Instructions to use SupraLabs/Supra-Mini-v3-0.5M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SupraLabs/Supra-Mini-v3-0.5M with Transformers:

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

pipe = pipeline("text-generation", model="SupraLabs/Supra-Mini-v3-0.5M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SupraLabs/Supra-Mini-v3-0.5M")
model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra-Mini-v3-0.5M")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SupraLabs/Supra-Mini-v3-0.5M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SupraLabs/Supra-Mini-v3-0.5M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/Supra-Mini-v3-0.5M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SupraLabs/Supra-Mini-v3-0.5M

SGLang

How to use SupraLabs/Supra-Mini-v3-0.5M 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 "SupraLabs/Supra-Mini-v3-0.5M" \
    --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": "SupraLabs/Supra-Mini-v3-0.5M",
		"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 "SupraLabs/Supra-Mini-v3-0.5M" \
        --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": "SupraLabs/Supra-Mini-v3-0.5M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SupraLabs/Supra-Mini-v3-0.5M with Docker Model Runner:
```
docker model run hf.co/SupraLabs/Supra-Mini-v3-0.5M
```

LH-Tech-AI commited on 10 days ago

Commit

8f95b93

verified ·

1 Parent(s): aedb965

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -102,5 +102,5 @@ print("\nOutput:\n" + generate_text(test_prompt))
 ## Training guide
 We trained Supra Mini v3 0.5M on a single NVIDIA RTX 5060 Ti 16GB in ~1 hour for 2 epochs.<br>
-The full training code can be found in this repo as `run.sh` (easily run the complete pipeline), `train_tokenizer.py` (train costum BPE tokenizer with vocab size of 2048), `train.py` (train the model) and `inference.py` (test the model).<br>
 The model was trained on the first 1 billion tokens of Sample-10BT from Fineweb-Edu using streaming tokenization.

 ## Training guide
 We trained Supra Mini v3 0.5M on a single NVIDIA RTX 5060 Ti 16GB in ~1 hour for 2 epochs.<br>
+The full training code can be found in this repo as `train_tokenizer.py` (train costum BPE tokenizer with vocab size of 4096), `train.py` (train the model) and `inference.py` (test the model).<br>
 The model was trained on the first 1 billion tokens of Sample-10BT from Fineweb-Edu using streaming tokenization.