Instructions to use Severian/Jamba-UltraInteract-Instruct-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Severian/Jamba-UltraInteract-Instruct-1B with Transformers:

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

pipe = pipeline("text-generation", model="Severian/Jamba-UltraInteract-Instruct-1B", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Severian/Jamba-UltraInteract-Instruct-1B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Severian/Jamba-UltraInteract-Instruct-1B", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Severian/Jamba-UltraInteract-Instruct-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Severian/Jamba-UltraInteract-Instruct-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Severian/Jamba-UltraInteract-Instruct-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Severian/Jamba-UltraInteract-Instruct-1B

SGLang

How to use Severian/Jamba-UltraInteract-Instruct-1B 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 "Severian/Jamba-UltraInteract-Instruct-1B" \
    --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": "Severian/Jamba-UltraInteract-Instruct-1B",
		"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 "Severian/Jamba-UltraInteract-Instruct-1B" \
        --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": "Severian/Jamba-UltraInteract-Instruct-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Severian/Jamba-UltraInteract-Instruct-1B with Docker Model Runner:
```
docker model run hf.co/Severian/Jamba-UltraInteract-Instruct-1B
```

This Jamba model has been pruned to just 1B parameters. It was then trained on the first 50k examples of the Ultra Interact Pair dataset for Instruction based fine-tuning.

Initial tests work but may be inconsistent. More info and examples will be posted later

Training

50k Examples
6 hours x A100

Downloads last month: 13

Safetensors

Model size

1B params

Tensor type

F32

Model tree for Severian/Jamba-UltraInteract-Instruct-1B

Base model

ai21labs/Jamba-v0.1

Finetuned

(5)

this model

Dataset used to train Severian/Jamba-UltraInteract-Instruct-1B

Collection including Severian/Jamba-UltraInteract-Instruct-1B

Jamba Models

Collection

Experimentations with the new SSM-Transformers Jamba • 4 items • Updated Apr 9, 2024 • 1