Text Generation
Transformers
Safetensors
English
llama
supra
chimera
50m
small
open
open-source
cpu
tiny
slm
text-generation-inference
Instructions to use SupraLabs/Supra-50M-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SupraLabs/Supra-50M-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SupraLabs/Supra-50M-Base")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SupraLabs/Supra-50M-Base") model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra-50M-Base") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use SupraLabs/Supra-50M-Base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SupraLabs/Supra-50M-Base" # 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-50M-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SupraLabs/Supra-50M-Base
- SGLang
How to use SupraLabs/Supra-50M-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 "SupraLabs/Supra-50M-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": "SupraLabs/Supra-50M-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 "SupraLabs/Supra-50M-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": "SupraLabs/Supra-50M-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SupraLabs/Supra-50M-Base with Docker Model Runner:
docker model run hf.co/SupraLabs/Supra-50M-Base
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ tags:
|
|
| 21 |
|
| 22 |
# 🦅 Supra-50M
|
| 23 |
|
| 24 |
-
**Supra-50M** is a compact 50M-parameter causal language model built by SupraLabs, trained from scratch using a Llama-style architecture on 20 billion tokens of high-quality educational web text. Despite being significantly smaller than comparable open models, it achieves competitive or superior results on several key benchmarks.
|
| 25 |
|
| 26 |
---
|
| 27 |
|
|
|
|
| 21 |
|
| 22 |
# 🦅 Supra-50M
|
| 23 |
|
| 24 |
+
**Supra-50M** is a compact 50M-parameter causal language model built by SupraLabs, trained from scratch using a Llama-style architecture on 20 billion tokens of high-quality educational web text. Despite being significantly smaller than comparable open models, it achieves competitive or superior results on several key benchmarks. It is our first Supra Scalling Up plan model.
|
| 25 |
|
| 26 |
---
|
| 27 |
|