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

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)

# pip install -U transformers accelerate
# 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=256)
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
```

Stack-2-9-finetuned / src

Commit History

Apr 9

22:09
fix: restore previous model card with tools showcase⁠

walidsobhie-code +1: Claude Opus 4.6

b64b6b0
21:57
release: prepare v1.0.0 for public release⁠

walidsobhie-code

13d8bea
21:14
reorganize: consolidate root level to 20 folders⁠

walidsobhie-code +1: Claude Opus 4.6

b8e3e42
19:33
chore: Rename MCP server to Stack2.9

walidsobhie-code

c7f1596
19:08
fix: Correct FastMCP.add_tool signature for MCP server

walidsobhie-code

5ddf5f9
19:03
feat: Add MCP server for Stack 2.9 tools exposure

walidsobhie-code

3de42e7
14:23
Fix tool parameter signatures and improve consistency

walidsobhie-code

359acf6
13:25
feat: Add remaining RTMP tools (FileRead, FileWrite, Sleep, AskQuestion, Brief, TaskGet, TeamDelete, MCPTool, Worktree, SyntheticOutput)

walidsobhie-code

5dc5419
12:59
feat: Add Tier 2 RTMP tools (TodoWrite, PlanMode, ConfigTool)

walidsobhie-code

31d646f
12:23
feat: Add FileEditTool, GrepTool, GlobTool (Tier 1 RTMP tools)⁠

walidsobhie-code

2531078
00:37
feat: Add Phase 2 RTMP tools (web_fetch, messaging, remote_trigger, tool_discovery)

walidsobhie-code

e6853d3
00:28
feat: Add RTMP tools implementation (Phase 1 & 2)⁠

walidsobhie-code

068bc7f

Apr 8

22:47
feat: Add comprehensive enhancement modules for Stack 2.9⁠

walidsobhie-code

8f05ad1
19:28
Add persistent chat history to ~/.stack-2.9/chat_history.json

walidsobhie-code

6807e9a
18:44
fix: remove feedback prompt from chat mode for cleaner UX

walidsobhie-code

31f5bef
17:28
fix: update benchmark paths in stack-2.9-cli.py and remove deprecated cli/ module⁠

walidsobhie-code

fd9b9a2
14:35
init

walidsobhie-code

a9b0b85
00:35
Add tools, fix web search, update model⁠

walidsobhie-code

35697c2

Apr 7

15:02
Fix Gradio/huggingface_hub version compatibility⁠

walidsobhie-code +1: Claude Opus 4.6

97fa10c

Apr 3

17:30
refactor: Clean up project structure - fewer root folders⁠

walidsobhie-code +1: Claude Opus 4.6

99a7be2
17:01
feat: add TypeScript modules and reorganize project structure⁠

walidsobhie-code +1: Claude Opus 4.6

bfc7d04

Commit History

Apr 9

fix: restore previous model card with tools showcase⁠

release: prepare v1.0.0 for public release⁠

reorganize: consolidate root level to 20 folders⁠

chore: Rename MCP server to Stack2.9

fix: Correct FastMCP.add_tool signature for MCP server

feat: Add MCP server for Stack 2.9 tools exposure

Fix tool parameter signatures and improve consistency

feat: Add remaining RTMP tools (FileRead, FileWrite, Sleep, AskQuestion, Brief, TaskGet, TeamDelete, MCPTool, Worktree, SyntheticOutput)

feat: Add Tier 2 RTMP tools (TodoWrite, PlanMode, ConfigTool)

feat: Add FileEditTool, GrepTool, GlobTool (Tier 1 RTMP tools)⁠

feat: Add Phase 2 RTMP tools (web_fetch, messaging, remote_trigger, tool_discovery)

feat: Add RTMP tools implementation (Phase 1 & 2)⁠

Apr 8

feat: Add comprehensive enhancement modules for Stack 2.9⁠

Add persistent chat history to ~/.stack-2.9/chat_history.json

fix: remove feedback prompt from chat mode for cleaner UX

fix: update benchmark paths in stack-2.9-cli.py and remove deprecated cli/ module⁠

init

Add tools, fix web search, update model⁠

Apr 7

Fix Gradio/huggingface_hub version compatibility⁠

Apr 3

refactor: Clean up project structure - fewer root folders⁠

feat: add TypeScript modules and reorganize project structure⁠