Instructions to use DavidBrowne17/LlamaThink-8B-instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavidBrowne17/LlamaThink-8B-instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="DavidBrowne17/LlamaThink-8B-instruct-GGUF",
	filename="LlamaThink-8B-instruct-bf16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use DavidBrowne17/LlamaThink-8B-instruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf DavidBrowne17/LlamaThink-8B-instruct-GGUF: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 DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DavidBrowne17/LlamaThink-8B-instruct-GGUF: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 DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use DavidBrowne17/LlamaThink-8B-instruct-GGUF with Ollama:
```
ollama run hf.co/DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M
```

Unsloth Studio new

How to use DavidBrowne17/LlamaThink-8B-instruct-GGUF 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 DavidBrowne17/LlamaThink-8B-instruct-GGUF 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 DavidBrowne17/LlamaThink-8B-instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DavidBrowne17/LlamaThink-8B-instruct-GGUF to start chatting

Pi new

How to use DavidBrowne17/LlamaThink-8B-instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use DavidBrowne17/LlamaThink-8B-instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf DavidBrowne17/LlamaThink-8B-instruct-GGUF: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 DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use DavidBrowne17/LlamaThink-8B-instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M
```

Lemonade

How to use DavidBrowne17/LlamaThink-8B-instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DavidBrowne17/LlamaThink-8B-instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.LlamaThink-8B-instruct-GGUF-Q4_K_M

List all available models

lemonade list

license: apache-2.0 base_model: - meta-llama/Llama-3.1-8B-Instruct

LlamaThink-8b-instruct

LlamaThink-8b-instruct is an instruction-tuned language model built on the LLaMA-3 architecture. It is optimized for generating thoughtful, structured responses using a unique dual-section output format.

Model Details

Architecture: LLaMA-3
Size: 8 billion parameters
License: Apache 2.0

Usage

System Prompt

To ensure the model generates responses in the intended format, use the following system prompt:

Respond in the following format:
<thinking>
...
</thinking>
<answer>
...
</answer>

Example Input

What are the benefits of using LlamaThink-8b-instruct for AI research?

Example Output

<thinking>
LlamaThink-8b-instruct is built on the robust LLaMA-3 architecture, which offers enhanced performance and scalability. Its instruction-tuning ensures it understands complex prompts and provides structured responses. This makes it ideal for research applications where clarity and precision are essential.
</thinking>
<answer>
Using LlamaThink-8b-instruct for AI research provides benefits such as improved contextual understanding, consistent response formatting, and adaptability to various domains. Its open-source Apache 2.0 license also encourages innovation and collaboration.
</answer>

Installation

You can load the model directly from Hugging Face:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "DavidBrowne17/LlamaThink-8B-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

Citation

If you use LlamaThink-8b-instruct in your research or applications, please cite it as follows:

@misc{llamathink2025,
  author = {David Browne},
  title = {LlamaThink-8b-instruct},
  year = {2025},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/DavidBrowne17/LlamaThink-8B-instruct}},
  license = {Apache 2.0}
}

License

LlamaThink-8b-instruct is released under the Apache License 2.0.

Contact

For questions or contributions, reach out via Hugging Face or GitHub.

Downloads last month: 21

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Inference Providers NEW

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

Model tree for DavidBrowne17/LlamaThink-8B-instruct-GGUF

Base model

meta-llama/Llama-3.1-8B

Finetuned

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

Quantized

(638)

this model