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

Libraries

How to use moogin/Qwisine with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("moogin/Qwisine", dtype="auto")

llama-cpp-python

How to use moogin/Qwisine with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="moogin/Qwisine",
	filename="unsloth.Q5_K_M.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 moogin/Qwisine with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf moogin/Qwisine:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf moogin/Qwisine:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf moogin/Qwisine:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf moogin/Qwisine:Q5_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 moogin/Qwisine:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf moogin/Qwisine:Q5_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 moogin/Qwisine:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf moogin/Qwisine:Q5_K_M

Use Docker

docker model run hf.co/moogin/Qwisine:Q5_K_M

LM Studio
Jan
Ollama
How to use moogin/Qwisine with Ollama:
```
ollama run hf.co/moogin/Qwisine:Q5_K_M
```

Unsloth Studio new

How to use moogin/Qwisine 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 moogin/Qwisine 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 moogin/Qwisine to start chatting

Using HuggingFace Spaces for Unsloth

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

Pi new

How to use moogin/Qwisine with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf moogin/Qwisine:Q5_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "moogin/Qwisine:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use moogin/Qwisine with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf moogin/Qwisine:Q5_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default moogin/Qwisine:Q5_K_M

Run Hermes

hermes

Docker Model Runner
How to use moogin/Qwisine with Docker Model Runner:
```
docker model run hf.co/moogin/Qwisine:Q5_K_M
```

Lemonade

How to use moogin/Qwisine with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull moogin/Qwisine:Q5_K_M

Run and chat with the model

lemonade run user.Qwisine-Q5_K_M

List all available models

lemonade list

Qwisine 14B

Model details

Field	Description
Base model	Qwen‑3-14B (pre‑trained)
Fine‑tuned by	Mugi
Task	Question‑Answering & Code Generation for the Convex TypeScript backend/database framework
Language(s)	English (developer‑oriented)
License	NAH just use it.
Model name	Qwisine

Qwisine is a specialised version of Qwen‑3 fine‑tuned on curated Convex documentation & synthethic code and community Q&A. The model understands Convex‐specific concepts (data modelling, mutations, actions, idioms, client usage, etc.) and can generate code snippets or explain behaviour in plain English.

Intended use & limitations

Primary use‑case

Conversational assistant for developers building on Convex.
Drafting / Helping with convex orientated questions & tasks.
Documentation chatbots or support assistants.

Out‑of‑scope

Production‑critical decision making without human review.

Dataset

Size : 938 Q&A pairs
Source: Convex official docs, example apps, public issues, community Discord, and synthetic edge‑cases.
Question types (distilled)
- what_is – factual look‑ups (no reasoning)
- why – causal explanations (no reasoning)
- task – recipe‑style how‑to (with reasoning)
- edge_case – tricky or undocumented scenarios (with reasoning)
- v‑task – verbose multi‑step tasks (with reasoning)

Reasoning‑bearing examples represent ~85 % of the dataset.

Training procedure -- will add later since i ran & experimented MANY RUNS 😭😭😭😭

Epochs : **
Batch : **
LR / schedule : **
Optimizer : **

Fine‑tuning followed standard QLORA with unsloth. No additional RLHF was applied.

Evaluation results

Category	Think mode	Fully Non‑Think mode
Fundamentals	75.05 %	73.44 %
Data modelling	82.82 %	87.36 %
Queries	74.38 %	74.19 %
Mutations	71.04 %	73.59 %
Actions	63.05 %	49.27 %
Idioms	75.06 %	75.06 %
Clients	69.84 %	69.84 %
Average	73.03 %	71.82 %

Think Mode

Parameter	Value	Notes
`temperature`	0.6	Reasoned answers with structure
`top_p`	0.95	Wider beam of sampling
`top_k`	20
`min_p`	0

Non-Think Mode

Parameter	Value	Notes
`temperature`	0.7	More diversity for simple prompts
`top_p`	0.8	Slightly tighter sampling
`top_k`	20
`min_p`	0

_{Adjust as needed for your deployment; these were used in LM Studio during evaluation.}

How to run locally

# LM Studio
search "Qwisine" in models menu.

# Ollama
il add soon.
# Llama‑cpp
il add soon.

Limitations & biases

Training data is entirely Convex‑centred; the model may hallucinate.
The dataset size is modest (938 samples); edge‑case coverage is still incomplete and so is more complex prompts like create project from scratch with multiple steps and instructions.

Future work

not sure yet

Citation

@misc{qwisine2025,
  title        = {Qwisine: A Qwen‑3 model fine‑tuned for Convex},
  author       = {mugi},
  year         = {2025},
  url          = {https://huggingface.co/mugivara1/Qwisine},
}

Acknowledgements

(To be completed)

Convex • Qwen‑3 • ...

Downloads last month: 7

GGUF

Model size

15B params

Architecture

qwen3

Hardware compatibility

5-bit

Inference Providers NEW

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

Model tree for moogin/Qwisine

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Quantized

unsloth/Qwen3-14B-unsloth-bnb-4bit

Quantized

(24)

this model