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", device_map="auto") 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 Settings
- 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
walidsobhie-code
feat: Add remaining RTMP tools (FileRead, FileWrite, Sleep, AskQuestion, Brief, TaskGet, TeamDelete, MCPTool, Worktree, SyntheticOutput)
5dc5419 | """FileReadTool - Read file contents for Stack 2.9""" | |
| import os | |
| from pathlib import Path | |
| from typing import Optional | |
| from .base import BaseTool, ToolResult | |
| from .registry import tool_registry | |
| class FileReadTool(BaseTool): | |
| """Read contents of a file.""" | |
| name = "file_read" | |
| description = "Read contents of a file" | |
| input_schema = { | |
| "type": "object", | |
| "properties": { | |
| "path": {"type": "string", "description": "File path to read"}, | |
| "offset": {"type": "number", "description": "Line offset to start reading"}, | |
| "limit": {"type": "number", "description": "Maximum lines to read"}, | |
| "show_lines": {"type": "boolean", "default": False, "description": "Include line numbers"} | |
| }, | |
| "required": ["path"] | |
| } | |
| async def execute(self, path: str, offset: Optional[int] = None, limit: Optional[int] = None, show_lines: bool = False) -> ToolResult: | |
| """Read file.""" | |
| file_path = Path(path) | |
| if not file_path.exists(): | |
| return ToolResult(success=False, error=f"File not found: {path}") | |
| if not file_path.is_file(): | |
| return ToolResult(success=False, error=f"Not a file: {path}") | |
| try: | |
| lines = file_path.read_text().split('\n') | |
| except Exception as e: | |
| return ToolResult(success=False, error=f"Cannot read file: {e}") | |
| total_lines = len(lines) | |
| # Apply offset | |
| if offset is not None and offset > 0: | |
| lines = lines[offset:] | |
| elif offset is not None: | |
| offset = 0 | |
| # Apply limit | |
| if limit is not None and limit > 0: | |
| lines = lines[:limit] | |
| if show_lines: | |
| start_line = (offset or 0) + 1 | |
| content = '\n'.join(f"{i}: {line}" for i, line in enumerate(lines, start_line)) | |
| else: | |
| content = '\n'.join(lines) | |
| return ToolResult(success=True, data={ | |
| "path": path, | |
| "content": content, | |
| "lines_read": len(lines), | |
| "total_lines": total_lines, | |
| "offset": offset, | |
| "truncated": limit is not None and len(lines) >= limit | |
| }) | |
| class FileExistsTool(BaseTool): | |
| """Check if a file exists.""" | |
| name = "file_exists" | |
| description = "Check if a file or directory exists" | |
| input_schema = { | |
| "type": "object", | |
| "properties": { | |
| "path": {"type": "string", "description": "Path to check"} | |
| }, | |
| "required": ["path"] | |
| } | |
| async def execute(self, path: str) -> ToolResult: | |
| """Check existence.""" | |
| p = Path(path) | |
| return ToolResult(success=True, data={ | |
| "path": path, | |
| "exists": p.exists(), | |
| "is_file": p.is_file() if p.exists() else None, | |
| "is_dir": p.is_dir() if p.exists() else None | |
| }) | |
| # Register tools | |
| tool_registry.register(FileReadTool()) | |
| tool_registry.register(FileExistsTool()) | |