Instructions to use ai21labs/Jamba-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ai21labs/Jamba-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="ai21labs/Jamba-tiny-random")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ai21labs/Jamba-tiny-random")
model = AutoModelForCausalLM.from_pretrained("ai21labs/Jamba-tiny-random")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ai21labs/Jamba-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ai21labs/Jamba-tiny-random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai21labs/Jamba-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ai21labs/Jamba-tiny-random

SGLang

How to use ai21labs/Jamba-tiny-random 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 "ai21labs/Jamba-tiny-random" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai21labs/Jamba-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ai21labs/Jamba-tiny-random" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai21labs/Jamba-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ai21labs/Jamba-tiny-random with Docker Model Runner:
```
docker model run hf.co/ai21labs/Jamba-tiny-random
```

This is a tiny, dummy version of Jamba, used for debugging and experimentation over the Jamba architecture.

It has 128M parameters (instead of 52B), and is initialized with random weights and did not undergo any training.

Downloads last month: 9,551

Safetensors

Model size

0.1B params

Tensor type

BF16