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

2aa22b3

1 Parent(s): 7a8afa9

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

Browse files

Files changed (1) hide show

chat.py +19 -6

chat.py CHANGED Viewed

@@ -1,6 +1,12 @@
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 print("Loading your fine-tuned Stack 2.9 model...")
 model = AutoModelForCausalLM.from_pretrained(
     '/Users/walidsobhi/stack-2-9-final-model',
@@ -11,8 +17,8 @@ tokenizer = AutoTokenizer.from_pretrained('/Users/walidsobhi/stack-2-9-final-mod
 print("✅ Ready!\n")
 # Generation settings
-MAX_TOKENS = 150
-TEMPERATURE = 0.3
 TOP_P = 0.9
 REP_PENALTY = 1.2
@@ -27,7 +33,9 @@ while True:
         if not prompt.strip():
             continue
-        inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
         outputs = model.generate(
             **inputs,
             max_new_tokens=MAX_TOKENS,
@@ -38,12 +46,17 @@ while True:
             pad_token_id=tokenizer.eos_token_id
         )
-        # Extract only the new tokens (skip the prompt)
         full_response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        response = full_response[len(prompt):].strip()
         # Stop at common stop points
-        for stop in ['\n\n\n', 'You:', 'AI:', 'User:', 'Assistant:']:
             if stop in response:
                 response = response.split(stop)[0].strip()

 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"""
 print("Loading your fine-tuned Stack 2.9 model...")
 model = AutoModelForCausalLM.from_pretrained(
     '/Users/walidsobhi/stack-2-9-final-model',
 print("✅ Ready!\n")
 # Generation settings
+MAX_TOKENS = 200
+TEMPERATURE = 0.4
 TOP_P = 0.9
 REP_PENALTY = 1.2
         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)
         outputs = model.generate(
             **inputs,
             max_new_tokens=MAX_TOKENS,
             pad_token_id=tokenizer.eos_token_id
         )
+        # Decode full response
         full_response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        # Extract only the assistant's response (after "Assistant:")
+        if "Assistant:" in full_response:
+            response = full_response.split("Assistant:")[-1].strip()
+        else:
+            response = full_response[len(full_prompt):].strip()
         # Stop at common stop points
+        for stop in ['\n\n\n', 'User:', 'You:']:
             if stop in response:
                 response = response.split(stop)[0].strip()