--- 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 --- # ๐Ÿ’Ž 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.** --- ## โšก 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 | --- # ๐Ÿง  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 --- # ๐Ÿ”ฅ Core Philosophy ```text USER REQUEST โ”‚ โ–ผ โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ OBSIDIAN-9B-Coder โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ”‚ โ–ผ COMPLETE IMPLEMENTATION โ”‚ โ”œโ”€โ”€ HTML โ”œโ”€โ”€ CSS โ”œโ”€โ”€ JavaScript โ”œโ”€โ”€ Three.js โ”œโ”€โ”€ Canvas โ””โ”€โ”€ 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. --- # ๐ŸŽฎ 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”‚ โ”œโ”€โ”€ Camera โ”œโ”€โ”€ Renderer โ”œโ”€โ”€ Lighting โ”œโ”€โ”€ Objects โ”‚ โ””โ”€โ”€ Materials โ”‚ โ”œโ”€โ”€ Input โ”œโ”€โ”€ State โ”œโ”€โ”€ Game Logic โ””โ”€โ”€ Animation Loop ``` --- # ๐ŸŒ Frontend Generation OBSIDIAN has strong exposure to complete frontend applications combining: ```text HTML โ”‚ โ”œโ”€โ”€ CSS โ”‚ โ””โ”€โ”€ JavaScript โ”‚ โ”œโ”€โ”€ DOM โ”œโ”€โ”€ State โ”œโ”€โ”€ Events โ”œโ”€โ”€ Canvas โ”œโ”€โ”€ Three.js โ”œโ”€โ”€ Rendering โ””โ”€โ”€ 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. --- # ๐ŸŒ 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` | | ๆ—ฅๆœฌ่ชž | `ja` | | ็ฎ€ไฝ“ไธญๆ–‡ | `zh` | | ะ ัƒัั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. --- # ๐Ÿ—ƒ๏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 | --- # ๐Ÿ“Š 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. --- # ๐Ÿงน 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. --- # ๐Ÿงช 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 ``` --- # ๐Ÿงฌ 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. --- # ๐Ÿ“ฆ 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 | --- # โš–๏ธ Quantization Guide ```text QUALITY โ–ฒ โ”‚ Q8_0 โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ Q6_K โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ Q5_K_M โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ Q4_K_M โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ Q3_K_M โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ–บ 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. --- # ๐Ÿš€ 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. --- # ๐Ÿ’ป 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. ``` --- # ๐ŸŽ›๏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. --- # ๐ŸŽฏ 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 --- # ๐Ÿ“ Evaluation Executable evaluation is strongly recommended for coding models. A useful evaluation pipeline is: ```text PROMPT โ”‚ โ–ผ GENERATE โ”‚ โ–ผ PARSE โ”‚ โ–ผ EXECUTE โ”‚ โ–ผ INSPECT โ”‚ โ–ผ 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. --- # โš ๏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. --- # ๐Ÿงฌ Model Lineage OBSIDIAN-9B-Coder was **not trained from scratch**. Its lineage is: ```text Qwen3.5 family โ”‚ โ–ผ Jackrong/Qwopus3.5-9B-Coder โ”‚ โ–ผ Coder Max Multilingual โ”‚ โ–ผ LoRA Supervised Fine-Tuning โ”‚ โ–ผ OBSIDIAN-9B-Coder โ”‚ โ–ผ GGUF Quantizations ``` OBSIDIAN therefore inherits substantial pretrained and coding capabilities from its base model while adding specialization through Coder Max. --- # ๐Ÿ“š 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. --- # ๐Ÿ—๏ธ Training Stack ```text Qwen3.5 Model Family โ”‚ โ–ผ Jackrong/Qwopus3.5-9B-Coder โ”‚ โ”‚ Base model โ–ผ Coder Max Multilingual guell00/Coder-max โ”‚ โ”‚ Code-focused SFT data โ–ผ LoRA + SFT Unsloth โ”‚ โ–ผ OBSIDIAN-9B-Coder โ”‚ โ–ผ GGUF โ”‚ โ”œโ”€โ”€ Q3_K_M โ”œโ”€โ”€ Q4_K_M โ”œโ”€โ”€ Q5_K_M โ”œโ”€โ”€ Q6_K โ””โ”€โ”€ Q8_0 ``` --- # ๐Ÿ™ 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 --- # ๐Ÿ’Ž 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.**