Instructions to use SupraLabs/Supra2.1-Ultra with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SupraLabs/Supra2.1-Ultra with Transformers:

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

pipe = pipeline("text-generation", model="SupraLabs/Supra2.1-Ultra")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SupraLabs/Supra2.1-Ultra")
model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra2.1-Ultra", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SupraLabs/Supra2.1-Ultra with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SupraLabs/Supra2.1-Ultra"
# 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/Supra2.1-Ultra",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SupraLabs/Supra2.1-Ultra

SGLang

How to use SupraLabs/Supra2.1-Ultra 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/Supra2.1-Ultra" \
    --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/Supra2.1-Ultra",
		"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/Supra2.1-Ultra" \
        --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/Supra2.1-Ultra",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SupraLabs/Supra2.1-Ultra with Docker Model Runner:
```
docker model run hf.co/SupraLabs/Supra2.1-Ultra
```

AxionLab-official commited on 15 days ago

Commit

9970da4

verified ·

1 Parent(s): 704a865

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ library_name: transformers
 ### Supra2.5-Ultra-Preview-001
-Supra2.5-Ultra-Preview-001 is the first preview model for the Supra2.5-Ultra family. It has 230M params, 40B tokens trained on, with LLaMa arch. It is an next-token prediction model. Don't expect chat capabilities.
 ### Config
@@ -44,6 +44,8 @@ This model was trained on a single A100 SXM.
 | ARC-Easy      | 0     | **56.80** | 51.10 | 25.0   |
 | ARC-Challenge | 0     | 25.20 | **25.90** | 25.0   |
 ### How to use
 ```python

 ### Supra2.5-Ultra-Preview-001
+Supra2.5-Ultra-Preview-001 is the first preview model for the Supra2.5-Ultra family. It has 230M params, 40B tokens trained on, with LLaMa arch. It is a small base model that may generate incorrect or biased text, and it has neither been aligned nor evaluated for safety.
 ### Config
 | ARC-Easy      | 0     | **56.80** | 51.10 | 25.0   |
 | ARC-Challenge | 0     | 25.20 | **25.90** | 25.0   |
+*Evaluated with lm-evaluation-harness, first 1,000 examples per task (--limit 1000). Standard error is about ±1.5 points. Full test-set evaluation planned for the second preview release.*
 ### How to use
 ```python