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

distilled GGUF available for those with low vram requirements

#17

by realrebelai - opened 15 days ago

Discussion

realrebelai

15 days ago

•

edited 15 days ago

smthem provided a gguf for the distilled model. i provided a workflow for it if anyones interested. its a different node setup than what this requires and takes a little work but runs PRETTY MUCH just as well! not sure if im stepping on toes by posting this here but the link to my workflow so you can grab the files and run it is here, download and installation instructions in description:

https://civitai.red/models/2606616/rebels-sulphur-2-ltx-23-nsfw-model-gguf

hope this helps some struggling vram cards! <3

plz12345

15 days ago

I'm trying to package this model for MLX, for the same reasons (VRAM poor). Wondering if you could share how you built yours, since the readme on this repo is basically a one-liner. No shame thrown, people on here are purely in it for the love of the game.

I'm just struggling on which loras in this repo matter, and for which use cases. I planned on packaging a dev model and a distilled model, but I want to bake in the loras because I also want it quantized.

Nice work on yours!

realrebelai

15 days ago

I'm trying to package this model for MLX, for the same reasons (VRAM poor). Wondering if you could share how you built yours, since the readme on this repo is basically a one-liner. No shame thrown, people on here are purely in it for the love of the game.

i must regretfully but respectfully admit this is not my work entirely, just the workflow itself. The guts behind it is smthem, hes a contributor on the site. ill link his nodes and model files so you can take a look. seems like everytime i touch his nodes with claude they break so i just leave it to him everytime. im not sure how he runs his nodes on the inside. definately give him a follow because he stays up to date on the less viral models. i use alot of his work in my youtube content.

github nodes:
https://github.com/smthemex/ComfyUI_LTX2_SM

HF model files:
https://huggingface.co/smthem/LTX-2.3-test-gguf/tree/main

plz12345

15 days ago

No shame there, credit where it's due, to all involved.

ComfyUI on Mac is pretty "Meh" at present, but I hope it improves over time. The few times I tried it, I had no luck. It's partly what sent me down the rabbit hole of creating MLX versions of this model, because we don't all have RTX 4090's and MLX + quantization = heaven, on MacOS generation.

Smite79

15 days ago

This comment has been hidden (marked as Resolved)

realrebelai

15 days ago

Model has been removed the Civitai Red site.

no it wasnt, its probably a bug. i just checked my page and its still there :)

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