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)

# 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
```

Stack-2-9-finetuned

Commit History

fix: restore previous model card with tools showcase

b64b6b0

walidsobhie-code Claude Opus 4.6 commited on Apr 9

release: prepare v1.0.0 for public release

13d8bea

walidsobhie-code commited on Apr 9

fix: add model card to repo root for HuggingFace display

bab1a6f

walidsobhie-code commited on Apr 9

reorganize: consolidate root level to 20 folders

b8e3e42

walidsobhie-code Claude Opus 4.6 commited on Apr 9

chore: Rename MCP server to Stack2.9

c7f1596

walidsobhie-code commited on Apr 9

fix: Correct FastMCP.add_tool signature for MCP server

5ddf5f9

walidsobhie-code commited on Apr 9

feat: Add MCP server for Stack 2.9 tools exposure

3de42e7

walidsobhie-code commited on Apr 9

Fix tool parameter signatures and improve consistency

359acf6

walidsobhie-code commited on Apr 9

Fix badges: remove broken loved badge, move badges to top

71c6bb8

walidsobhie-code commited on Apr 9

Update README with premium tools showcase, badges, and full tool list

1fba63f

walidsobhie-code commited on Apr 9

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

5dc5419

walidsobhie-code commited on Apr 9

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

31d646f

walidsobhie-code commited on Apr 9

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

2531078

walidsobhie-code commited on Apr 9

Add HuggingFace model card metadata

aeb76d4

walidsobhie-code commited on Apr 9

fix: Remove YAML from MODEL_CARD.md, rely on .modelcard.yml

feb5b3b

walidsobhie-code Claude Opus 4.6 commited on Apr 9

fix: Update model card YAML with model-index

692ebe1

walidsobhie-code Claude Opus 4.6 commited on Apr 9

fix: Clean up .modelcard.yml YAML metadata

0058968

walidsobhie-code Claude Opus 4.6 commited on Apr 9

chore: Update model card to match big brand style

e02416c

walidsobhie-code commited on Apr 9

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

e6853d3

walidsobhie-code commited on Apr 9

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

068bc7f

walidsobhie-code commited on Apr 9

feat: Add comprehensive enhancement modules for Stack 2.9

8f05ad1

walidsobhie-code commited on Apr 8

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

6807e9a

walidsobhie-code commited on Apr 8

fix: remove feedback prompt from chat mode for cleaner UX

31f5bef

walidsobhie-code commited on Apr 8

chore: update .gitignore to exclude archived files

faeab43

walidsobhie-code commited on Apr 8

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

fd9b9a2

walidsobhie-code commited on Apr 8

init

a9b0b85

walidsobhie-code commited on Apr 8

Add web UI, GitHub tool, enable all tools

faf9686

walidsobhie-code commited on Apr 8

Update README to remove unnecessary sections

002f981
unverified

Welly-code commited on Apr 8

Add tools, fix web search, update model

35697c2

walidsobhie-code commited on Apr 8

Exclude large jsonl files from repo

cee9266

walidsobhie-code commited on Apr 7

Add git lfs tracking for large jsonl files

29a776a

walidsobhie-code commited on Apr 7

Fix Gradio/huggingface_hub version compatibility

97fa10c

walidsobhie-code Claude Opus 4.6 commited on Apr 7

Add ddgs for free web search

729d832

walidsobhie-code commited on Apr 7

Add real web search with ddgs (DuckDuckGo HTML scraper, free, no API key)

0fbc572

walidsobhie-code commited on Apr 7

Fix search with DuckDuckGo API (proper JSON parsing)

35799ef

walidsobhie-code commited on Apr 7

Use local model instead of HF for faster loading

3c29912

walidsobhie-code commited on Apr 7

Add web search command (search:query) with DuckDuckGo API

40b1cc9

walidsobhie-code commited on Apr 7

Load model from HF: my-ai-stack/stack-2-9-finetuned

217c8d8

walidsobhie-code commited on Apr 7

Improve chat.py with system prompt and User/Assistant format

