Instructions to use FINGU-AI/Ultimos-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINGU-AI/Ultimos-32B with Transformers:

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

pipe = pipeline("text-generation", model="FINGU-AI/Ultimos-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FINGU-AI/Ultimos-32B")
model = AutoModelForCausalLM.from_pretrained("FINGU-AI/Ultimos-32B")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FINGU-AI/Ultimos-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINGU-AI/Ultimos-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FINGU-AI/Ultimos-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINGU-AI/Ultimos-32B

SGLang

How to use FINGU-AI/Ultimos-32B 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 "FINGU-AI/Ultimos-32B" \
    --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": "FINGU-AI/Ultimos-32B",
		"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 "FINGU-AI/Ultimos-32B" \
        --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": "FINGU-AI/Ultimos-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINGU-AI/Ultimos-32B with Docker Model Runner:
```
docker model run hf.co/FINGU-AI/Ultimos-32B
```

FINGU-AI commited on Feb 10, 2025

Commit

7bd9c64

verified ·

1 Parent(s): ad5d7e2

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -9,10 +9,10 @@ license: mit
 ---
 ## **Training & Fine-Tuning**
-RombUltima-32B is based on a **linear merge** of its parent models using equal weighting (0.5 each), resulting in a **balanced fusion** that leverages both structured knowledge from Rombos and enhanced generalization from Ultima.
 - **Tokenization Approach:** Uses a **union-based tokenizer** to maximize vocabulary coverage.
-- **Precision:** Trained and fine-tuned in **float16** for efficient inference.
 - **Long-Context Support:** Supports up to **32K tokens** (based on Qwen-32B), with stable generation up to **8K tokens**, depending on hardware constraints.
 - **Multilingual Strength:** Strong performance in **English, French, Chinese, and other global languages**.

 ---
 ## **Training & Fine-Tuning**
+RombUltima-32B is based on a **slerp merge** of its parent models using equal weighting (0.5 each), resulting in a **balanced fusion** that leverages both structured knowledge from Rombos and enhanced generalization from Ultima.
 - **Tokenization Approach:** Uses a **union-based tokenizer** to maximize vocabulary coverage.
+- **Precision:** Trained and fine-tuned in **bfloat16** for efficient inference.
 - **Long-Context Support:** Supports up to **32K tokens** (based on Qwen-32B), with stable generation up to **8K tokens**, depending on hardware constraints.
 - **Multilingual Strength:** Strong performance in **English, French, Chinese, and other global languages**.