Instructions to use nisten/meta-405b-instruct-cpu-optimized-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nisten/meta-405b-instruct-cpu-optimized-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nisten/meta-405b-instruct-cpu-optimized-gguf",
	filename="meta-405b-cpu-i1-q4xs-00001-of-00005.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use nisten/meta-405b-instruct-cpu-optimized-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nisten/meta-405b-instruct-cpu-optimized-gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf nisten/meta-405b-instruct-cpu-optimized-gguf:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nisten/meta-405b-instruct-cpu-optimized-gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf nisten/meta-405b-instruct-cpu-optimized-gguf:BF16

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 nisten/meta-405b-instruct-cpu-optimized-gguf:BF16
# Run inference directly in the terminal:
./llama-cli -hf nisten/meta-405b-instruct-cpu-optimized-gguf:BF16

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 nisten/meta-405b-instruct-cpu-optimized-gguf:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nisten/meta-405b-instruct-cpu-optimized-gguf:BF16

Use Docker

docker model run hf.co/nisten/meta-405b-instruct-cpu-optimized-gguf:BF16

LM Studio
Jan
Ollama
How to use nisten/meta-405b-instruct-cpu-optimized-gguf with Ollama:
```
ollama run hf.co/nisten/meta-405b-instruct-cpu-optimized-gguf:BF16
```

Unsloth Studio

How to use nisten/meta-405b-instruct-cpu-optimized-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 nisten/meta-405b-instruct-cpu-optimized-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 nisten/meta-405b-instruct-cpu-optimized-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nisten/meta-405b-instruct-cpu-optimized-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use nisten/meta-405b-instruct-cpu-optimized-gguf with Docker Model Runner:
```
docker model run hf.co/nisten/meta-405b-instruct-cpu-optimized-gguf:BF16
```

Lemonade

How to use nisten/meta-405b-instruct-cpu-optimized-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nisten/meta-405b-instruct-cpu-optimized-gguf:BF16

Run and chat with the model

lemonade run user.meta-405b-instruct-cpu-optimized-gguf-BF16

List all available models

lemonade list

Question about 1-bit quant

by ThomasBaruzier - opened Jul 29, 2024

Discussion

ThomasBaruzier

Jul 29, 2024

•

edited Jul 29, 2024

Hello,

You are claiming your 1 bit quant is "custom".
Could you please elaborate about how it was made, and if it is higher quality than a traditional IQ1_S or IQ1_M quant?

Thanks.

nisten

Owner Jul 29, 2024

only ~92% of the weights are 1bit,
so had to rewrite llama.cpp to do that custom quant,
also have not uploaded them yet

ThomasBaruzier

Jul 29, 2024

Thank you for the answer
If you plot the model size vs PPL for the two closest quants, would this custom quant yield a lower, equal, or higher perplexity? If there is a real benefit, it might be worth sharing your findings in the llama.cpp repo?

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