Instructions to use bartowski/Meta-Llama-3-8B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/Meta-Llama-3-8B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bartowski/Meta-Llama-3-8B-Instruct-GGUF",
	filename="Meta-Llama-3-8B-Instruct-IQ1_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bartowski/Meta-Llama-3-8B-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 bartowski/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/Meta-Llama-3-8B-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 bartowski/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bartowski/Meta-Llama-3-8B-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 bartowski/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/Meta-Llama-3-8B-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 bartowski/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/Meta-Llama-3-8B-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/Meta-Llama-3-8B-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/Meta-Llama-3-8B-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_M

Ollama
How to use bartowski/Meta-Llama-3-8B-Instruct-GGUF with Ollama:
```
ollama run hf.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use bartowski/Meta-Llama-3-8B-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 bartowski/Meta-Llama-3-8B-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 bartowski/Meta-Llama-3-8B-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 bartowski/Meta-Llama-3-8B-Instruct-GGUF to start chatting

Docker Model Runner
How to use bartowski/Meta-Llama-3-8B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/Meta-Llama-3-8B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/Meta-Llama-3-8B-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Meta-Llama-3-8B-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

You think you could re-quant with the regex fix?

by YearZero - opened May 6, 2024

Discussion

YearZero

May 6, 2024

•

edited May 6, 2024

https://github.com/ggerganov/llama.cpp/issues/7062

"For anyone wanting to use this:

Edit your HF model's tokenizer.json file
Swap the two patterns in the pretokenizer
Convert to gguf using llamacpp
Profit"

..alternatively there may be a llamacpp fix forthcoming (not sure yet), and we could just wait for that too.

Another commenter says:
"Note to users: there is no need to "re-quant". Replacing the regex pattern under LLAMA_VOCAB_PRE_TYPE_LLAMA3 in the llama.cpp file before building/compiling will fix the issue (at least for the fingerprint; I didn't test anything else).

[NOTE: this is the current workaround until the llama.cpp devs study this issue]

I tested for both llama.cpp CPU and GPU and I get the fingerprint. I also tested making this change to koboldcpp (but for default BPE regex, as I cannot use override-kv options in koboldcpp) and it worked perfectly. I have yet to test using server, but I asume it will also work."

bartowski

Owner May 7, 2024

Yeah i've been keeping my eye on that, i'm hoping that there'll be a real full fix merged soon, ideally it would be a fix that doesn't involve changing the existing official files

blankreg

May 11, 2024

What's the status of the llama fix? I'm not a techie, that issue @ github is closed but I don't understand if it has been fixed

bartowski

Owner May 11, 2024

It was a fix on the generation side of things

That said I'll be remaking this probably today anyways because there was a change in metas repo AND bf16 conversion is about to be added to llama.cpp, so it should yield slightly more accurate quants

blankreg

May 12, 2024

bf16 conversion is about to be added to llama.cpp

BTW this new comment about bf16 says "no statistically significant advantage over FP16" https://github.com/ggerganov/llama.cpp/issues/7062#issuecomment-2106158969

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