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
|
@@ -27,8 +27,6 @@ tags:
|
|
| 27 |
|
| 28 |
## 🏆 Benchmarks
|
| 29 |
|
| 30 |
-
### Benchmark Table
|
| 31 |
-
|
| 32 |
| Benchmark | Supra-50M *(ours)* | GPT-2 (124M) | SmolLM-135M | OpenELM-270M |
|
| 33 |
| :--- | :--- | :--- | :--- | :--- |
|
| 34 |
| **Parameters** | **50M** | 124M *(2.5×)* | 135M *(2.7×)* | 270M *(5.4×)* |
|
|
|
|
| 27 |
|
| 28 |
## 🏆 Benchmarks
|
| 29 |
|
|
|
|
|
|
|
| 30 |
| Benchmark | Supra-50M *(ours)* | GPT-2 (124M) | SmolLM-135M | OpenELM-270M |
|
| 31 |
| :--- | :--- | :--- | :--- | :--- |
|
| 32 |
| **Parameters** | **50M** | 124M *(2.5×)* | 135M *(2.7×)* | 270M *(5.4×)* |
|