Instructions to use neph1/sd-seer-griffin-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neph1/sd-seer-griffin-3b with Transformers:

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

pipe = pipeline("text-generation", model="neph1/sd-seer-griffin-3b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("neph1/sd-seer-griffin-3b")
model = AutoModelForCausalLM.from_pretrained("neph1/sd-seer-griffin-3b")

llama-cpp-python

How to use neph1/sd-seer-griffin-3b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="neph1/sd-seer-griffin-3b",
	filename="gguf/sd-seer-griffin-3b-q5_k_m.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use neph1/sd-seer-griffin-3b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf neph1/sd-seer-griffin-3b:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf neph1/sd-seer-griffin-3b:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf neph1/sd-seer-griffin-3b:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf neph1/sd-seer-griffin-3b:Q5_K_M

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 neph1/sd-seer-griffin-3b:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf neph1/sd-seer-griffin-3b:Q5_K_M

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 neph1/sd-seer-griffin-3b:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf neph1/sd-seer-griffin-3b:Q5_K_M

Use Docker

docker model run hf.co/neph1/sd-seer-griffin-3b:Q5_K_M

LM Studio
Jan

vLLM

How to use neph1/sd-seer-griffin-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neph1/sd-seer-griffin-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neph1/sd-seer-griffin-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/neph1/sd-seer-griffin-3b:Q5_K_M

SGLang

How to use neph1/sd-seer-griffin-3b 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 "neph1/sd-seer-griffin-3b" \
    --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": "neph1/sd-seer-griffin-3b",
		"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 "neph1/sd-seer-griffin-3b" \
        --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": "neph1/sd-seer-griffin-3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use neph1/sd-seer-griffin-3b with Ollama:
```
ollama run hf.co/neph1/sd-seer-griffin-3b:Q5_K_M
```

Unsloth Studio new

How to use neph1/sd-seer-griffin-3b 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 neph1/sd-seer-griffin-3b 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 neph1/sd-seer-griffin-3b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for neph1/sd-seer-griffin-3b to start chatting

Docker Model Runner
How to use neph1/sd-seer-griffin-3b with Docker Model Runner:
```
docker model run hf.co/neph1/sd-seer-griffin-3b:Q5_K_M
```

Lemonade

How to use neph1/sd-seer-griffin-3b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull neph1/sd-seer-griffin-3b:Q5_K_M

Run and chat with the model

lemonade run user.sd-seer-griffin-3b-Q5_K_M

List all available models

lemonade list

Model Card for Model ID

This is an experimental model that translates natural language into prompt tags for stable diffusion.

The input is synthetic, and generated with chronos-hermes-13b-v2.Q4_K_M

The tags come from Gustavosta's MagicPrompt-Stable-Diffusion.

Example (validation set):

Input: "Render a realistic 3D sneaker with a futuristic design, featuring intricate detail and a hexagon mesh pattern. Use soft, natural lighting to highlight the purple and blue leather, as well as the shiny plastic accents. The sneaker should be viewed from a side angle in close-up, with a sharp focus and neon glowing lines. The final image should be trending on popular art platforms like ArtStation and DeviantArt, and should resemble popular brands like Nike, Asics, and Salomon."

Output: "realistic 3d sneaker futuristic design by greg rutkowski with intricate detail in the style of alphonse mucha using soft natural lighting to highlight purple blue leather shiny plastic accents closeup sharp focus neon glowing lines trending on artstation deviantart nike asics salomon"

Ground truth: "realistic 3 d render of a futuristic sneaker, beautiful studio lighting, soft, sharp focus, neon glowing lines, intricate detail, purple and blue leather, soft white rubber, shiny plastic, hexagon mesh, gold filigree, octane render, side view, close up, trending on artstation, deviantart, nike, asics, salomon"

Other example (maybe polluted):

Input: "Cute, friendly barista in Tokyo by Charlie Bowater and Titian and ArtGerm. Intricate face with symmetrical eyes. Japanese cafe setting. Elegant and beautiful with highly detailed elements. Dramatic lighting and sharp focus. Trending on ArtStation with tags such as 'ArtStationHD', 'ArtStationHQ', 'Unreal Engine', '4K', and '8K'. Instruct the artist to create a piece that captures the essence of the barista's personality and the unique atmosphere of the cafe, while showcasing their skill in creating intricate and highly detailed artwork. Use vibrant colors and dynamic lighting to create a visually stunning piece that will stand out on ArtStation and other online platforms."

