Instructions to use leeroy-jankins/jimi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use leeroy-jankins/jimi 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 leeroy-jankins/jimi:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf leeroy-jankins/jimi:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf leeroy-jankins/jimi:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf leeroy-jankins/jimi: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 leeroy-jankins/jimi:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf leeroy-jankins/jimi: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 leeroy-jankins/jimi:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf leeroy-jankins/jimi:Q4_K_M

Use Docker

docker model run hf.co/leeroy-jankins/jimi:Q4_K_M

LM Studio
Jan

vLLM

How to use leeroy-jankins/jimi with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leeroy-jankins/jimi"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leeroy-jankins/jimi",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/leeroy-jankins/jimi:Q4_K_M

Ollama
How to use leeroy-jankins/jimi with Ollama:
```
ollama run hf.co/leeroy-jankins/jimi:Q4_K_M
```
Unsloth Desktop

How to use leeroy-jankins/jimi with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf leeroy-jankins/jimi:Q4_K_M

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": "leeroy-jankins/jimi:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use leeroy-jankins/jimi with Docker Model Runner:
```
docker model run hf.co/leeroy-jankins/jimi:Q4_K_M
```

Lemonade

How to use leeroy-jankins/jimi with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull leeroy-jankins/jimi:Q4_K_M

Run and chat with the model

lemonade run user.jimi-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use leeroy-jankins/jimi with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf leeroy-jankins/jimi:Q4_K_M

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 leeroy-jankins/jimi:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use leeroy-jankins/jimi with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf leeroy-jankins/jimi:Q4_K_M

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 "leeroy-jankins/jimi:Q4_K_M" \
  --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"

leeroy-jankins commited on Aug 13, 2025

Commit

4904997

verified ·

1 Parent(s): 2bd2dc8

Update README.md

Browse files

Files changed (1) hide show

README.md +27 -27

README.md CHANGED Viewed

@@ -1,32 +1,32 @@
----
-license: mit
-language:
-- en
-tags:
-- code
-- finance
-datasets:
-- mlabonne/FineTome-100k
-- leeroy-jankins/Regulations
-- leeroy-jankins/Appropriations
-- leeroy-jankins/OMB-Circular-A-11
-- leeroy-jankins/RedBook
-- leeroy-jankins/SF133
-- leeroy-jankins/US-General-Ledger
-- leeroy-jankins/Title-31-CFR-Money-and-Finance
-base_model:
-- unsloth/gemma-3-4b-it
-pipeline_tag: text-generation
-metrics:
-- accuracy
----
 <img src="assets/Bro.png" alt="Preview" width="1000"/>
 ## 🎯 Overview
-**Bro** is a fine-tuned variant of the `gemma-3-4b-it` transformer model, optimized for enhanced contextual comprehension, instruction following, and domain-specific reasoning. The fine-tuning process used supervised instruction tuning across multiple NLP domains, with a focus on factual recall, multi-step reasoning, and document comprehension.
-- Built on the lightweight yet powerful `Gemma 3 4B` architecture, **Bro** provides a balance between inference speed and linguistic depth — making it suitable for both production deployment and academic research.
@@ -78,8 +78,8 @@ Bro is intended for use in:
 ### Base Model
-- **Model**: `gemma-3-4b-pt`
-- **Parameters**: ~4.1 Billion
 - **Architecture**: Transformer decoder-only
 - **Tokenizer**: SentencePiece (32k vocab)
 - **Positional Encoding**: Rotary (RoPE)
@@ -102,7 +102,7 @@ Bro is intended for use in:
 ## 🧪 Benchmark Results
-| Task                      | Metric            | Bro (Ours) | Base gemma-3-4b |
 |--------------------------|-------------------|------------|-----------------|
 | ARC Challenge (25-shot)  | Accuracy (%)       | 71.3       | 64.5            |
 | NaturalQuestions (RAG)   | EM/F1              | 51.7 / 63.9| 44.2 / 56.8     |

+---
+license: mit
+language:
+- en
+tags:
+- code
+- finance
+datasets:
+- mlabonne/FineTome-100k
+- leeroy-jankins/Regulations
+- leeroy-jankins/Appropriations
+- leeroy-jankins/OMB-Circular-A-11
+- leeroy-jankins/RedBook
+- leeroy-jankins/SF133
+- leeroy-jankins/US-General-Ledger
+- leeroy-jankins/Title-31-CFR-Money-and-Finance
+base_model:
+- unsloth/gemma-3-1b-it-GGUF
+pipeline_tag: text-generation
+metrics:
+- accuracy
+---
 <img src="assets/Bro.png" alt="Preview" width="1000"/>
 ## 🎯 Overview
+**Bro** is a fine-tuned variant of the `gemma-3-1b-it` transformer model, optimized for enhanced contextual comprehension, instruction following, and domain-specific reasoning. The fine-tuning process used supervised instruction tuning across multiple NLP domains, with a focus on factual recall, multi-step reasoning, and document comprehension.
+- Built on the lightweight yet powerful `Gemma 3 1B` architecture, **Bro** provides a balance between inference speed and linguistic depth — making it suitable for both production deployment and academic research.
 ### Base Model
+- **Model**: `gemma-3-1b-pt`
+- **Parameters**: ~1.1 Billion
 - **Architecture**: Transformer decoder-only
 - **Tokenizer**: SentencePiece (32k vocab)
 - **Positional Encoding**: Rotary (RoPE)
 ## 🧪 Benchmark Results
+| Task                      | Metric            | Bro (Ours) | Base gemma-3-1b |
 |--------------------------|-------------------|------------|-----------------|
 | ARC Challenge (25-shot)  | Accuracy (%)       | 71.3       | 64.5            |
 | NaturalQuestions (RAG)   | EM/F1              | 51.7 / 63.9| 44.2 / 56.8     |