Instructions to use robsucher/Llama-3B-HBDI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use robsucher/Llama-3B-HBDI with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("robsucher/Llama-3B-HBDI", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use robsucher/Llama-3B-HBDI 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 robsucher/Llama-3B-HBDI:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf robsucher/Llama-3B-HBDI:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf robsucher/Llama-3B-HBDI:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf robsucher/Llama-3B-HBDI: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 robsucher/Llama-3B-HBDI:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf robsucher/Llama-3B-HBDI: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 robsucher/Llama-3B-HBDI:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf robsucher/Llama-3B-HBDI:Q4_K_M

Use Docker

docker model run hf.co/robsucher/Llama-3B-HBDI:Q4_K_M

LM Studio
Jan
Ollama
How to use robsucher/Llama-3B-HBDI with Ollama:
```
ollama run hf.co/robsucher/Llama-3B-HBDI:Q4_K_M
```
Unsloth Desktop

How to use robsucher/Llama-3B-HBDI with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf robsucher/Llama-3B-HBDI: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": "robsucher/Llama-3B-HBDI:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use robsucher/Llama-3B-HBDI with Docker Model Runner:
```
docker model run hf.co/robsucher/Llama-3B-HBDI:Q4_K_M
```

Lemonade

How to use robsucher/Llama-3B-HBDI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull robsucher/Llama-3B-HBDI:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3B-HBDI-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use robsucher/Llama-3B-HBDI with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf robsucher/Llama-3B-HBDI: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 robsucher/Llama-3B-HBDI:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use robsucher/Llama-3B-HBDI with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf robsucher/Llama-3B-HBDI: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 "robsucher/Llama-3B-HBDI: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"

Model Card for Model ID

It is a fine-tuned version of the Llama 3.2 3B LLM. The objective is to provide more detailed information concering the Herrmann Brain Dominance Instrument.

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub.

Developed by: Rob Sucher, Armstrong Webb Ltd
Model type: Llama
Finetuned from model [optional]: Llama 3.2 3B

Uses

As an 'instruct' model for HBDI questions.

Bias, Risks, Limitations, and Recommendation

Trained on limited number of Q&A pairs (these were not validated before fine-tuned training). Recommendation: use independent verification to confirm the status off the answers/results.

How to Get Started with the Model

Can be run locally. If using LM Studio, ensure that config.json is in same directory as the fine-tuned model.

Training Details

Training Data

The fine-tuning dataset is comprised of 100 'Herrmann Brain Dominance Inference' Q&A pairs that have been distilled from a larger LLM. Converted to ShareGPT format for training.

Training Procedure

QLoRA. 60 training iterations. Trained on Google Colab.

Training Hyperparameters

args = TrainingArguments(
    per_device_train_batch_size = 2,
    gradient_accumulation_steps = 4,
    warmup_steps = 5,
    # num_train_epochs = 1, # Set this for 1 full training run.
    max_steps = 60,
    learning_rate = 2e-4,
    fp16 = not is_bf16_supported(),
    bf16 = is_bf16_supported(),
    logging_steps = 1,
    optim = "adamw_8bit",
    weight_decay = 0.01,
    lr_scheduler_type = "linear",
    seed = 3407,
    output_dir = "outputs",
    report_to = "none", # Use this for WandB etc
)

Speeds, Sizes, Times [optional]

Less than 5 mins to train.

Compute Infrastructure

Google Colab

Software

Python, supporting packages (eg Unsloth, HF)

Downloads last month: 39

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

8-bit

Inference Providers NEW

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