Instructions to use mengmeong/meng-programming-skill-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mengmeong/meng-programming-skill-finetune with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mengmeong/meng-programming-skill-finetune",
	filename="meng-coding-skills_q8.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 mengmeong/meng-programming-skill-finetune with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mengmeong/meng-programming-skill-finetune
# Run inference directly in the terminal:
llama-cli -hf mengmeong/meng-programming-skill-finetune

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mengmeong/meng-programming-skill-finetune
# Run inference directly in the terminal:
llama-cli -hf mengmeong/meng-programming-skill-finetune

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 mengmeong/meng-programming-skill-finetune
# Run inference directly in the terminal:
./llama-cli -hf mengmeong/meng-programming-skill-finetune

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 mengmeong/meng-programming-skill-finetune
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mengmeong/meng-programming-skill-finetune

Use Docker

docker model run hf.co/mengmeong/meng-programming-skill-finetune

LM Studio
Jan

vLLM

How to use mengmeong/meng-programming-skill-finetune with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mengmeong/meng-programming-skill-finetune

Ollama
How to use mengmeong/meng-programming-skill-finetune with Ollama:
```
ollama run hf.co/mengmeong/meng-programming-skill-finetune
```

Unsloth Studio new

How to use mengmeong/meng-programming-skill-finetune 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 mengmeong/meng-programming-skill-finetune 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 mengmeong/meng-programming-skill-finetune to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mengmeong/meng-programming-skill-finetune to start chatting

Docker Model Runner
How to use mengmeong/meng-programming-skill-finetune with Docker Model Runner:
```
docker model run hf.co/mengmeong/meng-programming-skill-finetune
```

Lemonade

How to use mengmeong/meng-programming-skill-finetune with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mengmeong/meng-programming-skill-finetune

Run and chat with the model

lemonade run user.meng-programming-skill-finetune-{{QUANT_TAG}}

List all available models

lemonade list

Programming Skills Learning Path Model

This model is a fine-tuned version of the base mdoel designed to generate path of learning a skill based on input text. It's particularly useful for identifying emerging trends and skill combinations in the rapidly evolving tech landscape.

Usage & Limitations

The model is intended for:

Deploying in limited CPU resource, with average about 40 tps on 1 CPU core

The model has limits:

The dataset might not capture the very latest tools development in programming world
Chatbot usecase does not fit the model usecase
The model only return the response as JSON list.

Please note that this model was trained on a custom dataset and may reflect biases present in that data.