2aa22b3

walidsobhie-code commited on Apr 7

Add interactive chat script with improved generation settings

7a8afa9

walidsobhie-code commited on Apr 7

feat: add code completion generator and model registry tools

4ca507e

walidsobhie-code commited on Apr 5

feat: add 5000 more tool calling examples (total: 6500)

2e091e7

walidsobhie-code commited on Apr 5

feat: add training recipes for T4 QLoRA, A100, local training

e4ff487

walidsobhie-code commited on Apr 5

feat: add evaluation datasets (HumanEval 50, MBPP 100, Tool scenarios 50)

20a06fb

walidsobhie-code commited on Apr 5

feat: add production infrastructure - CI/CD, Docker, code quality, and monitoring

b5998ff

walidsobhie-code commited on Apr 5

feat: add inference API, quickstart guide, roadmap, and combined tool data

b03a8a0

walidsobhie-code commited on Apr 5

feat: add evaluation scripts, tool calling data generator, and 7B training configs

183b3b6

walidsobhie-code commited on Apr 5

fix: remove Google Drive mount (Colab-only) - use Kaggle output + GitHub push instead

a8f2981

walidsobhie-code commited on Apr 5

feat: add Google Drive auto-save to prevent losing model outputs

65c52b2

walidsobhie-code commited on Apr 5

feat: add model testing and evaluation scripts

f4b31b2

walidsobhie-code commited on Apr 5

Commit History

fix: restore previous model card with tools showcase b64b6b0

release: prepare v1.0.0 for public release 13d8bea

fix: add model card to repo root for HuggingFace display bab1a6f

reorganize: consolidate root level to 20 folders b8e3e42

chore: Rename MCP server to Stack2.9 c7f1596

fix: Correct FastMCP.add_tool signature for MCP server 5ddf5f9

feat: Add MCP server for Stack 2.9 tools exposure 3de42e7

Fix tool parameter signatures and improve consistency 359acf6

Fix badges: remove broken loved badge, move badges to top 71c6bb8

Update README with premium tools showcase, badges, and full tool list 1fba63f

feat: Add remaining RTMP tools (FileRead, FileWrite, Sleep, AskQuestion, Brief, TaskGet, TeamDelete, MCPTool, Worktree, SyntheticOutput) 5dc5419

feat: Add Tier 2 RTMP tools (TodoWrite, PlanMode, ConfigTool) 31d646f

feat: Add FileEditTool, GrepTool, GlobTool (Tier 1 RTMP tools) 2531078

Add HuggingFace model card metadata aeb76d4

fix: Remove YAML from MODEL_CARD.md, rely on .modelcard.yml feb5b3b

fix: Update model card YAML with model-index 692ebe1

fix: Clean up .modelcard.yml YAML metadata 0058968

chore: Update model card to match big brand style e02416c

feat: Add Phase 2 RTMP tools (web_fetch, messaging, remote_trigger, tool_discovery) e6853d3

feat: Add RTMP tools implementation (Phase 1 & 2) 068bc7f

feat: Add comprehensive enhancement modules for Stack 2.9 8f05ad1

Add persistent chat history to ~/.stack-2.9/chat_history.json 6807e9a

fix: remove feedback prompt from chat mode for cleaner UX 31f5bef

chore: update .gitignore to exclude archived files faeab43

fix: update benchmark paths in stack-2.9-cli.py and remove deprecated cli/ module fd9b9a2

init a9b0b85

Add web UI, GitHub tool, enable all tools faf9686

Update README to remove unnecessary sections 002f981 unverified

Add tools, fix web search, update model 35697c2

Exclude large jsonl files from repo cee9266

Add git lfs tracking for large jsonl files 29a776a

Fix Gradio/huggingface_hub version compatibility 97fa10c

Add ddgs for free web search 729d832

Add real web search with ddgs (DuckDuckGo HTML scraper, free, no API key) 0fbc572

Fix search with DuckDuckGo API (proper JSON parsing) 35799ef

Use local model instead of HF for faster loading 3c29912

Add web search command (search:query) with DuckDuckGo API 40b1cc9

Load model from HF: my-ai-stack/stack-2-9-finetuned 217c8d8

Improve chat.py with system prompt and User/Assistant format 2aa22b3

Add interactive chat script with improved generation settings 7a8afa9

feat: add code completion generator and model registry tools 4ca507e

