---
language:
- pt
- en
- es
- fr
- de
- it
- ja
- zh
- ru
- tr
pipeline_tag: text-generation
tags:
- code
- coding
- coder
- qwen
- qwen3.5
- gguf
- unsloth
- lora
- sft
- html
- css
- javascript
- threejs
- canvas
- python
- multilingual
---
# ๐ OBSIDIAN-9B-Coder
> **Complete Code ยท Long Context ยท Interactive Software**
**OBSIDIAN-9B-Coder** is a 9B-class coding model fine-tuned from **Jackrong/Qwopus3.5-9B-Coder** using the **Coder Max Multilingual** dataset.
The model is specialized in generating **complete software implementations**, with a strong focus on modern frontend development, interactive browser applications, Three.js, HTML5 Canvas, JavaScript, HTML/CSS, Python and general programming.
OBSIDIAN is designed around a simple objective:
> **Generate the implementation, not fragments of it.**
---
## โก Highlights
| Feature | OBSIDIAN-9B-Coder |
|---|---|
| Model Class | 9B |
| Training Context | 32K |
| Training Method | LoRA SFT |
| Training Framework | Unsloth |
| Languages | 10 |
| Primary Focus | Code Generation |
| Frontend | Strong specialization |
| Three.js | Strong specialization |
| Canvas | Strong specialization |
| JavaScript | Strong specialization |
| Python | Supported |
| Distribution | GGUF |
---
# ๐ง Overview
OBSIDIAN-9B-Coder was created to further specialize an already capable coding model toward **implementation-heavy programming tasks**.
Instead of focusing primarily on explanations surrounding code, the fine-tuning corpus heavily emphasizes generation of the actual implementation.
The model is particularly suited for:
- Complete single-file web applications
- HTML5
- Modern CSS
- JavaScript ES6+
- Three.js
- HTML5 Canvas
- Interactive browser applications
- Browser games
- Graphical experiments
- DOM manipulation
- Animation loops
- State management
- Python
- Algorithms
- Multilingual programming instructions
- Long-form code generation
---
# ๐ฅ Core Philosophy
```text
USER REQUEST
โ
โผ
โโโโโโโโโโโโโโโโโโโโโโโโ
โ OBSIDIAN-9B-Coder โ
โโโโโโโโโโโโโโโโโโโโโโโโ
โ
โผ
COMPLETE IMPLEMENTATION
โ
โโโ HTML
โโโ CSS
โโโ JavaScript
โโโ Three.js
โโโ Canvas
โโโ Python
```
The training strategy emphasizes:
```text
Less boilerplate explanation
+
More actual implementation
+
Complete long-form outputs
=
OBSIDIAN
```
OBSIDIAN is fine-tuned to preserve long application structures including:
- document layout;
- styles;
- application state;
- event handlers;
- rendering logic;
- animation loops;
- user interaction;
- game logic;
- DOM lifecycle;
- complete closing structures.
---
# ๐ฎ Three.js Specialization
Three.js is one of the primary specialization targets of OBSIDIAN.
Training examples contain patterns involving:
- Scene creation
- Perspective cameras
- Lighting
- Meshes
- Materials
- Geometry
- Animation loops
- Keyboard input
- Mouse interaction
- Game mechanics
- Collision logic
- 3D environments
- Interactive simulations
- Complete browser games
- Single-file Three.js applications
The objective is not simply to teach isolated Three.js API calls.
The model is trained to connect the different components required to produce an actual working application.
For example:
```text
Scene
โ
โโโ Camera
โโโ Renderer
โโโ Lighting
โโโ Objects
โ
โโโ Materials
โ
โโโ Input
โโโ State
โโโ Game Logic
โโโ Animation Loop
```
---
# ๐ Frontend Generation
OBSIDIAN has strong exposure to complete frontend applications combining:
```text
HTML
โ
โโโ CSS
โ
โโโ JavaScript
โ
โโโ DOM
โโโ State
โโโ Events
โโโ Canvas
โโโ Three.js
โโโ Rendering
โโโ Animation
```
A typical training target may contain an entire application:
```html
```
The objective is to reduce common failure modes where coding models generate the beginning of an application but fail to correctly complete its architecture.
---
# ๐ Multilingual Programming
OBSIDIAN was fine-tuned with programming instructions across **10 languages**.
| Language | Code |
|---|---|
| Portuguรชs | `pt` |
| English | `en` |
| Espaรฑol | `es` |
| Franรงais | `fr` |
| Deutsch | `de` |
| Italiano | `it` |
| ๆฅๆฌ่ช | `ja` |
| ็ฎไฝไธญๆ | `zh` |
| ะ ัััะบะธะน | `ru` |
| Tรผrkรงe | `tr` |
The goal is to make coding capability less dependent on the natural language used in the instruction.
A developer can therefore ask for implementations using prompts in multiple languages while still requesting code in the same programming ecosystem.
---
# ๐๏ธ Training Dataset
OBSIDIAN-9B-Coder was fine-tuned using **Coder Max Multilingual**.
**Dataset:**
`guell00/Coder-max`
Coder Max is a conversational supervised fine-tuning dataset focused heavily on code generation.
The corpus was designed around **complete implementations rather than heavily truncated programming responses**.
## Dataset Characteristics
| Characteristic | Description |
|---|---|
| Format | JSONL |
| Structure | Conversational messages |
| Training Type | Supervised Fine-Tuning |
| Languages | 10 |
| Main Content | Programming |
| Code Density | ~95%+ |
| Frontend Focus | Strong |
| Three.js Specialization | Strong |
| Long Code Outputs | Preserved |
---
# ๐ Coder Max Scale
Coder Max is distributed in multiple incremental variants.
| Variant | Physical Size | Records | Messages | Code Density |
|---|---:|---:|---:|---:|
| `001MB` | 3,739,874 B | 109 | 220 | 99.08% |
| `010MB` | 12,709,008 B | 969 | 2,012 | 96.18% |
| `100MB` | 102,679,666 B | 9,790 | 20,396 | 95.84% |
| `300MB` | 302,689,973 B | 29,233 | 60,916 | 95.83% |
| `500MB` | 502,678,782 B | 48,676 | 101,442 | 95.82% |
| `600MB` | 602,666,385 B | 58,466 | 121,848 | 95.82% |
| `001GB` | 1,002,677,454 B | 97,499 | 203,200 | 95.82% |
| `total_4GB` | 4,002,669,404 B | 390,302 | 813,452 | 95.81% |
The larger variants contain the content represented by the smaller variants, allowing different training scales without requiring manual concatenation.
---
# ๐งน Dataset Curation
Coder Max was built with a code-oriented preprocessing pipeline.
Important characteristics include:
### Code Density
More than 95% of the larger corpus variants consist of code-oriented content.
### Python Syntax Validation
Python blocks were structurally checked during preprocessing.
Invalid or corrupted samples could therefore be removed before training.
### Complete Code Preservation
Long HTML, CSS and JavaScript applications are preserved rather than intentionally truncated.
This is especially important for teaching:
- closing tags;
- application state;
- complete functions;
- event listeners;
- rendering loops;
- lifecycle logic.
### Data Sanitization
The preprocessing pipeline targets removal of artifacts such as:
- credentials;
- API keys;
- local IP addresses;
- runtime artifacts.
### Provenance
Dataset records include SHA-256-based provenance metadata.
---
# ๐งช Fine-Tuning
OBSIDIAN-9B-Coder was produced using supervised fine-tuning with **LoRA**.
Training configuration:
```text
Training method LoRA
Precision BF16
LoRA rank 16
LoRA alpha 32
LoRA dropout 0
Context target 32,768
Trainer Unsloth
Optimizer AdamW BNB 8-bit
Scheduler Cosine
Response-only training Enabled
```
LoRA target modules:
```text
q_proj
k_proj
v_proj
o_proj
gate_proj
up_proj
down_proj
```
---
# ๐งฌ Training Strategy
The model was trained using a code-heavy SFT corpus designed around long-form completions.
Important characteristics include:
- long HTML responses;
- complete application generation;
- high-value specialization examples;
- multilingual prompt variants;
- frontend-oriented training;
- Three.js exposure;
- Canvas exposure;
- JavaScript-heavy examples;
- assistant-response-only loss.
Some repetitions in the source dataset may be intentional.
