Instructions to use sinatras/bonsai-8b-split with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sinatras/bonsai-8b-split with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sinatras/bonsai-8b-split",
	filename="Q2_K/Bonsai-8B-Q2_K-00001-of-00002.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 sinatras/bonsai-8b-split with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sinatras/bonsai-8b-split:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf sinatras/bonsai-8b-split:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sinatras/bonsai-8b-split:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf sinatras/bonsai-8b-split:Q4_K_M

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 sinatras/bonsai-8b-split:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sinatras/bonsai-8b-split:Q4_K_M

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 sinatras/bonsai-8b-split:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sinatras/bonsai-8b-split:Q4_K_M

Use Docker

docker model run hf.co/sinatras/bonsai-8b-split:Q4_K_M

LM Studio
Jan
Ollama
How to use sinatras/bonsai-8b-split with Ollama:
```
ollama run hf.co/sinatras/bonsai-8b-split:Q4_K_M
```

Unsloth Studio new

How to use sinatras/bonsai-8b-split 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 sinatras/bonsai-8b-split 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 sinatras/bonsai-8b-split to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sinatras/bonsai-8b-split to start chatting

Docker Model Runner
How to use sinatras/bonsai-8b-split with Docker Model Runner:
```
docker model run hf.co/sinatras/bonsai-8b-split:Q4_K_M
```

Lemonade

How to use sinatras/bonsai-8b-split with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sinatras/bonsai-8b-split:Q4_K_M

Run and chat with the model

lemonade run user.bonsai-8b-split-Q4_K_M

List all available models

lemonade list

sinatras commited on 18 days ago

Commit

5395db6

verified ·

1 Parent(s): dc82cf1

Add files using upload-large-folder tool

Browse files

Files changed (1) hide show

README.md +24 -0

README.md ADDED Viewed

	@@ -0,0 +1,24 @@

+---
+license: apache-2.0
+base_model: prism-ml/Bonsai-8B-unpacked
+tags:
+- gguf
+- wllama
+- browser
+---
+# bonsai-8b-split
+Bonsai 8B split GGUF artifacts converted for the playground wllama preset.
+These files are the GGUF artifacts used by the local Transformers.js playground
+wllama CPU presets. Large files are kept under quantization subdirectories so
+browser clients can request the first shard URL and expand the remaining shards.
+## Source And License
+- Source model/artifact: [prism-ml/Bonsai-8B-unpacked](https://huggingface.co/prism-ml/Bonsai-8B-unpacked)
+- License: Apache-2.0, inherited from the source model/artifact.
+The GGUF conversion, quantization, and splitting steps do not change the
+upstream model license.