Instructions to use SulphurAI/Sulphur-2-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SulphurAI/Sulphur-2-base with Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("SulphurAI/Sulphur-2-base", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

llama-cpp-python

How to use SulphurAI/Sulphur-2-base with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SulphurAI/Sulphur-2-base",
	filename="prompt_enhancer/mmproj-BF16.gguf",
)

llm.create_chat_completion(
	messages = "\"A young man walking on the street\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SulphurAI/Sulphur-2-base with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SulphurAI/Sulphur-2-base:BF16
# Run inference directly in the terminal:
llama-cli -hf SulphurAI/Sulphur-2-base:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SulphurAI/Sulphur-2-base:BF16
# Run inference directly in the terminal:
llama-cli -hf SulphurAI/Sulphur-2-base:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf SulphurAI/Sulphur-2-base:BF16
# Run inference directly in the terminal:
./llama-cli -hf SulphurAI/Sulphur-2-base:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf SulphurAI/Sulphur-2-base:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SulphurAI/Sulphur-2-base:BF16

Use Docker

docker model run hf.co/SulphurAI/Sulphur-2-base:BF16

LM Studio
Jan
Ollama
How to use SulphurAI/Sulphur-2-base with Ollama:
```
ollama run hf.co/SulphurAI/Sulphur-2-base:BF16
```

Unsloth Studio new

How to use SulphurAI/Sulphur-2-base with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SulphurAI/Sulphur-2-base to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SulphurAI/Sulphur-2-base to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SulphurAI/Sulphur-2-base to start chatting

Pi new

How to use SulphurAI/Sulphur-2-base with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SulphurAI/Sulphur-2-base:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SulphurAI/Sulphur-2-base:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SulphurAI/Sulphur-2-base with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SulphurAI/Sulphur-2-base:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default SulphurAI/Sulphur-2-base:BF16

Run Hermes

hermes

Docker Model Runner
How to use SulphurAI/Sulphur-2-base with Docker Model Runner:
```
docker model run hf.co/SulphurAI/Sulphur-2-base:BF16
```

Lemonade

How to use SulphurAI/Sulphur-2-base with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SulphurAI/Sulphur-2-base:BF16

Run and chat with the model

lemonade run user.Sulphur-2-base-BF16

List all available models

lemonade list

Prompt Enhancer issue.

#10

by XXxMadWolxfXX - opened 22 days ago

Discussion

XXxMadWolxfXX

22 days ago

Just wanna know, your model is uncensored and NSFW, but the prompt enhancer isn't? It simply says "I cannot help you with that" for any NSFW prompt or uncensored prompts. Even when I simply asked "How NSFW can u go"

Smite79

21 days ago

There are already multiple criticisms about the workflow and models either not working or not generating the desired results. Personally, I have not used it. My recommendation is to use the AIKnowledge2Go workflow and pair with the following:

Q6_K or Q8_K GGUF Unet
Sikaworld's Abliterated High Fidelity Text Encoder
One of Kajai's dynamic LoRA's
Then add one of the many LoRA's from Civitai Red.

That combination will pretty much give you anything that is NSFW.

XXxMadWolxfXX

21 days ago

There are already multiple criticisms about the workflow and models either not working or not generating the desired results. Personally, I have not used it. My recommendation is to use the AIKnowledge2Go workflow and pair with the following:

Q6_K or Q8_K GGUF Unet
Sikaworld's Abliterated High Fidelity Text Encoder
One of Kajai's dynamic LoRA's
Then add one of the many LoRA's from Civitai Red.

That combination will pretty much give you anything that is NSFW.

Thank you

Smite79

21 days ago

•

edited 21 days ago

I should also clarify that this workflow is designed for ComfyUI and not LMStudio.

tech77

21 days ago

•

edited 21 days ago

@XXxMadWolxfXX
Just pick image you want at Lmstudio and give a short prompt what you want to happen at video and prompt enhancer will do the job.
Its not bot for talking...

XXxMadWolxfXX

21 days ago

@XXxMadWolxfXX
Just pick image you want at Lmstudio and give a short prompt what you want to happen at video and prompt enhancer will do the job.
Its not bot for talking...

LMAO, Yeah it worked.

cupra-ai

19 days ago

Which settings are you using for the PE? Temperature, top_k, penalties, etc...

stduhpf

16 days ago

•

edited 10 days ago

I think using Qwen3.5 as a base for the prompt ehencer was an odd choice, this model is more STEM-focused than creative, and it's very deeply censored too. Something like Ministral or Gemma would have worked better for this. It works pretty well regardless, though it still sometimes refuse even some barely risqué prompts.

Edit: Unlike whats' advised in the model card, adding a simple system prompt like: "Improve the user's video description. Do not omit the details provided by the user" seems to decrease the amount of refusals or soft-censoring a lot.

XXxMadWolxfXX

10 days ago

Which settings are you using for the PE? Temperature, top_k, penalties, etc...

Default. I don't change a thing, and it's working great for me, just not for chatting. If I give it an image and a prompt, it sometimes doesn't follow it, but most of the time it works.

XXxMadWolxfXX changed discussion status to closed 10 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment