Instructions to use FPHam/Jackson_The_Formalizer_V2_13b_GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FPHam/Jackson_The_Formalizer_V2_13b_GPTQ with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="FPHam/Jackson_The_Formalizer_V2_13b_GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FPHam/Jackson_The_Formalizer_V2_13b_GPTQ")
model = AutoModelForCausalLM.from_pretrained("FPHam/Jackson_The_Formalizer_V2_13b_GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FPHam/Jackson_The_Formalizer_V2_13b_GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FPHam/Jackson_The_Formalizer_V2_13b_GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FPHam/Jackson_The_Formalizer_V2_13b_GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FPHam/Jackson_The_Formalizer_V2_13b_GPTQ

SGLang

How to use FPHam/Jackson_The_Formalizer_V2_13b_GPTQ with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "FPHam/Jackson_The_Formalizer_V2_13b_GPTQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FPHam/Jackson_The_Formalizer_V2_13b_GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "FPHam/Jackson_The_Formalizer_V2_13b_GPTQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FPHam/Jackson_The_Formalizer_V2_13b_GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FPHam/Jackson_The_Formalizer_V2_13b_GPTQ with Docker Model Runner:
```
docker model run hf.co/FPHam/Jackson_The_Formalizer_V2_13b_GPTQ
```

Please support me: Ko-fi

Jackson The Formalizer V2 - Uncensored, but that means nothing to Jackson. He doesn't really have any opinion either way.

Version 2 (improved rewriting abilities, while keeping the structure intact)

Note: Jackson V2 uses different instruction format than V1

Currently, Mr. Jackson works for FP editing services where he was previously employed by the government department responsible for proofreading official documents. We always turn to Jackson when we need to edit something too exciting.

His skill set allows him to create perfectly dull versions of texts most of the time while also improving spelling and grammar.

Input

USER: Formalize: "WTF?" I shouted angrily. "I thought he was just wearing that to scare Volsemort!"

"Hello everyone." he said happily. "As u can see I gave the room a makeover. Whjat do u fink about it?"

Everyone from the poser table in Gryiffindoor started to cheer. Well we goths just looked at each other all disfusted and shook our heads. We couldn't believe what a poser he was!1.

"BTW you can call me Albert." HE CALLED AS WE LEFT to our classes.

"What a f*****g poser!" Draco shouted angrily as we we to Transfomation. We were holding hands. Vampire looked really jealous. I could see him crying blood in a gothic way (geddit, way lik Gerard) but I didn't say anything. "I bet he's havin a mid-life crisis!" Willow shouted.

Output

ASSISTANT: "What is going on here?" I yelled loudly. "I believed he wore that to frighten Voldemort."

"Good day to everyone." He stated with enthusiasm. "You will notice that I have redesigned this room. What are your thoughts on my work?"

The people sitting at the table for the house of Griffindore began cheering. We Goths simply looked at one another and shook our heads in disgust. We couldn't believe how much of a poser he was.

"By the way, you may refer to me as Albert." As we left to go to class, he called out his name.

"That person is very annoying." Draco exclaimed angrily while we walked towards Transformation. We held hands. Vampire appeared quite envious. I saw him shed tears in a gothic manner, similar to Gerard, but did not comment. "He must be experiencing a mid-life crisis." Willow declared.

Jackson uses this instruct (different than V1)

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.

USER: <the text> 
 
ASSISTANT:

You can use commands such as rewrite the text, make it sound more formal, formalize, etc... or just paste a paragraph without any instructions. Jackson will happily rewrite it.

Note: The goal of these models is not just rewrite the text on sentence by sentence basis as in grammar checker but to actually understand the concept of the input paragraph. Sometimes two sentences can be replaced by one or the other way around.

You can also chat with Jackson. He can figure out if you are asking a question or want to rewrite the text, although his responses may be peculiar.

Downloads last month: 2

FPHam
/

Jackson_The_Formalizer_V2_13b_GPTQ

Jackson The Formalizer V2 - Uncensored, but that means nothing to Jackson. He doesn't really have any opinion either way.

Space using FPHam/Jackson_The_Formalizer_V2_13b_GPTQ 1