Instructions to use itsdotscience/Magicoder-S-DS-6.7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use itsdotscience/Magicoder-S-DS-6.7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="itsdotscience/Magicoder-S-DS-6.7B-GGUF",
	filename="Magicoder-S-DS-6.7B_q8_0.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 itsdotscience/Magicoder-S-DS-6.7B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0

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 itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0

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 itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0

Use Docker

docker model run hf.co/itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use itsdotscience/Magicoder-S-DS-6.7B-GGUF with Ollama:
```
ollama run hf.co/itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0
```

Unsloth Studio new

How to use itsdotscience/Magicoder-S-DS-6.7B-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 itsdotscience/Magicoder-S-DS-6.7B-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 itsdotscience/Magicoder-S-DS-6.7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for itsdotscience/Magicoder-S-DS-6.7B-GGUF to start chatting

Docker Model Runner
How to use itsdotscience/Magicoder-S-DS-6.7B-GGUF with Docker Model Runner:
```
docker model run hf.co/itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0
```

Lemonade

How to use itsdotscience/Magicoder-S-DS-6.7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull itsdotscience/Magicoder-S-DS-6.7B-GGUF:Q8_0

Run and chat with the model

lemonade run user.Magicoder-S-DS-6.7B-GGUF-Q8_0

List all available models

lemonade list

Please provide 4 bit, Thank you.

by NK-Spacewalk - opened Jan 18, 2024

Discussion

NK-Spacewalk

Jan 18, 2024

Thank you, please provide 4 bit also. only your Magicoder-S-DS-6.7B-GGUF model is working . Please update your models according to this. @TheBloke , @jan-hq

PivPav

Jan 20, 2024

I also would like to have Q6_K or Q5_K_M as a great balance between size and performance (Q4 can be a bit rough around the edges at this model size)

PivPav

Jan 20, 2024

Actually you can do it yourself (although it's not recommended for already quantized models) with llama.cpp. Just build llama.cpp from source and then run:

(llama.cpp)$ ./quantize --allow-requantize Magicoder-S-DS-6.7B_q8_0.gguf <output_requantized_model>.gguf q4_k_m

akhil3417

Feb 1, 2024

any 4 bit good quants yet?

matthoffner

Feb 3, 2024

I just uploaded a q3, q4 and q5 here https://huggingface.co/matthoffner/Magicoder-S-DS-6.7B-GGUF/tree/main

akhil3417

Feb 3, 2024

I just uploaded a q3, q4 and q5 here https://huggingface.co/matthoffner/Magicoder-S-DS-6.7B-GGUF/tree/main

Hey thanks, i ended up( merging 417884e regex_gpt2_preprocess pr and it works) , wonder if this will produce any better results or otherwise.

matthoffner

Feb 3, 2024

It seems to work ok so far, I set up a space with it here https://huggingface.co/spaces/matthoffner/ggml-coding-llm

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