Instructions to use mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Llama-3-Giraffe-70B-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 mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Llama-3-Giraffe-70B-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 mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Llama-3-Giraffe-70B-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 mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Llama-3-Giraffe-70B-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 mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Llama-3-Giraffe-70B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3-Giraffe-70B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

How are you quantizing?

by moona99 - opened May 5, 2024

Discussion

moona99

May 5, 2024

Im trying to convert and quantize a llama-3 in llamacpp. convert.py is not working with many models now. convert-hf-to-gguf.py isn't working because every safetensors repo doesn't have a tokenizer.model file. So Im curious how this is getting done.

mradermacher

Owner May 5, 2024

current convert-hf-to-gguf.py is the only correct method for llama-3 and generally does work (it does not require a tokenizer.model file). unfortunately, this specific model is not supported because the tokenizer does not match, but support can added via convert-hf-to-gguf-update.py, which is (kind of) what I did.

specifically, this is the script I used for this model: http://data.plan9.de/convert-hfhfix-to-gguf.py

mradermacher changed discussion status to closed May 5, 2024

moona99

May 5, 2024

ah... Thank you for taking the time to enlighten me! I missed that there was an update script. I will give that a try. Thank you!

mradermacher

Owner May 5, 2024

You are welcome, good luck!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment