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 • ...