Instructions to use Technotech/MagicPrompt-tinystories-33M-epoch10-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Technotech/MagicPrompt-tinystories-33M-epoch10-merged with Transformers:

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

pipe = pipeline("text-generation", model="Technotech/MagicPrompt-tinystories-33M-epoch10-merged")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Technotech/MagicPrompt-tinystories-33M-epoch10-merged")
model = AutoModelForCausalLM.from_pretrained("Technotech/MagicPrompt-tinystories-33M-epoch10-merged")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Technotech/MagicPrompt-tinystories-33M-epoch10-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Technotech/MagicPrompt-tinystories-33M-epoch10-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Technotech/MagicPrompt-tinystories-33M-epoch10-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Technotech/MagicPrompt-tinystories-33M-epoch10-merged

SGLang

How to use Technotech/MagicPrompt-tinystories-33M-epoch10-merged 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 "Technotech/MagicPrompt-tinystories-33M-epoch10-merged" \
    --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": "Technotech/MagicPrompt-tinystories-33M-epoch10-merged",
		"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 "Technotech/MagicPrompt-tinystories-33M-epoch10-merged" \
        --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": "Technotech/MagicPrompt-tinystories-33M-epoch10-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Technotech/MagicPrompt-tinystories-33M-epoch10-merged with Docker Model Runner:
```
docker model run hf.co/Technotech/MagicPrompt-tinystories-33M-epoch10-merged
```

MagicPrompt TinyStories-33M (Merged)

Info

Magic prompt completion model trained on a dataset of 80k Stable Diffusion prompts. Base model: TinyStories-33M. Inspired by MagicPrompt-Stable-Diffusion.

Model seems to be pretty decent for 33M params due to the TinyStories base, but it clearly lacks much of an understanding of pretty much anything. Still, considering the size, I think it's decent. Whether you would use this over a small GPT-2 based model is up to you.

Examples

Best generation settings I found: max_new_tokens=40, do_sample=True, temperature=1.2, num_beams=10, no_repeat_ngram_size=2, early_stopping=True, repetition_penalty=1.35, top_k=50, top_p=0.55, eos_token_id=tokenizer.eos_token_id, pad_token_id=0 (there may be better settings). no_repeat_ngram_size is important for making sure the model doesn't repeat phrases (as it is quite small).

(Bold text is generated by the model)

"found footage of a ufo in the forest, by lusax, wlop, greg rutkowski, stanley artgerm, highly detailed, intricate, digital painting, artstation, concept art, smooth"

"A close shot of a bird in a jungle, with two legs, with long hair on a tall, long brown body, long white skin, sharp teeth, high bones, digital painting, artstation, concept art, illustration by wlop,"

"Camera shot of a strange young girl wearing a cloak, wearing a mask in clothes, with long curly hair, long hair, black eyes, dark skin, white teeth, long brown eyes eyes, big eyes, sharp"

"An illustration of a house, stormy weather, sun, moonlight, night, concept art, 4 k, wlop, by wlop, by jose stanley, ilya kuvshinov, sprig"

"A field of flowers, camera shot, 70mm lens, fantasy, intricate, highly detailed, artstation, concept art, sharp focus, illustration, illustration, artgerm jake daggaws, artgerm and jaggodieie brad"

Next steps

Larger dataset ie neuralworm/stable-diffusion-discord-prompts or daspartho/stable-diffusion-prompts
More epochs
Instead of going smaller than GPT-2 137M, fine tune a 1-7B param model

Training config

Rank 16 LoRA
Trained on Gustavosta/Stable-Diffusion-Prompts for 10 epochs
Batch size of 64

Training procedure

The following bitsandbytes quantization config was used during training:

load_in_8bit: False
load_in_4bit: True
llm_int8_threshold: 6.0
llm_int8_skip_modules: None
llm_int8_enable_fp32_cpu_offload: False
llm_int8_has_fp16_weight: False
bnb_4bit_quant_type: fp4
bnb_4bit_use_double_quant: False
bnb_4bit_compute_dtype: float32

Framework versions

PEFT 0.5.0.dev0

Downloads last month: 8

Safetensors

Model size

85.3M params

Tensor type

F32

BOOL

Technotech
/

MagicPrompt-tinystories-33M-epoch10-merged