Instructions to use Sakalti/ultiima-108B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sakalti/ultiima-108B with Transformers:

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

pipe = pipeline("text-generation", model="Sakalti/ultiima-108B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Sakalti/ultiima-108B")
model = AutoModelForMultimodalLM.from_pretrained("Sakalti/ultiima-108B")
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 Settings

vLLM

How to use Sakalti/ultiima-108B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sakalti/ultiima-108B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sakalti/ultiima-108B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sakalti/ultiima-108B

SGLang

How to use Sakalti/ultiima-108B 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 "Sakalti/ultiima-108B" \
    --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": "Sakalti/ultiima-108B",
		"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 "Sakalti/ultiima-108B" \
        --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": "Sakalti/ultiima-108B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sakalti/ultiima-108B with Docker Model Runner:
```
docker model run hf.co/Sakalti/ultiima-108B
```

ultiima-108B / README.md

Sakalti

Update README.md

efc05ca verified over 1 year ago

preview code

raw

history blame contribute delete

923 Bytes

metadata

base_model:
  - Sakalti/ultiima-72B
library_name: transformers
tags:
  - mergekit
  - merge
license: other
license_name: qwen
license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE

Built With Qwen

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Sakalti/ultiima-72B

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - layer_range: [0, 40]
    model: Sakalti/ultiima-72B
- sources:
  - layer_range: [20, 60]
    model: Sakalti/ultiima-72B
- sources:
  - layer_range: [40, 80]
    model: Sakalti/ultiima-72B
dtype: float16
merge_method: passthrough