Instructions to use SupraLabs/Supra1.5-50M-Base-exp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SupraLabs/Supra1.5-50M-Base-exp with Transformers:

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

pipe = pipeline("text-generation", model="SupraLabs/Supra1.5-50M-Base-exp")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SupraLabs/Supra1.5-50M-Base-exp")
model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra1.5-50M-Base-exp", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SupraLabs/Supra1.5-50M-Base-exp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SupraLabs/Supra1.5-50M-Base-exp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/Supra1.5-50M-Base-exp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SupraLabs/Supra1.5-50M-Base-exp

SGLang

How to use SupraLabs/Supra1.5-50M-Base-exp 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/Supra1.5-50M-Base-exp" \
    --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/Supra1.5-50M-Base-exp",
		"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/Supra1.5-50M-Base-exp" \
        --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/Supra1.5-50M-Base-exp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SupraLabs/Supra1.5-50M-Base-exp with Docker Model Runner:
```
docker model run hf.co/SupraLabs/Supra1.5-50M-Base-exp
```

Supra1.5-50M-Base-exp / README.md

LH-Tech-AI

Update README.md

297d305 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

1.79 kB

metadata

license: apache-2.0
language:
  - en
pipeline_tag: text-generation
library_name: transformers
tags:
  - supra
  - supra-1.5
  - llama
  - 50m
  - base
  - continued-pretraining
  - long-context
  - 5k-context
  - Supra
  - Supra-50M

Supra1.5-50M Base

Continued Pretraining • 50M Parameters • 5K Context

Supra-1.5-50M-Base-exp is a continued-pretrained 50M parameter Llama-style base model derived from SupraLabs/Supra-50M-Base. The target update expands the usable context window from 1,024 tokens to 5,120 tokens using RoPE scaling and full-weight continued pretraining.

Architecture

The model keeps the original Supra-50M architecture and tokenizer:

Specification	Value
Architecture	`LlamaForCausalLM`
Parameters	~50M
Vocabulary Size	32,000
Hidden Size	512
Layers	12
Attention Heads	8
KV Heads	4
Context Length	5,120 tokens
Tokenizer	Original Supra byte-level BPE tokenizer

Continued Pretraining Objective

This is CPT, not instruction fine-tuning. Training uses packed raw text with standard causal language-modeling loss:

labels = input_ids
all non-pad tokens are trained
no response-only masking
no system/user/assistant masking
no LoRA adapters in the default run

Data Mix

The current local training mix prepared for this run is:

3,000,000,062 CPT tokens
- 30% Tool Calling
- 30% ChatML Conversations
- 25% Factual Text (articles, essays, blogs)
- 15% Math & Logic Questions

Intended Use

Supervised Fine-Tuning (SFT) and Reinforcement Learning

Credit goes to @QyrouNnet-AI