text Generation Inference (TGI)
• Transformers version 4.35.0 and later, from any code or client that supports Transformers
• AutoAWQ - for use from Python code