Instructions to use Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-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 Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-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 Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Chemin-AI/llama3-8b-cpt-sahabatai-v1-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 Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Chemin-AI/llama3-8b-cpt-sahabatai-v1-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 Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf:Q4_K_M

Use Docker

docker model run hf.co/Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf with Ollama:
```
ollama run hf.co/Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf with Docker Model Runner:
```
docker model run hf.co/Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf:Q4_K_M
```

Lemonade

How to use Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Chemin-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf:Q4_K_M

Run and chat with the model

lemonade run user.llama3-8b-cpt-sahabatai-v1-instruct-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

            # Supa-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf
            This model was converted to GGUF format from [`GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct`](https://huggingface.co/GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct) using llama.cpp.
            Refer to the [original model card](https://huggingface.co/GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct) for more details on the model.

            ## Available Versions
            - `llama3-8b-cpt-sahabatai-v1-instruct.q2_k.gguf` (q2_k)

llama3-8b-cpt-sahabatai-v1-instruct.q3_k_m.gguf (q3_k_m)
llama3-8b-cpt-sahabatai-v1-instruct.q4_0.gguf (q4_0)
llama3-8b-cpt-sahabatai-v1-instruct.q4_k_m.gguf (q4_k_m)
llama3-8b-cpt-sahabatai-v1-instruct.q5_0.gguf (q5_0)
llama3-8b-cpt-sahabatai-v1-instruct.q5_k_m.gguf (q5_k_m)
llama3-8b-cpt-sahabatai-v1-instruct.q6_k.gguf (q6_k)

llama3-8b-cpt-sahabatai-v1-instruct.q8_0.gguf (q8_0)

          ## Use with llama.cpp
          Replace `FILENAME` with one of the above filenames.

          ### CLI:
          ```bash
          llama-cli --hf-repo Supa-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf --hf-file FILENAME -p "Your prompt here"
          ```

          ### Server:
          ```bash
          llama-server --hf-repo Supa-AI/llama3-8b-cpt-sahabatai-v1-instruct-gguf --hf-file FILENAME -c 2048
          ```

          ## Model Details
          - **Original Model:** [GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct](https://huggingface.co/GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct)
          - **Format:** GGUF