Instructions to use andreclaudino/CodeLlama-70b-Instruct-bitnet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use andreclaudino/CodeLlama-70b-Instruct-bitnet with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="andreclaudino/CodeLlama-70b-Instruct-bitnet",
	filename="model-F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use andreclaudino/CodeLlama-70b-Instruct-bitnet with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf andreclaudino/CodeLlama-70b-Instruct-bitnet:F16
# Run inference directly in the terminal:
llama-cli -hf andreclaudino/CodeLlama-70b-Instruct-bitnet:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf andreclaudino/CodeLlama-70b-Instruct-bitnet:F16
# Run inference directly in the terminal:
llama-cli -hf andreclaudino/CodeLlama-70b-Instruct-bitnet:F16

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 andreclaudino/CodeLlama-70b-Instruct-bitnet:F16
# Run inference directly in the terminal:
./llama-cli -hf andreclaudino/CodeLlama-70b-Instruct-bitnet:F16

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 andreclaudino/CodeLlama-70b-Instruct-bitnet:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf andreclaudino/CodeLlama-70b-Instruct-bitnet:F16

Use Docker

docker model run hf.co/andreclaudino/CodeLlama-70b-Instruct-bitnet:F16

LM Studio
Jan
Ollama
How to use andreclaudino/CodeLlama-70b-Instruct-bitnet with Ollama:
```
ollama run hf.co/andreclaudino/CodeLlama-70b-Instruct-bitnet:F16
```

Unsloth Studio new

How to use andreclaudino/CodeLlama-70b-Instruct-bitnet 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 andreclaudino/CodeLlama-70b-Instruct-bitnet 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 andreclaudino/CodeLlama-70b-Instruct-bitnet to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for andreclaudino/CodeLlama-70b-Instruct-bitnet to start chatting

Docker Model Runner
How to use andreclaudino/CodeLlama-70b-Instruct-bitnet with Docker Model Runner:
```
docker model run hf.co/andreclaudino/CodeLlama-70b-Instruct-bitnet:F16
```

Lemonade

How to use andreclaudino/CodeLlama-70b-Instruct-bitnet with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull andreclaudino/CodeLlama-70b-Instruct-bitnet:F16

Run and chat with the model

lemonade run user.CodeLlama-70b-Instruct-bitnet-F16

List all available models

lemonade list

Can this be used with bitnet.cpp?

by MaZeNsMz - opened Nov 15, 2024

Discussion

MaZeNsMz

Nov 15, 2024

Hi there,

Thanks for making this.
I am just wondering if this model can be used by Bitnet.cpp.
Or what client can use it? Or how to convert it to gguf?

Thanks again.

Regards...

andreclaudino

Owner Nov 15, 2024

Thank you for reaching me out. This model was just made yesterday. I believe it's not ready yet, need more tests. Before using that with bitnetcpp (or a recent version of LLAMMACpp which suporta Bitnet) you first meet to convert it to GGUF format. I am working in a GGUF version to be included on this repository soon.

MaZeNsMz

Nov 15, 2024

Thank you for reaching me out. This model was just made yesterday. I believe it's not ready yet, need more tests. Before using that with bitnetcpp (or a recent version of LLAMMACpp which suporta Bitnet) you first meet to convert it to GGUF format. I am working in a GGUF version to be included on this repository soon.

Thanks, I am just too exceited to test the Bitnet.cpp.

Regards...

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