Instructions to use OxxoCodes/jamba-small-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OxxoCodes/jamba-small-v1 with Transformers:

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

pipe = pipeline("text-generation", model="OxxoCodes/jamba-small-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OxxoCodes/jamba-small-v1")
model = AutoModelForCausalLM.from_pretrained("OxxoCodes/jamba-small-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OxxoCodes/jamba-small-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OxxoCodes/jamba-small-v1

SGLang

How to use OxxoCodes/jamba-small-v1 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 "OxxoCodes/jamba-small-v1" \
    --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": "OxxoCodes/jamba-small-v1",
		"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 "OxxoCodes/jamba-small-v1" \
        --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": "OxxoCodes/jamba-small-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OxxoCodes/jamba-small-v1 with Docker Model Runner:
```
docker model run hf.co/OxxoCodes/jamba-small-v1
```

Jamba-Small v1

This is a pruned version of AI21 Labs' Jamba-v0.1 model that is ~25% the size of Jamba-v0.1.

Model Details

Whereas Jamba-v0.1 contains 4 Jamba blocks, Jamba-Small contains only 1 Jamba block. Jamba-Small's Jamba blocks follow the same structure seen in Jamba-v0.1, with a 1:7 ratio of attention-to-Mamba layers and MoE applied every 2 layers.

Jamba-Small's weights are initialized from various layers in the original Jamba-v0.1 model. For v1, the layer weights are mapped as follows (left is Jamba-Small layer number, right is Jamba-v0.1 layer number):

Note that no additional fine-tuning has been performed on this model. As such, its performance is exceptionally poor. This should not be used in production without additional training.

Model Description

Developed by: Nathan Brown (OxxoCodes)
Compute provided by: Clemson Palmetto Cluster
Model type: Joint Attention and Mamba (Jamba)
Language(s) (NLP): English
License: Apache 2.0
Original model: Jamba-v0.1
Jamba paper: https://arxiv.org/pdf/2403.19887.pdf

Downloads last month: 9

Safetensors

Model size

13B params

Tensor type

F32

Paper for OxxoCodes/jamba-small-v1

Jamba: A Hybrid Transformer-Mamba Language Model

Paper • 2403.19887 • Published Mar 28, 2024 • 113