Ornith-1.0-9B-GGUF

Ornith-1.0-9B-GGUF

GGUF quantizations of Ornith-1.0-9B, converted from the original Hugging Face release by deepreinforce-ai for use with LM Studio, llama.cpp, Ollama, and other GGUF-compatible inference engines.

---

Base Model

• Original Model: deepreinforce-ai/Ornith-1.0-9B
• Format: GGUF
• Converted by: arunb74

This repository contains only GGUF conversions. All model architecture, weights, tokenizer, and training were created by the original authors.

---

Available Files

Additional quantizations may be added in future releases.

---

Supported Software

This GGUF model is compatible with:

• LM Studio
• llama.cpp
• Ollama (via a custom Modelfile)
• text-generation-webui
• KoboldCpp
• Jan
• Most applications that support the GGUF format

---

Using with LM Studio

1. Open LM Studio.
2. Go to the Discover tab.
3. Search for:

arunb74/Ornith-1.0-9B-GGUF

1. Download Ornith-9b-Q4_K_M.gguf.
2. Load the model from My Models.
3. Start chatting.

Alternatively, download the GGUF file manually from this repository and place it in your LM Studio models directory.

---

Using with llama.cpp

Download the GGUF file and run:

llama-cli \
    -m Ornith-9b-Q4_K_M.gguf \
    -p "Explain reinforcement learning."

Or start an interactive chat:

llama-cli \
    -m Ornith-9b-Q4_K_M.gguf

---

Using with Ollama

Create a Modelfile:

FROM ./Ornith-9b-Q4_K_M.gguf

Create the model:

ollama create Ornith-9b -f Modelfile

Run it:

ollama run Ornith-9b

---

Conversion Details

The model was converted using the latest version of llama.cpp.

Conversion:

python convert_hf_to_gguf.py \
    ./Ornith-1.0-9B \
    --outfile Ornith-9b-f16.gguf

Quantization:

llama-quantize \
    Ornith-9b-f16.gguf \
    Ornith-9b-Q4_K_M.gguf \
    Q4_K_M

---

Hardware Requirements

For the best inference performance, GPU acceleration is recommended.

---

License

This repository contains only GGUF conversions of the original model.

Please refer to the original model repository for the license and usage terms:

https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B

---

Credits

• deepreinforce-ai for creating and releasing Ornith-1.0-9B.
• ggml-org for developing llama.cpp and the GGUF tooling.
• Hugging Face for model hosting and distribution.

---

If you find this GGUF conversion useful, please consider giving the repository a ❤️ on Hugging Face.