Selected programming concepts and application patterns can be repeated to reinforce specific behaviors and specialization targets.
---
# ๐ฆ GGUF
OBSIDIAN-9B-Coder is distributed in **GGUF** format for efficient local inference.
Available quantizations include:
| File | Quantization | Recommended Use |
|---|---|---|
| `Qwopus3.5-9B-Coder.Q8_0.gguf` | Q8_0 | Maximum practical GGUF fidelity |
| `Qwopus3.5-9B-Coder.Q6_K.gguf` | Q6_K | High quality |
| `Qwopus3.5-9B-Coder.Q5_K_M.gguf` | Q5_K_M | Quality / size balance |
| `Qwopus3.5-9B-Coder.Q4_K_M.gguf` | Q4_K_M | Recommended general use |
| `Qwopus3.5-9B-Coder.Q3_K_M.gguf` | Q3_K_M | Memory-constrained systems |
| `Qwopus3.5-9B-Coder.BF16-mmproj.gguf` | BF16 mmproj | Multimodal projector |
---
# โ๏ธ Quantization Guide
```text
QUALITY
โฒ
โ
Q8_0 โโโโโโโโโโโโโโโโโโโโ
Q6_K โโโโโโโโโโโโโโโโโโ
Q5_K_M โโโโโโโโโโโโโโโโโ
Q4_K_M โโโโโโโโโโโโโโโ
Q3_K_M โโโโโโโโโโโโ
โ
โโโโโโโโโโโโโโโโบ LOWER MEMORY
```
## Q8_0
Use when preserving model fidelity is more important than memory consumption.
## Q6_K
High-quality option with lower requirements than Q8_0.
## Q5_K_M
Strong compromise between model fidelity and memory requirements.
## Q4_K_M
Recommended starting point for most local deployments.
## Q3_K_M
Designed for systems where memory consumption is the primary constraint.
For coding workloads, **Q4_K_M** and **Q5_K_M** are good starting points.
---
# ๐ llama.cpp
For compatible text inference:
```bash
llama-cli -hf guell00/OBSIDIAN-9B-Coder --jinja
```
For compatible multimodal inference:
```bash
llama-mtmd-cli -hf guell00/OBSIDIAN-9B-Coder --jinja
```
The exact command and available features depend on the installed `llama.cpp` version and selected GGUF files.
---
# ๐ป Example Prompts
## Three.js Game
```text
Create a complete Three.js game inside a single HTML file.
Include:
- responsive rendering;
- perspective camera;
- dynamic lighting;
- keyboard controls;
- collision logic;
- score system;
- restart functionality;
- animation loop.
Return the complete HTML file.
```
---
## Frontend Application
```text
Create a complete responsive web application using HTML,
CSS and vanilla JavaScript.
The application must include:
- modern interface;
- internal state;
- animations;
- user interaction;
- responsive design.
Return a single complete HTML file.
```
---
## Portuguese
```text
Crie uma aplicaรงรฃo web completa usando HTML, CSS e JavaScript.
A aplicaรงรฃo deve possuir uma interface moderna, animaรงรตes,
estado interno e interaรงรฃo com o usuรกrio.
Retorne o arquivo HTML completo.
```
---
## Canvas
```text
Build a complete interactive particle simulation using the
HTML5 Canvas API.
Include mouse interaction, animation, responsive resizing
and performance-conscious rendering.
```
---
## Python
```text
Implement a complete Python solution for the following problem.
Explain the algorithm briefly and return working code.
```
---
# ๐๏ธ Generation Settings
Coding tasks generally benefit from conservative sampling.
A reasonable starting point:
```text
temperature: 0.2
top_p: 0.9
```
For more creative frontend generation:
```text
temperature: 0.5 - 0.7
top_p: 0.9 - 0.95
```
These values are starting points rather than guaranteed optimal settings.
Generation parameters should be benchmarked for the target workload.
---
# ๐ฏ Intended Use
OBSIDIAN-9B-Coder is intended for:
- Coding assistants
- Frontend code generation
- HTML/CSS/JavaScript generation
- Three.js applications
- Browser games
- Canvas applications
- Interactive interfaces
- Python programming
- Programming experiments
- Multilingual coding assistants
- Local coding models
- Research into code-specialized fine-tuning
---
# ๐ Evaluation
Executable evaluation is strongly recommended for coding models.
