Text Generation
Transformers
English
qwen2
code-generation
python
fine-tuning
Qwen
tools
agent-framework
multi-agent
conversational
Eval Results (legacy)
Instructions to use my-ai-stack/Stack-2-9-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use my-ai-stack/Stack-2-9-finetuned with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="my-ai-stack/Stack-2-9-finetuned") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("my-ai-stack/Stack-2-9-finetuned") model = AutoModelForCausalLM.from_pretrained("my-ai-stack/Stack-2-9-finetuned") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use my-ai-stack/Stack-2-9-finetuned with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "my-ai-stack/Stack-2-9-finetuned" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "my-ai-stack/Stack-2-9-finetuned", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/my-ai-stack/Stack-2-9-finetuned
- SGLang
How to use my-ai-stack/Stack-2-9-finetuned with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "my-ai-stack/Stack-2-9-finetuned" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "my-ai-stack/Stack-2-9-finetuned", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "my-ai-stack/Stack-2-9-finetuned" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "my-ai-stack/Stack-2-9-finetuned", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use my-ai-stack/Stack-2-9-finetuned with Docker Model Runner:
docker model run hf.co/my-ai-stack/Stack-2-9-finetuned
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>Stack 2.9 — Your Pattern-Learning AI Companion</title> | |
| <link rel="stylesheet" href="styles.css"> | |
| <link rel="icon" href="data:image/svg+xml,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><text y='.9em' font-size='90'>🤖</text></svg>"> | |
| <meta name="description" content="Stack 2.9 - Open-source AI that learns, adapts, and improves itself over time. Built on Qwen2.5-Coder-32B."> | |
| </head> | |
| <body> | |
| <nav class="navbar"> | |
| <div class="nav-container"> | |
| <a href="#" class="logo"> | |
| <span class="logo-icon">🤖</span> | |
| <span class="logo-text">Stack 2.9</span> | |
| </a> | |
| <button class="mobile-toggle" id="mobileToggle" aria-label="Toggle menu"> | |
| <span></span> | |
| <span></span> | |
| <span></span> | |
| </button> | |
| <ul class="nav-links" id="navLinks"> | |
| <li><a href="#features">Features</a></li> | |
| <li><a href="#demo">Live Demo</a></li> | |
| <li><a href="benchmark.html">Benchmarks</a></li> | |
| <li><a href="#faq">FAQ</a></li> | |
| <li><a href="https://github.com/my-ai-stack/stack-2.9" class="nav-github" target="_blank"> | |
| <svg viewBox="0 0 24 24" width="20" height="20" fill="currentColor"> | |
| <path d="M12 0C5.37 0 0 5.37 0 12c0 5.31 3.435 9.795 8.205 11.385.6.105.825-.255.825-.57 0-.285-.015-1.23-.015-2.235-3.015.555-3.795-.735-4.035-1.41-.135-.345-.72-1.41-1.23-1.695-.42-.225-1.02-.78-.015-.795.945-.015 1.62.87 1.845 1.23 1.08 1.815 2.805 1.305 3.495.99.105-.78.42-1.305.765-1.605-2.67-.3-5.46-1.335-5.46-5.925 0-1.305.465-2.385 1.23-3.225-.12-.3-.54-1.53.12-3.18 0 0 1.005-.315 3.3 1.23.96-.27 1.98-.405 3-.405s2.04.135 3 .405c2.295-1.56 3.3-1.23 3.3-1.23.66 1.65.24 2.88.12 3.18.765.84 1.23 1.905 1.23 3.225 0 4.605-2.805 5.625-5.475 5.925.435.375.81 1.095.81 2.22 0 1.605-.015 2.895-.015 3.3 0 .315.225.69.825.57A12.02 12.02 0 0024 12c0-6.63-5.37-12-12-12z"/> | |
| </svg> | |
| GitHub | |
| </a></li> | |
| </ul> | |
| </div> | |
| </nav> | |
| <section class="hero"> | |
| <div class="hero-bg"></div> | |
| <div class="hero-content"> | |
| <div class="hero-text"> | |
| <h1 class="hero-title"> | |
| <span class="gradient-text">Your AI</span> that gets<br> | |
| smarter with use | |
| </h1> | |
| <p class="hero-subtitle"> | |
| Stack 2.9 is an open-source AI that learns, adapts, and improves itself over time. | |
| Built on Qwen2.5-Coder-32B, but transformed into something new. | |
| </p> | |
| <div class="hero-buttons"> | |
| <a href="https://github.com/my-ai-stack/stack-2.9" class="btn btn-primary" target="_blank"> | |
| <svg viewBox="0 0 24 24" width="20" height="20" fill="currentColor"> | |
