Instructions to use lilyanatia/Bonsai-8B-requantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use lilyanatia/Bonsai-8B-requantized with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lilyanatia/Bonsai-8B-requantized:IQ1_S
# Run inference directly in the terminal:
llama cli -hf lilyanatia/Bonsai-8B-requantized:IQ1_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lilyanatia/Bonsai-8B-requantized:IQ1_S
# Run inference directly in the terminal:
llama cli -hf lilyanatia/Bonsai-8B-requantized:IQ1_S

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 lilyanatia/Bonsai-8B-requantized:IQ1_S
# Run inference directly in the terminal:
./llama-cli -hf lilyanatia/Bonsai-8B-requantized:IQ1_S

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 lilyanatia/Bonsai-8B-requantized:IQ1_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lilyanatia/Bonsai-8B-requantized:IQ1_S

Use Docker

docker model run hf.co/lilyanatia/Bonsai-8B-requantized:IQ1_S

LM Studio
Jan
Ollama
How to use lilyanatia/Bonsai-8B-requantized with Ollama:
```
ollama run hf.co/lilyanatia/Bonsai-8B-requantized:IQ1_S
```
Unsloth Desktop

How to use lilyanatia/Bonsai-8B-requantized with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lilyanatia/Bonsai-8B-requantized:IQ1_S

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "lilyanatia/Bonsai-8B-requantized:IQ1_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use lilyanatia/Bonsai-8B-requantized with Docker Model Runner:
```
docker model run hf.co/lilyanatia/Bonsai-8B-requantized:IQ1_S
```

Lemonade

How to use lilyanatia/Bonsai-8B-requantized with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lilyanatia/Bonsai-8B-requantized:IQ1_S

Run and chat with the model

lemonade run user.Bonsai-8B-requantized-IQ1_S

List all available models

lemonade list

Hermes Agent

How to use lilyanatia/Bonsai-8B-requantized with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lilyanatia/Bonsai-8B-requantized:IQ1_S

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default lilyanatia/Bonsai-8B-requantized:IQ1_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use lilyanatia/Bonsai-8B-requantized with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lilyanatia/Bonsai-8B-requantized:IQ1_S

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "lilyanatia/Bonsai-8B-requantized:IQ1_S" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

lilyanatia commited on Apr 2

Commit

548839f

verified ·

1 Parent(s): 6886562

Upload folder using huggingface_hub

Browse files

Files changed (7) hide show

.gitattributes +5 -0
Bonsai-8B-IQ1_S.gguf +3 -0
Bonsai-8B-Q2_K.gguf +3 -0
Bonsai-8B-TQ1_0.gguf +3 -0
Bonsai-8B-TQ2_0.gguf +3 -0
README.md +7 -0
imatrix.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Bonsai-8B-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Bonsai-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Bonsai-8B-TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text
+Bonsai-8B-TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text
+imatrix.gguf filter=lfs diff=lfs merge=lfs -text

Bonsai-8B-IQ1_S.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d96fae7612cc0f7eaa2ce2b5e6dff48e77d5b914d7ff9f6dbff201cf946360
+size 1891395872

Bonsai-8B-Q2_K.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:065ec98ec65d54967836142d8f4b008bf2a93d777ce8d5d8e3e3cd397b6f15e3
+size 2974705952

Bonsai-8B-TQ1_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2df33ceb893266b0c44e7e6aecafcda63a157e4230d56a424ac4d5c873b7d5da
+size 1734390368

Bonsai-8B-TQ2_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:11ab2c9e64e1e7e13669a8d7fd7f164576c25bdc2c8df8de6ef7593de060b048
+size 2118214112

README.md ADDED Viewed

	@@ -0,0 +1,7 @@

+---
+base_model: prism-ml/Bonsai-8B-gguf
+library_name: llama.cpp
+quantized_by: lilyanatia
+---
+requantized [Bonsai-8B](https://huggingface.co/prism-ml/Bonsai-8B-gguf) for software that doesn't support Q1\_0\_g128 quantization.
+<!-- end -->

imatrix.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c4423f7979c32a1632ac982cb97f9e04b46e6ec7f47c05c088eba2243c3ebfb2
+size 5347200