Instructions to use LoneStriker/DeepMagic-Coder-7b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LoneStriker/DeepMagic-Coder-7b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LoneStriker/DeepMagic-Coder-7b-GGUF",
	filename="DeepMagic-Coder-7b-Q3_K_L.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 LoneStriker/DeepMagic-Coder-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 LoneStriker/DeepMagic-Coder-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LoneStriker/DeepMagic-Coder-7b-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 LoneStriker/DeepMagic-Coder-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LoneStriker/DeepMagic-Coder-7b-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 LoneStriker/DeepMagic-Coder-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LoneStriker/DeepMagic-Coder-7b-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 LoneStriker/DeepMagic-Coder-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LoneStriker/DeepMagic-Coder-7b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/LoneStriker/DeepMagic-Coder-7b-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use LoneStriker/DeepMagic-Coder-7b-GGUF with Ollama:
```
ollama run hf.co/LoneStriker/DeepMagic-Coder-7b-GGUF:Q4_K_M
```

Unsloth Studio new

How to use LoneStriker/DeepMagic-Coder-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 LoneStriker/DeepMagic-Coder-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 LoneStriker/DeepMagic-Coder-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 LoneStriker/DeepMagic-Coder-7b-GGUF to start chatting

Docker Model Runner
How to use LoneStriker/DeepMagic-Coder-7b-GGUF with Docker Model Runner:
```
docker model run hf.co/LoneStriker/DeepMagic-Coder-7b-GGUF:Q4_K_M
```

Lemonade

How to use LoneStriker/DeepMagic-Coder-7b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LoneStriker/DeepMagic-Coder-7b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepMagic-Coder-7b-GGUF-Q4_K_M

List all available models

lemonade list

DeepMagic-Coder-7b

Alternate version:

https://huggingface.co/rombodawg/DeepMagic-Coder-7b-Alt

This is an extremely successful merge of the deepseek-coder-6.7b-instruct and Magicoder-S-DS-6.7B models, bringing an uplift in overall coding performance without any compromise to the models integrity (at least with limited testing).

This is the first of my models to use the merge-kits task_arithmetic merging method. The method is detailed bellow, and its clearly very usefull for merging ai models that were fine-tuned from a common base:

Task Arithmetic:

Computes "task vectors" for each model by subtracting a base model. 
Merges the task vectors linearly and adds back the base. 
Works great for models that were fine tuned from a common ancestor. 
Also a super useful mental framework for several of the more involved 
merge methods.

The original models used in this merge can be found here:

The Merge was created using Mergekit and the paremeters can be found bellow:

models:
  - model: deepseek-ai_deepseek-coder-6.7b-instruct
    parameters:
      weight: 1
  - model: ise-uiuc_Magicoder-S-DS-6.7B
    parameters:
      weight: 1
merge_method: task_arithmetic
base_model: ise-uiuc_Magicoder-S-DS-6.7B
parameters:
  normalize: true
  int8_mask: true
dtype: float16

Downloads last month: 77

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support