| <path d="M12 0C5.37 0 0 5.37 0 12c0 5.31 3.435 9.795 8.205 11.385.6.105.825-.255.825-.57 0-.285-.015-1.23-.015-2.235-3.015.555-3.795-.735-4.035-1.41-.135-.345-.72-1.41-1.23-1.695-.42-.225-1.02-.78-.015-.795.945-.015 1.62.87 1.845 1.23 1.08 1.815 2.805 1.305 3.495.99.105-.78.42-1.305.765-1.605-2.67-.3-5.46-1.335-5.46-5.925 0-1.305.465-2.385 1.23-3.225-.12-.3-.54-1.53.12-3.18 0 0 1.005-.315 3.3 1.23.96-.27 1.98-.405 3-.405s2.04.135 3 .405c2.295-1.56 3.3-1.23 3.3-1.23.66 1.65.24 2.88.12 3.18.765.84 1.23 1.905 1.23 3.225 0 4.605-2.805 5.625-5.475 5.925.435.375.81 1.095.81 2.22 0 1.605-.015 2.895-.015 3.3 0 .315.225.69.825.57A12.02 12.02 0 0024 12c0-6.63-5.37-12-12-12z"/> | |
| </svg> | |
| Star on GitHub | |
| <span class="star-count" id="starCount">2.4k</span> | |
| </a> | |
| <a href="#demo" class="btn btn-secondary">Try Live Demo</a> | |
| </div> | |
| </div> | |
| <div class="hero-demo"> | |
| <div class="code-editor"> | |
| <div class="editor-header"> | |
| <div class="editor-dots"> | |
| <span class="dot red"></span> | |
| <span class="dot yellow"></span> | |
| <span class="dot green"></span> | |
| </div> | |
| <span class="editor-title">stack_2.9</span> | |
| </div> | |
| <div class="editor-content"> | |
| <div class="code-lines" id="codeLines"></div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="features" id="features"> | |
| <div class="container"> | |
| <h2 class="section-title">Why Stack 2.9?</h2> | |
| <p class="section-subtitle">Built for developers who want an AI that grows with them</p> | |
| <div class="features-grid"> | |
| <div class="feature-card"> | |
| <div class="feature-icon">🧠</div> | |
| <h3>Pattern Learning</h3> | |
| <p>Learns from every conversation and task. Improves its own capabilities through experience. Gets smarter the more you use it.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <div class="feature-icon">📚</div> | |
| <h3>Codebase-Aware</h3> | |
| <p>Deep understanding of your entire project. Extracts patterns and applies learned knowledge to solve new problems.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <div class="feature-icon">🔧</div> | |
| <h3>37 Built-in Tools</h3> | |
| <p>Coding, debugging, file operations, search, API calls, system commands, and more. Natural language commands.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <div class="feature-icon">🚀</div> | |
| <h3>Deploy Anywhere</h3> | |
| <p>Self-host with Docker, run locally, or use cloud. Your data stays yours. Complete control over your AI.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <div class="feature-icon">💾</div> | |
| <h3>Persistent Memory</h3> | |
| <p>Remembers past conversations and learned patterns. Builds long-term knowledge across sessions.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <div class="feature-icon">🤝</div> | |
| <h3>Multi-Agent</h3> | |
| <p>Collaborate with multiple agents. Delegate tasks, share context, work together on complex problems.</p> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="benchmarks-preview"> | |
| <div class="container"> | |
| <h2 class="section-title">Performance</h2> | |
| <p class="section-subtitle">Competitive results on standard coding benchmarks</p> | |
| <div class="benchmark-grid"> | |
| <div class="benchmark-card"> | |
| <div class="benchmark-value">TBD</div> | |
| <div class="benchmark-label">HumanEval</div> | |
| <div class="benchmark-bar"> | |
| <div class="benchmark-fill" style="width: 0%"></div> | |
| </div> | |
| </div> | |
| <div class="benchmark-card"> | |
| <div class="benchmark-value">TBD</div> | |
| <div class="benchmark-label">MBPP</div> | |
| <div class="benchmark-bar"> | |
| <div class="benchmark-fill" style="width: 0%"></div> | |
| </div> | |
| </div> | |
| <div class="benchmark-card highlight"> | |
| <div class="benchmark-value">TBD</div> | |
| <div class="benchmark-label">Tool Use</div> | |
| <div class="benchmark-bar"> | |
| <div class="benchmark-fill" style="width: 0%"></div> | |
| </div> | |
| </div> | |
| <div class="benchmark-card"> | |
| <div class="benchmark-value">Evolves</div> | |
| <div class="benchmark-label">Self-Improvement</div> | |
| <div class="benchmark-bar"> | |
| <div class="benchmark-fill pulse" style="width: 100%"></div> | |
| </div> | |
| </div> | |
| </div> | |
| <a href="benchmark.html" class="btn btn-outline">View Full Benchmarks</a> | |
| </div> | |
| </section> | |
| <section class="demo" id="demo"> | |
| <div class="container"> | |
| <h2 class="section-title">Try It Live</h2> | |
| <p class="section-subtitle">Experience Stack 2.9 in action</p> | |
| <div class="demo-container"> | |
| <div class="demo-terminal"> | |
