Instructions to use SupraLabs/Supra-50M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SupraLabs/Supra-50M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="SupraLabs/Supra-50M-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SupraLabs/Supra-50M-Instruct")
model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra-50M-Instruct")

llama-cpp-python

How to use SupraLabs/Supra-50M-Instruct with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SupraLabs/Supra-50M-Instruct",
	filename="supra-50m-instruct-f16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use SupraLabs/Supra-50M-Instruct with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SupraLabs/Supra-50M-Instruct:F16
# Run inference directly in the terminal:
llama-cli -hf SupraLabs/Supra-50M-Instruct:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SupraLabs/Supra-50M-Instruct:F16
# Run inference directly in the terminal:
llama-cli -hf SupraLabs/Supra-50M-Instruct:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf SupraLabs/Supra-50M-Instruct:F16
# Run inference directly in the terminal:
./llama-cli -hf SupraLabs/Supra-50M-Instruct:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf SupraLabs/Supra-50M-Instruct:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SupraLabs/Supra-50M-Instruct:F16

Use Docker

docker model run hf.co/SupraLabs/Supra-50M-Instruct:F16

LM Studio
Jan

vLLM

How to use SupraLabs/Supra-50M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SupraLabs/Supra-50M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/Supra-50M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SupraLabs/Supra-50M-Instruct:F16

SGLang

How to use SupraLabs/Supra-50M-Instruct 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-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/Supra-50M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SupraLabs/Supra-50M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use SupraLabs/Supra-50M-Instruct with Ollama:
```
ollama run hf.co/SupraLabs/Supra-50M-Instruct:F16
```

Unsloth Studio new

How to use SupraLabs/Supra-50M-Instruct with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SupraLabs/Supra-50M-Instruct to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SupraLabs/Supra-50M-Instruct to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SupraLabs/Supra-50M-Instruct to start chatting

Docker Model Runner
How to use SupraLabs/Supra-50M-Instruct with Docker Model Runner:
```
docker model run hf.co/SupraLabs/Supra-50M-Instruct:F16
```

Lemonade

How to use SupraLabs/Supra-50M-Instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SupraLabs/Supra-50M-Instruct:F16

Run and chat with the model

lemonade run user.Supra-50M-Instruct-F16

List all available models

lemonade list

AxionLab-official commited on 2 days ago

Commit

7fda93e

verified ·

1 Parent(s): a02d332

Update README.md

Browse files

Files changed (1) hide show

README.md +32 -1

README.md CHANGED Viewed

@@ -132,6 +132,15 @@ if __name__ == "__main__":
 ## 💬 Sample Outputs
 **User:** What is AI?<br>
 **Supra-50M Instruct:**:<br>
 AI refers to the simulation of human intelligence and creativity in machines, which are designed to mimic or surpass human cognition and reasoning. It is the process by which AI systems can solve problems, make predictions, or automate processes that typically require human-level thinking and problem solving. AI technology has been rapidly growing and evolving over time, with many potential benefits for society as a whole. Some of these include:
@@ -141,7 +150,29 @@ AI refers to the simulation of human intelligence and creativity in machines, wh
 <br>
-See samples.txt for more!
 ---

 ## 💬 Sample Outputs
+**This outputs was generated with this samplings:
+<code>temperature=0.7<code>
+<code>top_k=50<code>
+<code>top_p=0.9<code>
+<code>repetition_penalty=1.15<code>**
+(The model still hallucinates, but can respond a big quantity of questions correctly)
 **User:** What is AI?<br>
 **Supra-50M Instruct:**:<br>
 AI refers to the simulation of human intelligence and creativity in machines, which are designed to mimic or surpass human cognition and reasoning. It is the process by which AI systems can solve problems, make predictions, or automate processes that typically require human-level thinking and problem solving. AI technology has been rapidly growing and evolving over time, with many potential benefits for society as a whole. Some of these include:
 <br>
+**User:** What is the capital of Japan?<br>
+**Supra-50M Instruct:**:<br>
+The capital of Japan is Tokyo.
+<br>
+**User:** Hi!<br>
+**Supra-50M Instruct:**:<br>
+Hello! How can i help you today?
+<br>
+**User:** What is the capital of United States?<br>
+**Supra-50M Instruct:**:<br>
+The capital of United States is New York City.
+<br>
+**User:** What is the capital of Russia?<br>
+**Supra-50M Instruct:**:<br>
+The capital of Russia is Moscow.
+<br>
 ---