Instructions to use Smilyai-labs/Sam-flash-mini-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Smilyai-labs/Sam-flash-mini-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Smilyai-labs/Sam-flash-mini-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Smilyai-labs/Sam-flash-mini-v1")
model = AutoModelForCausalLM.from_pretrained("Smilyai-labs/Sam-flash-mini-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Smilyai-labs/Sam-flash-mini-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Smilyai-labs/Sam-flash-mini-v1

SGLang

How to use Smilyai-labs/Sam-flash-mini-v1 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 "Smilyai-labs/Sam-flash-mini-v1" \
    --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": "Smilyai-labs/Sam-flash-mini-v1",
		"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 "Smilyai-labs/Sam-flash-mini-v1" \
        --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": "Smilyai-labs/Sam-flash-mini-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Smilyai-labs/Sam-flash-mini-v1 with Docker Model Runner:
```
docker model run hf.co/Smilyai-labs/Sam-flash-mini-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Sam-flash-mini-v1

Sam-flash-mini-v1 is a compact and efficient text generation model fine-tuned from DistilGPT2 by Smilyai Labs. Designed for creative writing, storytelling, and rapid prototyping, this model offers a balance between performance and resource efficiency.

Model Details

Base Model: DistilGPT2
Architecture: GPT2
Language: English
License: MIT
Developed by: Smilyai Labs

Try it out!

You can test this model in an interactive app:
Launch the Sam Flash Story Generator

Usage

You can easily load and use the model with the Hugging Face Transformers library:

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Smilyai-labs/Sam-flash-mini-v1")
model = AutoModelForCausalLM.from_pretrained("Smilyai-labs/Sam-flash-mini-v1")

input_text = "Once upon a time,"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 7

Safetensors

Model size

81.9M params

Tensor type

F32

Model tree for Smilyai-labs/Sam-flash-mini-v1

Quantizations

1 model

Smilyai-labs
/

Sam-flash-mini-v1

Sam-flash-mini-v1

Model Details

Try it out!

Usage

Model tree for Smilyai-labs/Sam-flash-mini-v1

Space using Smilyai-labs/Sam-flash-mini-v1 1