Quantized GGUF versions of Charty-1B, a compact text-to-Mermaid diagram generation model fine-tuned from LFM2.5-1.2B-Instruct. Designed for on-device, mobile, and CPU-only inference.
This model ships with Unsloth's fixed Jinja chat template embedded in the GGUF versions and is applied automatically by llama.cpp with --jinja.
🎯 Intended Use
Generate Mermaid diagram syntax (flowcharts, sequence, class, state, ER, Gantt, pie, git graphs, mindmaps, quadrant charts, …) from plain-text prompts.
Run on low-end hardware: mobile phones, edge devices, laptops, embedded systems.
Power apps that need offline, private, diagram-as-code generation.
What it does
Input (user prompt):
Create a flowchart showing the user login process with MFA verification.
Output (model response):
mermaid
1graph TD
2 A[User Visits Login Page]--> B[Enter Credentials]3 B --> C{Credentials Valid?}4 C -->|No| D[Show Error Message]5 D --> B
6 C -->|Yes| E[Send MFA Code]7 E --> F[Enter MFA Code]8 F --> G{MFA Valid?}9 G -->|No| H[Show MFA Error]10 H --> F
11 G -->|Yes| I[Grant Access]
The model outputs only the Mermaid syntax code. No wrapping text, no mermaid fences.
🏃 Inference
Recommended Generation Parameters
Parameter
Value
temperature
0.1
top_k
50
top_p
0.1
repetition_penalty
1.05
📊 Training Details
Detail
Value
Framework
Unsloth + Hugging Face TRL
Method
LoRA Supervised Fine-Tuning (SFT), merged into full weights
Dataset
ali-thowfeek/text-to-mermaid
Dataset size
3,837 examples
Dataset source
Derived from Celiadraw/text-to-mermaid-2, cleaned, reworded, and validated against Mermaid v11 (core)
Validation
100% of training examples produce valid Mermaid v11 core syntax
Output format
Raw Mermaid syntax only (no markdown fences, no explanations)
