Instructions to use Aryanne/Astrea-RP-v1-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aryanne/Astrea-RP-v1-4B with Transformers:

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

pipe = pipeline("text-generation", model="Aryanne/Astrea-RP-v1-4B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Aryanne/Astrea-RP-v1-4B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Aryanne/Astrea-RP-v1-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aryanne/Astrea-RP-v1-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aryanne/Astrea-RP-v1-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Aryanne/Astrea-RP-v1-4B

SGLang

How to use Aryanne/Astrea-RP-v1-4B 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 "Aryanne/Astrea-RP-v1-4B" \
    --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": "Aryanne/Astrea-RP-v1-4B",
		"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 "Aryanne/Astrea-RP-v1-4B" \
        --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": "Aryanne/Astrea-RP-v1-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Aryanne/Astrea-RP-v1-4B with Docker Model Runner:
```
docker model run hf.co/Aryanne/Astrea-RP-v1-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Will probably merge it with more models in the future.

Merged

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:

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 10]
    model: Aryanne/Astrea-RP-v1.5-3B
- sources:
  - layer_range: [10, 14]
    model: jeiku/Refined_3B
- sources:
  - layer_range: [7, 14]
    model: Aryanne/Astrea-RP-v1-3B
- sources:
  - layer_range: [13, 19]
    model: jeiku/Refined_3B
- sources:
  - layer_range: [18, 25]
    model: Aryanne/Astrea-RP-v1-3B
- sources:
  - layer_range: [18, 22]
    model: jeiku/Refined_3B
- sources:
  - layer_range: [22, 32]
    model: Aryanne/Astrea-RP-v1.5-3B