Instructions to use arcee-ai/raspberry-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/raspberry-3B with Transformers:

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

pipe = pipeline("text-generation", model="arcee-ai/raspberry-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arcee-ai/raspberry-3B")
model = AutoModelForCausalLM.from_pretrained("arcee-ai/raspberry-3B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use arcee-ai/raspberry-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arcee-ai/raspberry-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/raspberry-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arcee-ai/raspberry-3B

SGLang

How to use arcee-ai/raspberry-3B 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 "arcee-ai/raspberry-3B" \
    --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": "arcee-ai/raspberry-3B",
		"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 "arcee-ai/raspberry-3B" \
        --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": "arcee-ai/raspberry-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use arcee-ai/raspberry-3B with Docker Model Runner:
```
docker model run hf.co/arcee-ai/raspberry-3B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Prompt Format: ChatML

This is an experimental which was heavily optimized for reasoning tasks and not meant for production-use.

GGUFs: https://huggingface.co/mradermacher/raspberry-3B-GGUF

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	15.40
IFEval (0-Shot)	31.54
BBH (3-Shot)	19.53
MATH Lvl 5 (4-Shot)	7.63
GPQA (0-shot)	3.69
MuSR (0-shot)	9.41
MMLU-PRO (5-shot)	20.60

Downloads last month: 39

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for arcee-ai/raspberry-3B

Base model

Qwen/Qwen2.5-3B

Finetuned

(392)

this model

Merges

3 models

Quantizations

4 models

arcee-ai
/

raspberry-3B

Open LLM Leaderboard Evaluation Results

Model tree for arcee-ai/raspberry-3B

Space using arcee-ai/raspberry-3B 1