feat: add 5000 more tool calling examples (total: 6500) 2e091e7

feat: add training recipes for T4 QLoRA, A100, local training e4ff487

feat: add evaluation datasets (HumanEval 50, MBPP 100, Tool scenarios 50) 20a06fb

feat: add production infrastructure - CI/CD, Docker, code quality, and monitoring b5998ff

feat: add inference API, quickstart guide, roadmap, and combined tool data b03a8a0

feat: add evaluation scripts, tool calling data generator, and 7B training configs 183b3b6

fix: remove Google Drive mount (Colab-only) - use Kaggle output + GitHub push instead a8f2981

feat: add Google Drive auto-save to prevent losing model outputs 65c52b2

feat: add model testing and evaluation scripts f4b31b2

fix: restore previous model card with tools showcase

b64b6b0

release: prepare v1.0.0 for public release

13d8bea

fix: add model card to repo root for HuggingFace display

bab1a6f

reorganize: consolidate root level to 20 folders

b8e3e42

chore: Rename MCP server to Stack2.9

c7f1596

fix: Correct FastMCP.add_tool signature for MCP server

5ddf5f9

feat: Add MCP server for Stack 2.9 tools exposure

3de42e7

Fix tool parameter signatures and improve consistency

359acf6

Fix badges: remove broken loved badge, move badges to top

71c6bb8

Update README with premium tools showcase, badges, and full tool list

1fba63f

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

5dc5419

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

31d646f

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

2531078

Add HuggingFace model card metadata

aeb76d4

fix: Remove YAML from MODEL_CARD.md, rely on .modelcard.yml

feb5b3b

fix: Update model card YAML with model-index

692ebe1

fix: Clean up .modelcard.yml YAML metadata

0058968

chore: Update model card to match big brand style

e02416c

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

e6853d3

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

068bc7f

feat: Add comprehensive enhancement modules for Stack 2.9

8f05ad1

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

6807e9a

fix: remove feedback prompt from chat mode for cleaner UX

31f5bef

chore: update .gitignore to exclude archived files

faeab43

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

fd9b9a2

init

a9b0b85

Add web UI, GitHub tool, enable all tools

faf9686

Update README to remove unnecessary sections

002f981
unverified

Add tools, fix web search, update model

35697c2

Exclude large jsonl files from repo

cee9266

Add git lfs tracking for large jsonl files

29a776a

Fix Gradio/huggingface_hub version compatibility

97fa10c

Add ddgs for free web search

729d832

Add real web search with ddgs (DuckDuckGo HTML scraper, free, no API key)

0fbc572

Fix search with DuckDuckGo API (proper JSON parsing)

35799ef

Use local model instead of HF for faster loading

3c29912

Add web search command (search:query) with DuckDuckGo API

40b1cc9

Load model from HF: my-ai-stack/stack-2-9-finetuned

217c8d8

Improve chat.py with system prompt and User/Assistant format

2aa22b3

Add interactive chat script with improved generation settings

7a8afa9

feat: add code completion generator and model registry tools

4ca507e

feat: add 5000 more tool calling examples (total: 6500)

2e091e7

feat: add training recipes for T4 QLoRA, A100, local training

e4ff487

feat: add evaluation datasets (HumanEval 50, MBPP 100, Tool scenarios 50)

20a06fb

feat: add production infrastructure - CI/CD, Docker, code quality, and monitoring

b5998ff

feat: add inference API, quickstart guide, roadmap, and combined tool data

b03a8a0

feat: add evaluation scripts, tool calling data generator, and 7B training configs

183b3b6

fix: remove Google Drive mount (Colab-only) - use Kaggle output + GitHub push instead

a8f2981

feat: add Google Drive auto-save to prevent losing model outputs

65c52b2

feat: add model testing and evaluation scripts

f4b31b2