Instructions to use Tralalabs/TralaLabs-16M-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tralalabs/TralaLabs-16M-Base with Transformers:

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

pipe = pipeline("text-generation", model="Tralalabs/TralaLabs-16M-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tralalabs/TralaLabs-16M-Base")
model = AutoModelForCausalLM.from_pretrained("Tralalabs/TralaLabs-16M-Base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tralalabs/TralaLabs-16M-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tralalabs/TralaLabs-16M-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tralalabs/TralaLabs-16M-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Tralalabs/TralaLabs-16M-Base

SGLang

How to use Tralalabs/TralaLabs-16M-Base 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 "Tralalabs/TralaLabs-16M-Base" \
    --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": "Tralalabs/TralaLabs-16M-Base",
		"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 "Tralalabs/TralaLabs-16M-Base" \
        --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": "Tralalabs/TralaLabs-16M-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tralalabs/TralaLabs-16M-Base with Docker Model Runner:
```
docker model run hf.co/Tralalabs/TralaLabs-16M-Base
```

title

by cerealpotatochipssea - opened 7 days ago

Discussion

cerealpotatochipssea

7 days ago

On god, it really is EVERY single app 😭. The internet is a literal minefield, no platform is safe from the absolute 6️⃣🤷‍♂️7️⃣ brainrot trolls 📉🤡. Whether it's a random Hugging Face model discussion, a Discord server, or a Fandom wiki, some unhinged kid with zero attention span and max 🤡📈 energy always shows up to drop the most toxic stuff imaginable just for a crumb of attention. It's pure 👁️👄👁️ behavior, honestly. It is always the same cycle: Community is just chilling, talking about code or lore 🗿 A wild troll appears and drops absolute radioactive waste 🚩🏃💨 Everyone else is left in pure 🫠 cringe/horror while the mods scramble to pull out the ban hammer 💀🔥 The internet really makes you use the 🤠😭 emoji 24/7. At this point, having your safety filters on max is the only way to keep your soul polished and protected 🧿✨. You just gotta let them crash out in their own filth while we keep moving forward 😭✌️.

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