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
File size: 3,734 Bytes
b6ae7b8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 | #!/usr/bin/env python3
"""
Stack 2.9 Demo Script
Showcases the capabilities of the Stack 2.9 CLI and Agent Interface.
"""
import os
import sys
from pathlib import Path
# Add stack_cli to path
sys.path.insert(0, str(Path(__file__).parent / "stack_cli"))
from stack_cli.agent import create_agent
from stack_cli.tools import list_tools
from stack_cli.context import create_context_manager
def print_section(title: str):
"""Print a section header."""
print("\n" + "="*60)
print(f" {title}")
print("="*60)
def demo():
"""Run the demo."""
print_banner()
# Initialize
print("\n➤ Initializing Stack 2.9 Agent...")
agent = create_agent()
print(f" ✓ Agent loaded with {len(list_tools())} tools")
# Show context
print_section("Workspace Context")
ctx = agent.get_context()
print(ctx)
# Show available tools
print_section("Available Tools")
tools = list_tools()
print(f"\nTotal tools: {len(tools)}\n")
categories = {
"File Operations": ["read", "write", "edit", "search", "grep", "copy", "move", "delete"],
"Git Operations": ["git_status", "git_commit", "git_push", "git_pull", "git_branch", "git_log", "git_diff"],
"Code Execution": ["run", "test", "lint", "format", "typecheck", "server", "install"],
"Web Tools": ["web_search", "fetch", "download", "check_url", "screenshot"],
"Memory & Context": ["memory_recall", "memory_save", "memory_list", "context_load", "project_scan"],
"Task Planning": ["create_task", "list_tasks", "update_task", "delete_task", "create_plan", "execute_plan"]
}
for category, tool_list in categories.items():
print(f"\n{category} ({len(tool_list)}):")
for tool in tool_list:
if tool in tools:
print(f" ✓ {tool}")
# Demo: Run a sample query
print_section("Demo: Sample Query")
print("\nQuery: \"list my tasks\"")
response = agent.process("list my tasks")
print(f"\nResponse:\n {response.content}")
print_section("Demo: Project Scan")
print("\nQuery: \"scan project structure\"")
response = agent.process("scan project structure")
print(f"\nResponse:\n {response.content[:500]}...")
print_section("Agent Capabilities")
print("""
The Stack 2.9 Agent can:
• Understand natural language queries
• Select appropriate tools automatically
• Generate helpful responses
• Self-reflect and improve
• Maintain conversation context
• Execute complex workflows
""")
print_section("Quick Start")
print("""
To use Stack 2.9 CLI:
1. Interactive Chat:
$ python -m stack_cli.cli
or
$ stack
2. Single Command:
$ python -m stack_cli.cli -c "read README.md"
or
$ stack -c "git status"
3. Specific Tools:
$ stack -t project_scan list_tasks
4. Voice Mode (requires setup):
$ stack -v
5. Python API:
from stack_cli import create_agent
agent = create_agent()
response = agent.process("list files")
print(response.content)
""")
print_section("Demo Complete!")
print("\nThe Stack 2.9 CLI and Agent Interface is ready to use.")
print("Run 'python stack.py' or 'stack' to start.\n")
def print_banner():
"""Print the banner."""
banner = r"""
____ _ _ _
| _ \ ___ _ __ __| |_ __ ___ (_)_ __ | | __
| |_) / _ \ '_ \ / _` | '__/ _ \| | '_ \ | |/ /
| _ < __/ | | | (_| | | | (_) | | | | | | <
|_| \_\___|_| |_|\__,_|_| \___/|_|_| |_| |_|\_\
CLI & Agent Interface v2.9.0
"""
print(banner)
if __name__ == "__main__":
demo()
|