Instructions to use SupraLabs/Supra-Mini-0.1M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SupraLabs/Supra-Mini-0.1M with Transformers:

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

pipe = pipeline("text-generation", model="SupraLabs/Supra-Mini-0.1M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SupraLabs/Supra-Mini-0.1M")
model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra-Mini-0.1M")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SupraLabs/Supra-Mini-0.1M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SupraLabs/Supra-Mini-0.1M"
# 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-0.1M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SupraLabs/Supra-Mini-0.1M

SGLang

How to use SupraLabs/Supra-Mini-0.1M 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-0.1M" \
    --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-0.1M",
		"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-0.1M" \
        --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-0.1M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SupraLabs/Supra-Mini-0.1M with Docker Model Runner:
```
docker model run hf.co/SupraLabs/Supra-Mini-0.1M
```

Harley-ml commited on 6 days ago

Commit

08a6bea

verified ·

1 Parent(s): 71c55a8

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -1

README.md CHANGED Viewed

@@ -48,7 +48,7 @@ new_version: SupraLabs/Supra-Mini-v4-2M
 ---
 # 🦅 Supra Mini 0.1M
-Supra Mini 0.1M is a very tiny base model trained on 500 million tokens of Fineweb-Edu for 2 epochs to prove how well very tiny models can perform on world knowledge.
 ## Model Config
@@ -120,6 +120,18 @@ print("-" * 30)
 print("\nOutput:\n" + generate_text(test_prompt))
 ```
 ## Training guide
 We trained Supra Mini 0.1M on a single T4 GPU in ~45 minutes 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 250), `train.py` (train the model) and `inference.py` (test the model).<br>

 ---
 # 🦅 Supra Mini 0.1M
+Supra Mini 0.1M is a very small, yes, very small base model trained on 500 million tokens of Fineweb-Edu for 2 epochs to prove how well very tiny models can perform on world knowledge.
 ## Model Config
 print("\nOutput:\n" + generate_text(test_prompt))
 ```
+## Use cases
+1. Educational research
+2. deployment or testing/fine-tuning on edge environments
+3. Or more simply, for fun
+## Limitations
+1. Cannot reason, chat, or code
+2. Incoherent more often than not
+3. Mostly unfactual
 ## Training guide
 We trained Supra Mini 0.1M on a single T4 GPU in ~45 minutes 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 250), `train.py` (train the model) and `inference.py` (test the model).<br>