Instructions to use Severian/Jamba-900M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Severian/Jamba-900M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Severian/Jamba-900M-GGUF",
	filename="jamba-900M.bf16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Severian/Jamba-900M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Severian/Jamba-900M-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf Severian/Jamba-900M-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Severian/Jamba-900M-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf Severian/Jamba-900M-GGUF:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Severian/Jamba-900M-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf Severian/Jamba-900M-GGUF:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Severian/Jamba-900M-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Severian/Jamba-900M-GGUF:BF16

Use Docker

docker model run hf.co/Severian/Jamba-900M-GGUF:BF16

LM Studio
Jan
Ollama
How to use Severian/Jamba-900M-GGUF with Ollama:
```
ollama run hf.co/Severian/Jamba-900M-GGUF:BF16
```

Unsloth Studio new

How to use Severian/Jamba-900M-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Severian/Jamba-900M-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Severian/Jamba-900M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Severian/Jamba-900M-GGUF to start chatting

Docker Model Runner
How to use Severian/Jamba-900M-GGUF with Docker Model Runner:
```
docker model run hf.co/Severian/Jamba-900M-GGUF:BF16
```

Lemonade

How to use Severian/Jamba-900M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Severian/Jamba-900M-GGUF:BF16

Run and chat with the model

lemonade run user.Jamba-900M-GGUF-BF16

List all available models

lemonade list

Jamba 900M GGUF

This is the first GGUF of the new Jamba architecture recently hacked with llama.cpp using this Repo https://github.com/ggerganov/llama.cpp/tree/compilade/refactor-kv-cache

Model: pszemraj/jamba-900M-v0.13-KIx2

Downloads last month: 15

GGUF

Model size

0.9B params

Architecture

jamba

Hardware compatibility

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including Severian/Jamba-900M-GGUF

Jamba GGUF

Collection

Current GGUF's conversion of the Jamba models. Will be updated as support in llama.cpp merges/ https://github.com/ggerganov/llama.cpp/pull/7531 • 4 items • Updated May 30, 2024 • 2