Instructions to use jeiku/Rosa_v1_3.43B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jeiku/Rosa_v1_3.43B with Transformers:

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

pipe = pipeline("text-generation", model="jeiku/Rosa_v1_3.43B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("jeiku/Rosa_v1_3.43B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jeiku/Rosa_v1_3.43B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jeiku/Rosa_v1_3.43B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jeiku/Rosa_v1_3.43B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jeiku/Rosa_v1_3.43B

SGLang

How to use jeiku/Rosa_v1_3.43B 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 "jeiku/Rosa_v1_3.43B" \
    --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": "jeiku/Rosa_v1_3.43B",
		"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 "jeiku/Rosa_v1_3.43B" \
        --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": "jeiku/Rosa_v1_3.43B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jeiku/Rosa_v1_3.43B with Docker Model Runner:
```
docker model run hf.co/jeiku/Rosa_v1_3.43B
```

Check merge.yml for more information on the creation of this model.

This model, much like Damascus steel, includes layers of high quality merges, extended out to 40 overall layers spread over 3 merged models which include at least 4 models each. This model includes som essay writing components, som medical components, a small amount of RAG processing components and many roleplaying and conversational components.

I have tested this model, and it has proven interesting enough to be the daily driver for my mobile device.

GGUF available here: https://huggingface.co/jeiku/Rosa_v1_3.34B_GGUF

Downloads last month: 7

Safetensors

Model size

3B params

Tensor type

F16