Instructions to use Jimmydog/goask-hr-q8_0.gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Jimmydog/goask-hr-q8_0.gguf 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 Jimmydog/goask-hr-q8_0.gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf Jimmydog/goask-hr-q8_0.gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Jimmydog/goask-hr-q8_0.gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf Jimmydog/goask-hr-q8_0.gguf:Q8_0

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 Jimmydog/goask-hr-q8_0.gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Jimmydog/goask-hr-q8_0.gguf:Q8_0

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 Jimmydog/goask-hr-q8_0.gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Jimmydog/goask-hr-q8_0.gguf:Q8_0

Use Docker

docker model run hf.co/Jimmydog/goask-hr-q8_0.gguf:Q8_0

LM Studio
Jan
Ollama
How to use Jimmydog/goask-hr-q8_0.gguf with Ollama:
```
ollama run hf.co/Jimmydog/goask-hr-q8_0.gguf:Q8_0
```
Unsloth Desktop

How to use Jimmydog/goask-hr-q8_0.gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Jimmydog/goask-hr-q8_0.gguf:Q8_0

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": "Jimmydog/goask-hr-q8_0.gguf:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Jimmydog/goask-hr-q8_0.gguf with Docker Model Runner:
```
docker model run hf.co/Jimmydog/goask-hr-q8_0.gguf:Q8_0
```

Lemonade

How to use Jimmydog/goask-hr-q8_0.gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Jimmydog/goask-hr-q8_0.gguf:Q8_0

Run and chat with the model

lemonade run user.goask-hr-q8_0.gguf-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Jimmydog/goask-hr-q8_0.gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Jimmydog/goask-hr-q8_0.gguf:Q8_0

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 Jimmydog/goask-hr-q8_0.gguf:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Jimmydog/goask-hr-q8_0.gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Jimmydog/goask-hr-q8_0.gguf:Q8_0

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 "Jimmydog/goask-hr-q8_0.gguf:Q8_0" \
  --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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

HR Jimmy -- Enterprise HR Assistant

Based on Meta Llama 3.1 8B Instruct

Overview

HR Jimmy is a domain-specialized enterprise HR assistant built on top of Meta Llama 3.1 8B Instruct.

The model is designed for structured HR workflow automation, including:

Leave application processing
Overtime submission handling
HR policy question answering
Structured data extraction
Multi-step enterprise workflow guidance
Deterministic enterprise-grade responses

This repository provides configuration and deployment instructions to reproduce the HR Jimmy behavior.

Base Model

This project is built upon:

meta-llama/Llama-3.1-8B-Instruct

Users must download the base model directly from Meta or Hugging Face and comply with the original license terms.

This repository does NOT redistribute the base model weights.

Model Configuration

Architecture: LLaMA
Parameters: 8B
Deployment Quantization: Q8_0 (GGUF)
Context Length: 131072 tokens
Temperature: 0.01 (deterministic enterprise mode)
Stop Tokens:
- <|start_header_id|>
- <|end_header_id|>
- <|eot_id|>

Repository Contents

Modelfile
Prompt template configuration
Stop token configuration
Deployment instructions
Workflow design notes

Base model weights are not included.

Reproduction Instructions (Ollama)

Step 1 -- Pull Base Model

ollama pull llama3.1:latest

Step 2 -- Build HR Jimmy

ollama create hr_jimmy -f Modelfile

Step 3 -- Run

ollama run hr_jimmy

Optional: Generating GGUF for llama.cpp

If you wish to generate a GGUF file:

Download the original FP16 base model from Meta.
Merge fine-tuned adapters (if applicable).
Convert using llama.cpp conversion tools.
Quantize to Q8_0 or other supported formats.

This ensures compliance with Meta's license terms.

Intended Use

HR Jimmy is intended for:

Enterprise HR chatbot systems
Internal workflow automation
Structured form completion
Deterministic multi-step reasoning in business environments
Agent-based enterprise AI systems

It is not intended for open-domain general conversation.

Fine-tuning Details (If Applicable)

Fine-tuning Method: LoRA / QLoRA
Domain: Enterprise HR workflows
Data Type: Structured conversational and workflow data
Optimization Goal: Deterministic structured output generation

Adapter weights require the original base model.

License Notice

This project depends on Meta Llama 3.1 8B Instruct.

Users must review and comply with the official Meta Llama 3 license:

https://ai.meta.com/llama/license/

This repository provides configuration and workflow adaptation only.
It does not redistribute base model weights.

Enterprise Positioning

HR Jimmy demonstrates:

Prompt Engineering for deterministic output
Enterprise workflow modeling
Multi-agent structured reasoning
Low-temperature production configuration
LLM integration within HR automation systems

For enterprise deployment inquiries, please adapt configuration to your internal compliance standards.

Downloads last month: 10

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

8-bit

Inference Providers NEW

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