Instructions to use Devnexai/DevNexAI_Pro1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Devnexai/DevNexAI_Pro1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Devnexai/DevNexAI_Pro1",
	filename="llama-3-8b.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Devnexai/DevNexAI_Pro1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Devnexai/DevNexAI_Pro1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Devnexai/DevNexAI_Pro1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Devnexai/DevNexAI_Pro1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Devnexai/DevNexAI_Pro1: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 Devnexai/DevNexAI_Pro1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Devnexai/DevNexAI_Pro1: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 Devnexai/DevNexAI_Pro1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Devnexai/DevNexAI_Pro1:Q4_K_M

Use Docker

docker model run hf.co/Devnexai/DevNexAI_Pro1:Q4_K_M

LM Studio
Jan

vLLM

How to use Devnexai/DevNexAI_Pro1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Devnexai/DevNexAI_Pro1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Devnexai/DevNexAI_Pro1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Devnexai/DevNexAI_Pro1:Q4_K_M

Ollama
How to use Devnexai/DevNexAI_Pro1 with Ollama:
```
ollama run hf.co/Devnexai/DevNexAI_Pro1:Q4_K_M
```

Unsloth Studio new

How to use Devnexai/DevNexAI_Pro1 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 Devnexai/DevNexAI_Pro1 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 Devnexai/DevNexAI_Pro1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Devnexai/DevNexAI_Pro1 to start chatting

Docker Model Runner
How to use Devnexai/DevNexAI_Pro1 with Docker Model Runner:
```
docker model run hf.co/Devnexai/DevNexAI_Pro1:Q4_K_M
```

Lemonade

How to use Devnexai/DevNexAI_Pro1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Devnexai/DevNexAI_Pro1:Q4_K_M

Run and chat with the model

lemonade run user.DevNexAI_Pro1-Q4_K_M

List all available models

lemonade list

nzros commited on Jan 19

Commit

868c848

verified ·

1 Parent(s): 836c049

Model card DevnexAI Updated

Browse files

Files changed (1) hide show

README.md +46 -3

README.md CHANGED Viewed

@@ -1,3 +1,46 @@
----
-license: llama3
----

+---
+license: llama3
+language:
+- en
+- code
+pipeline_tag: text-generation
+tags:
+- python
+- software-architecture
+- clean-code
+- senior-level
+- optimization
+- devnexai
+base_model: meta-llama/Meta-Llama-3-8B
+widget:
+- text: "Refactor this function to use a Decorator for logging execution time and memory usage:"
+- text: "Explain the difference between threading and asyncio in Python with a thread-safe Singleton example."
+---
+# 🚀 DevNexAI-v1-Pro: The Senior Python Architect
+**Model by [DevNexAi]** | *Part of the DevNexAI Ecosystem*
+> **"Stop generating Junior code. Start generating Architecture."**
+**DevNexAI-v1-Pro** is a specialized fine-tuned Large Language Model based on **Llama-3-8B**, engineered specifically for Senior Software Engineers, System Architects, and Tech Leads.
+Unlike generalist models that prioritize speed or generic scripting, this model has been rigorously trained on a curated dataset of **Senior-Level Python**, focusing on maintainability, performance, and enterprise-grade best practices.
+## 🧠 Senior-Level Capabilities
+This model doesn't just write code; it understands the engineering behind it.
+* **🐍 Idiomatic Python (Pythonic):** Expert usage of List Comprehensions, Generators, Context Managers, and Metaclasses.
+* **🏗️ Clean Architecture:** Strict application of SOLID principles, Design Patterns (Factory, Strategy, Observer), and Hexagonal Architecture concepts.
+* **⚡ Optimization & Concurrency:** Correct implementation of `asyncio`, `multiprocessing`, and efficient memory management.
+* **🛡️ Robustness:** Strict Type Hinting, professional Docstrings, and defensive error handling.
+## 💻 How to Use (Local Inference)
+The most efficient way to run this model locally while keeping your data private is using **Ollama** or **LM Studio**.
+### Option A: Ollama (Recommended)
+1. Download the `.gguf` file from this repository.
+2. Create a file named `Modelfile` with the following content:
+   ```dockerfile
+   FROM ./devnexai-v1-pro.Q4_K_M.gguf
+   SYSTEM "You are a Senior Software Architect. You write efficient, documented, and idiomatic Python code. You prefer clean architecture over quick hacks."