Instructions to use AxiomicLabs/GPT-S2-5M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AxiomicLabs/GPT-S2-5M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AxiomicLabs/GPT-S2-5M", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("AxiomicLabs/GPT-S2-5M", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AxiomicLabs/GPT-S2-5M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AxiomicLabs/GPT-S2-5M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AxiomicLabs/GPT-S2-5M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AxiomicLabs/GPT-S2-5M
- SGLang
How to use AxiomicLabs/GPT-S2-5M 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 "AxiomicLabs/GPT-S2-5M" \ --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": "AxiomicLabs/GPT-S2-5M", "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 "AxiomicLabs/GPT-S2-5M" \ --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": "AxiomicLabs/GPT-S2-5M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AxiomicLabs/GPT-S2-5M with Docker Model Runner:
docker model run hf.co/AxiomicLabs/GPT-S2-5M
hey model idea
train ai on ai weights so you can make ais without training big brain
Be GONE Tralalabs, I cast thee out
Be GONE Tralalabs, I cast thee out
im not tralalabs if u cant make basic model then say ur bad at ai
Be GONE Tralalabs, I cast thee out
im not tralalabs if u cant make basic model then say ur bad at ai
I said OUT TRALALABS, begone!
Be GONE Tralalabs, I cast thee out
im not tralalabs if u cant make basic model then say ur bad at ai
I said OUT TRALALABS, begone!
I am tralalabs and my models suck balls
Damn bruh atleast you admit it
Damn bruh atleast you admit it
Im a silly little man and I admit defeat
Good to hear bro
Damn bruh atleast you admit it
Im a silly little man and I admit defeat
Finally he admitted! Good boy!
I'm a silly little man and I admit defeat.
ohhhhh, have some ego, do some benchmarks, push yourself, it raises the overall AI level (well... ;p, I'm kidding! but don't put yourself down like that, you just need to be respectful, that's all. After that, don't give up either (even if you take some losses lol ;)
Create a new organization (I'd call it Drixpy), not as a reference to SupraLabs, and let's have a respectful war.
SupraLabs VS Drixpy VS OpenAI Community VS WhirlwindAI