--- license: apache-2.0 language: - en library_name: transformers pipeline_tag: text-generation tags: - code - code-generation - coding-assistant - qlora - unsloth - local-inference - merkium-ai - adamas-mini-1 model-index: - name: Arti Code Mini results: [] ---
arti-code-mini > Arti Code Mini Local Coding apache-2.0  ·  3B params  ·  2,048 ctx  ·  6GB+ VRAM
# Arti Code Mini Arti Code Mini is a 3B-parameter coding assistant fine-tuned by **Merkium AI** for local deployment on consumer hardware. It targets clean, well-structured code generation and multi-turn debugging assistance without a dependency on cloud inference.
Table of Contents - [Model Details](#model-details) - [Intended Use](#intended-use) - [Installation](#installation) - [Usage](#usage) - [Hardware Requirements](#hardware-requirements) - [Example Prompts](#example-prompts) - [Limitations](#limitations) - [Citation](#citation) - [License](#license) - [Contact](#contact)
**Quick start** ```bash pip install transformers torch accelerate bitsandbytes python -c " from transformers import pipeline pipe = pipeline('text-generation', model='Merkiumai/Arti-code-mini', device_map='auto') print(pipe([{'role': 'user', 'content': 'Write a function that reverses a string.'}], max_new_tokens=200)[0]['generated_text'][-1]['content']) " ``` ## Model Details | Property | Value | |---|---| | Developer | Merkium AI | | Parameters | 3 Billion | | Fine-tuning method | QLoRA (LoRA via Unsloth) | | Primary use case | Coding assistant | | Context length | 2,048 tokens | | Precision | float16 / 4-bit quantized | | License | Apache 2.0 | | tuned | Adamas Mini 1 | ## Intended Use **In scope:** - Writing and completing code across multiple languages - Debugging and explaining existing code - Generating functions, classes, algorithms, and scripts - Learning support for programming concepts and best practices **Out of scope:** - General conversation or non-coding tasks - Fully autonomous code generation without human review - Production systems without independent testing and validation ## Installation ```bash pip install transformers torch accelerate bitsandbytes ``` ## Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer import torch model_name = "Merkiumai/Arti-code-mini" tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True ) messages = [ {"role": "user", "content": "Write a Python function that checks if a number is prime."} ] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) inputs = tokenizer(text, return_tensors="pt").to(model.device) outputs = model.generate( **inputs, max_new_tokens=300, temperature=0.3, do_sample=True, pad_token_id=tokenizer.eos_token_id ) response = tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True) print(response) ``` Chat formatting is applied automatically via `tokenizer.apply_chat_template()`. The underlying format: ```text ### System: You are Arti Code Mini, a helpful coding assistant created by Merkium AI. ### User: Write a Python function that reverses a string. ### Arti: def reverse_string(s: str) -> str: return s[::-1] ``` ## Hardware Requirements | Component | Minimum | Recommended | |---|---|---| | GPU VRAM | 6 GB | 8 GB+ | | RAM | 8 GB | 16 GB | | Storage | 4 GB free | 8 GB free | ## Example Prompts - Write a Python function that checks if a string is a palindrome. - Create a FastAPI endpoint that accepts a name and returns a greeting. - Explain how binary search works and provide an implementation. - Write a class for a bank account with deposit and withdraw methods. - Write a decorator that measures the execution time of a function. - Remove duplicates from a list while preserving order. ## Limitations - May occasionally produce incorrect or incomplete code. - Performs best with clear, specific, well-structured prompts. - Not suited to tasks outside coding and software development. - Context limited to 2,048 tokens per session. - All generated code should be reviewed by a human before use in production. ## Citation ```bibtex @misc{artimini2025, title = {Arti Code Mini: A Lightweight Local Coding Assistant}, author = {{Merkium AI}}, year = {2025}, url = {https://huggingface.co/Merkiumai/Arti-code-mini} } ``` ## License Released under the [Apache 2.0](LICENSE) license. ## Contact Model repository: [huggingface.co/Merkiumai/Arti-code-mini](https://huggingface.co/Merkiumai/Arti-code-mini) ---

Developed and maintained by Merkium AI