| <div class="terminal-header"> | |
| <span>Stack 2.9 Interactive</span> | |
| <button class="terminal-clear" id="clearDemo">Clear</button> | |
| </div> | |
| <div class="terminal-body" id="demoOutput"> | |
| <div class="terminal-line system">🤖 Stack 2.9 ready! Type a command...</div> | |
| </div> | |
| <div class="terminal-input"> | |
| <span class="prompt">></span> | |
| <input type="text" id="demoInput" placeholder="Ask anything... (try 'help' for commands)" autocomplete="off"> | |
| </div> | |
| </div> | |
| <div class="demo-commands"> | |
| <p>Try these commands:</p> | |
| <button class="demo-cmd" data-cmd="help">help</button> | |
| <button class="demo-cmd" data-cmd="explain self-evolution">explain self-evolution</button> | |
| <button class="demo-cmd" data-cmd="list tools">list tools</button> | |
| <button class="demo-cmd" data-cmd="benchmark">benchmark</button> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="how-it-works"> | |
| <div class="container"> | |
| <h2 class="section-title">How Pattern Learning Works</h2> | |
| <div class="steps"> | |
| <div class="step"> | |
| <div class="step-number">1</div> | |
| <h3>Observe</h3> | |
| <p>Watches its own problem-solving process</p> | |
| </div> | |
| <div class="step-arrow">→</div> | |
| <div class="step"> | |
| <div class="step-number">2</div> | |
| <h3>Learn</h3> | |
| <p>Extracts patterns from successes</p> | |
| </div> | |
| <div class="step-arrow">→</div> | |
| <div class="step"> | |
| <div class="step-number">3</div> | |
| <h3>Remember</h3> | |
| <p>Stores knowledge in persistent memory</p> | |
| </div> | |
| <div class="step-arrow">→</div> | |
| <div class="step"> | |
| <div class="step-number">4</div> | |
| <h3>Apply</h3> | |
| <p>Uses wisdom in future tasks</p> | |
| </div> | |
| <div class="step-arrow">→</div> | |
| <div class="step"> | |
| <div class="step-number">5</div> | |
| <h3>Improve</h3> | |
| <p>Gradually becomes smarter</p> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <section class="faq" id="faq"> | |
| <div class="container"> | |
| <h2 class="section-title">Frequently Asked Questions</h2> | |
| <div class="faq-grid"> | |
| <div class="faq-item"> | |
| <h3>What's the difference between Stack 2.9 and other AI assistants?</h3> | |
| <p>Stack 2.9 learns from every interaction. While other assistants reset between sessions, Stack 2.9 remembers, evolves, and gets better over time.</p> | |
| </div> | |
| <div class="faq-item"> | |
| <h3>How does self-evolution work?</h3> | |
| <p>Stack 2.9 observes its problem-solving process, extracts patterns from successful solutions, stores learned knowledge in persistent memory, and applies that knowledge to future tasks.</p> | |
| </div> | |
| <div class="faq-item"> | |
| <h3>Can I self-host Stack 2.9?</h3> | |
| <p>Absolutely! Stack 2.9 is designed for self-hosting. Deploy with Docker, run locally, or integrate into your own infrastructure. Your data stays yours.</p> | |
| </div> | |
| <div class="faq-item"> | |
| <h3>What tools are available?</h3> | |
| <p>37 built-in tools including file operations, code execution, search, API calls, git operations, terminal commands, and more. All accessible via natural language.</p> | |
| </div> | |
| <div class="faq-item"> | |
| <h3>Is it free to use?</h3> | |
| <p>Yes! Stack 2.9 is open-source under Apache 2.0 license. You can use, modify, and distribute it freely.</p> | |
| </div> | |
| <div class="faq-item"> | |
| <h3>What hardware do I need?</h3> | |
| <p>Stack 2.9 runs on consumer hardware. A machine with 16GB+ RAM can handle the 32B model. GPU acceleration recommended for best performance.</p> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <footer class="footer"> | |
| <div class="container"> | |
| <div class="footer-content"> | |
| <div class="footer-brand"> | |
| <span class="logo-icon">🤖</span> | |
| <span>Stack 2.9</span> | |
| <p>Your pattern-learning AI companion</p> | |
| </div> | |
| <div class="footer-links"> | |
| <a href="https://github.com/my-ai-stack/stack-2.9" target="_blank">GitHub</a> | |
| <a href="benchmark.html">Benchmarks</a> | |
| <a href="#">Documentation</a> | |
| <a href="#">Community</a> | |
| </div> | |
| </div> | |
| <div class="footer-bottom"> | |
| <p>© 2024 Stack 2.9 — Open source under Apache 2.0</p> | |
| </div> | |
| </div> | |
| </footer> | |
| <script src="app.js"></script> | |
| </body> | |
| </html> |