A useful evaluation pipeline is:
```text
PROMPT
โ
โผ
GENERATE
โ
โผ
PARSE
โ
โผ
EXECUTE
โ
โผ
INSPECT
โ
โผ
TEST
```
Useful evaluation categories include:
- HTML completeness
- CSS validity
- JavaScript syntax
- JavaScript runtime behavior
- Three.js initialization
- Rendering-loop correctness
- DOM interaction
- Canvas rendering
- Python syntax
- Algorithmic correctness
- Long-response completion
- Multilingual instruction following
For code-generation models, executable correctness is generally more informative than text similarity alone.
---
# โ ๏ธ Limitations
OBSIDIAN-9B-Coder is a generative model.
Generated code can contain:
- logical errors;
- security vulnerabilities;
- hallucinated APIs;
- outdated library usage;
- incomplete edge-case handling;
- incorrect assumptions;
- dependency incompatibilities.
Generated applications should be inspected and tested before production deployment.
Long context capacity also does not guarantee perfect reasoning or perfect retention across every token of a long prompt.
---
# ๐งฌ Model Lineage
OBSIDIAN-9B-Coder was **not trained from scratch**.
Its lineage is:
```text
Qwen3.5 family
โ
โผ
Jackrong/Qwopus3.5-9B-Coder
โ
โผ
Coder Max Multilingual
โ
โผ
LoRA Supervised Fine-Tuning
โ
โผ
OBSIDIAN-9B-Coder
โ
โผ
GGUF Quantizations
```
OBSIDIAN therefore inherits substantial pretrained and coding capabilities from its base model while adding specialization through Coder Max.
---
# ๐ Training Sources
## Base Model
OBSIDIAN-9B-Coder was fine-tuned from:
**Jackrong/Qwopus3.5-9B-Coder**
Hugging Face:
https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder
The Jackrong model is itself a coding-focused derivative of the Qwen3.5 model family and provides the underlying pretrained and coding capabilities used as the starting point for OBSIDIAN.
---
## Fine-Tuning Dataset
The dataset used for the OBSIDIAN fine-tuning stage was:
**Coder Max Multilingual**
**Author:** guell00
Hugging Face:
https://huggingface.co/datasets/guell00/Coder-max
Coder Max provides the additional specialization toward:
- complete code generation;
- HTML/CSS/JavaScript;
- Three.js;
- Canvas;
- Python;
- interactive applications;
- long-form implementations;
- multilingual programming instructions.
---
# ๐๏ธ Training Stack
```text
Qwen3.5 Model Family
โ
โผ
Jackrong/Qwopus3.5-9B-Coder
โ
โ Base model
โผ
Coder Max Multilingual
guell00/Coder-max
โ
โ Code-focused SFT data
โผ
LoRA + SFT
Unsloth
โ
โผ
OBSIDIAN-9B-Coder
โ
โผ
GGUF
โ
โโโ Q3_K_M
โโโ Q4_K_M
โโโ Q5_K_M
โโโ Q6_K
โโโ Q8_0
```
---
# ๐ Credits
OBSIDIAN-9B-Coder builds upon work from the open-source model ecosystem.
### Qwen
For the underlying Qwen model family and architecture.
### Jackrong
For **Qwopus3.5-9B-Coder**, used as the direct base model for this fine-tuning.
### Unsloth
For the efficient fine-tuning and model conversion tooling used during training.
### guell00
For:
- **Coder Max Multilingual**
- OBSIDIAN fine-tuning
- dataset preparation
- model specialization
- GGUF release
---
# ๐ OBSIDIAN-9B-Coder
```text
Base
Jackrong/Qwopus3.5-9B-Coder
+
Dataset
guell00/Coder-max
+
Fine-Tuning
LoRA SFT / Unsloth
=
OBSIDIAN-9B-Coder
```
**9B ยท 32K Training Context ยท Three.js ยท JavaScript ยท HTML ยท CSS ยท Canvas ยท Python ยท Multilingual**
> **OBSIDIAN-9B-Coder โ specialized for complete code generation.**