Output: "Cute friendly barista by Charlie Bowater Titian artgerm juliette lewis symmetrical eyes Japanese cafe setting elegant beautiful highly detailed intricate, dramatic lighting sharp focus trending on artstation hq unreal engine 4 k 8 k, ArtStationHD ,ArtStationHQ"

Model Description

Example comparisons: In all cases: 1. Natural language as prompt. 2. Tags. 3. sd-seer output as prompt. 4. sd-seer output, but sdxl

Prompt: Render a realistic 3D sneaker with a futuristic design, featuring intricate detail and a hexagon mesh pattern. Use soft, natural lighting to highlight the purple and blue leather, as well as the shiny plastic accents. The sneaker should be viewed from a side angle in close-up, with a sharp focus and neon glowing lines. The final image should be trending on popular art platforms like ArtStation and DeviantArt, and should resemble popular brands like Nike, Asics, and Salomon.

Prompt: A whirlwind of souls rushing inside the metaverse, with half-body figures wearing a tiara and a tattoo of a pharaoh on their skin. The android or cyborg character should have a cyberpunk face, and the artwork should be inspired by the styles of Loish, D&D, fantasy, intricate, elegant, highly detailed, colorful, and vivid color. The final piece should be a digital painting that showcases the artist's skill and creativity, and can be submitted to ArtStation or featured in a concept art gallery.

Prompt: Cute, friendly barista in Tokyo by Charlie Bowater and Titian and ArtGerm. Intricate face with symmetrical eyes. Japanese cafe setting. Elegant and beautiful with highly detailed elements. Dramatic lighting and sharp focus. Trending on ArtStation with tags such as 'ArtStationHD', 'ArtStationHQ', 'Unreal Engine', '4K', and '8K'. Instruct the artist to create a piece that captures the essence of the barista's personality and the unique atmosphere of the cafe, while showcasing their skill in creating intricate and highly detailed artwork. Use vibrant colors and dynamic lighting to create a visually stunning piece that will stand out on ArtStation and other online platforms.

Developed by: Me
Model type: Llama2
License: Apache 2.0
Finetuned from model: https://huggingface.co/acrastt/Griffin-3B

How to Get Started with the Model

System prompt: "This is a conversation between User and the helpful AI-bot Llama. Llama breaks down image descriptions into precise comma-separated single-word tags adding tags where they might increase quality. Llama writes only in comma-separated tags without asking questions.""

Prompt template:

### HUMAN:
prompt

### RESPONSE:
<leave a newline for the model to answer>

Temperature: 0.3

Training Details

Training Procedure

I based my dataset on the prompts from this dataset: https://huggingface.co/Gustavosta/MagicPrompt-Stable-Diffusion

Based on that, I asked chronos-hermes-v2-13b to generate natural language descriptions.

I then trained a model on the pairs, with the NL as input and the prompt tags as output

Training Hyperparameters

Number of training epochs

num_train_epochs = 5

Enable fp16/bf16 training (set bf16 to True with an A100)

fp16 = False bf16 = True

Batch size per GPU for training

per_device_train_batch_size = 8

Batch size per GPU for evaluation

per_device_eval_batch_size = 8

Number of update steps to accumulate the gradients for

gradient_accumulation_steps = 1

Enable gradient checkpointing

gradient_checkpointing = True

Maximum gradient normal (gradient clipping)

max_grad_norm = 0.3

Initial learning rate (AdamW optimizer)

learning_rate = 3e-5

Weight decay to apply to all layers except bias/LayerNorm weights

weight_decay = 0.001

Optimizer to use

optim = "paged_adamw_32bit"

Learning rate schedule

lr_scheduler_type = "cosine"

Number of training steps (overrides num_train_epochs)

max_steps = -1

Ratio of steps for a linear warmup (from 0 to learning rate)

warmup_ratio = 0.03

Environmental Impact

Hardware Type: RTX 3060
Hours used: 6 hours
Carbon Emitted: None? As I use a non-co2 emitting energy provider.

Downloads last month: 213

Safetensors

Model size

3B params

Tensor type

F16

Datasets used to train neph1/sd-seer-griffin-3b

Collection including neph1/sd-seer-griffin-3b

sd-seer

Collection

Experimental models to convert natural language stable diffusion prompts to tags • 2 items • Updated Oct 20, 2024 • 1