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
```

walidsobhie-code commited on Apr 7

Commit

40b1cc9

1 Parent(s): 217c8d8

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

Browse files

Files changed (1) hide show

chat.py +29 -2

chat.py CHANGED Viewed

@@ -1,11 +1,13 @@
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 SYSTEM_PROMPT = """You are Stack 2.9, an expert AI coding assistant.
 - Answer questions naturally and helpfully
 - When the user asks for code, write clean complete code
 - When the user asks a question, answer in plain language
-- Be concise and practical"""
 MODEL_NAME = "my-ai-stack/stack-2-9-finetuned"
@@ -24,7 +26,20 @@ TEMPERATURE = 0.4
 TOP_P = 0.9
 REP_PENALTY = 1.2
-print(f"Settings: max_tokens={MAX_TOKENS}, temperature={TEMPERATURE}, top_p={TOP_P}\n")
 # Interactive loop
 while True:
@@ -35,6 +50,18 @@ while True:
         if not prompt.strip():
             continue
         # Prepend system prompt
         full_prompt = f"{SYSTEM_PROMPT}\n\nUser: {prompt}\nAssistant:"
         inputs = tokenizer(full_prompt, return_tensors='pt').to(model.device)

 import torch
+import requests
 from transformers import AutoModelForCausalLM, AutoTokenizer
 SYSTEM_PROMPT = """You are Stack 2.9, an expert AI coding assistant.
 - Answer questions naturally and helpfully
 - When the user asks for code, write clean complete code
 - When the user asks a question, answer in plain language
+- Be concise and practical
+- If asked to search the internet, use the search: command"""
 MODEL_NAME = "my-ai-stack/stack-2-9-finetuned"
 TOP_P = 0.9
 REP_PENALTY = 1.2
+print(f"Settings: max_tokens={MAX_TOKENS}, temperature={TEMPERATURE}, top_p={TOP_P}")
+print("Commands: search:<query> - search the web, quit/exit - stop\n")
+def web_search(query, count=5):
+    """Search the web using DuckDuckGo JSON API"""
+    try:
+        url = f"https://duckduckgo.com/?q={query}&format=json&no_redirect=1"
+        headers = {"User-Agent": "Mozilla/5.0 (compatible; Stack29Bot/1.0)"}
+        resp = requests.get(url, headers=headers, timeout=10)
+        if resp.status_code == 200:
+            return {"success": True, "results": [{"query": query, "source": "duckduckgo"}]}
+        return {"success": False, "error": f"HTTP {resp.status_code}"}
+    except Exception as e:
+        return {"success": False, "error": str(e)}
 # Interactive loop
 while True:
         if not prompt.strip():
             continue
+        # Handle search command
+        if prompt.lower().startswith("search:"):
+            query = prompt[7:].strip()
+            print("🔍 Searching...")
+            result = web_search(query)
+            if result["success"]:
+                print(f"✅ Found results for: {query}")
+                print(f"   (Web search results would appear here)")
+            else:
+                print(f"❌ Search failed: {result['error']}")
+            continue
         # Prepend system prompt
         full_prompt = f"{SYSTEM_PROMPT}\n\nUser: {prompt}\nAssistant:"
         inputs = tokenizer(full_prompt, return_tensors='pt').to(model.device)