Instructions to use arcee-ai/teeny-tiny-mixtral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/teeny-tiny-mixtral with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arcee-ai/teeny-tiny-mixtral")
model = AutoModelForCausalLM.from_pretrained("arcee-ai/teeny-tiny-mixtral")
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 arcee-ai/teeny-tiny-mixtral with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arcee-ai/teeny-tiny-mixtral"
# 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/teeny-tiny-mixtral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arcee-ai/teeny-tiny-mixtral

SGLang

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

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

Model Card for Model ID

This model is a dummy model created for testing purposes only. It utilizes a custom configuration to explore various training scenarios and should not be used for production.

Configuration Highlights

The configuration of this dummy model is distinct from the original model in several key aspects:

Number of Layers: Reduced to 2, allowing for quicker tests of layer-specific behaviors.
Experts: Configured with 4 local experts and 2 experts per token, experimenting with the model's capacity to handle multiple expert inputs.
Hidden Size: Set at 512, this smaller size is suitable for testing the impact of network width.
Intermediate Size: Enlarged to 3579, to investigate how an increase in the size affects the model's ability to process information deeply.

Downloads last month: 299

Safetensors

Model size

78.1M params

Tensor type

F32

Model tree for arcee-ai/teeny-tiny-mixtral

Quantizations

2 models