Instructions to use my-ai-stack/Stack-X-Ultimate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use my-ai-stack/Stack-X-Ultimate with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="my-ai-stack/Stack-X-Ultimate")
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-X-Ultimate")
model = AutoModelForCausalLM.from_pretrained("my-ai-stack/Stack-X-Ultimate", 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-X-Ultimate 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-X-Ultimate"
# 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-X-Ultimate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/my-ai-stack/Stack-X-Ultimate

SGLang

How to use my-ai-stack/Stack-X-Ultimate 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-X-Ultimate" \
    --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-X-Ultimate",
		"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-X-Ultimate" \
        --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-X-Ultimate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use my-ai-stack/Stack-X-Ultimate with Docker Model Runner:
```
docker model run hf.co/my-ai-stack/Stack-X-Ultimate
```

Walid Sobhi commited on Apr 26

Commit

f631730

verified ·

1 Parent(s): c653ee6

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +34 -1

README.md CHANGED Viewed

@@ -1,3 +1,35 @@
 # Stack X Ultimate
 **A state-of-the-art agentic coding model built on Qwen2.5-Coder-3B-Instruct**
@@ -109,7 +141,8 @@ tokenizer = AutoTokenizer.from_pretrained("my-ai-stack/Stack-X-Ultimate-Merged")
 Base model:        Qwen/Qwen2.5-Coder-3B-Instruct
 LoRA rank:         32 (59M trainable params)
 LoRA alpha:        64
-Target modules:    q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
 Learning rate:     2e-4 (cosine decay)
 Warmup:            150 steps
 Batch size:        1 × gradient_accumulation=16

+---
+base_model: Qwen/Qwen2.5-Coder-3B-Instruct
+datasets:
+  - nvidia/Nemotron-Agentic-v1
+  - my-ai-stack/Stack-4.0-Dataset
+pipeline_tag: causal-lm
+license: apache-2.0
+tags:
+  - code-generation
+  - agentic-ai
+  - tool-use
+  - lora
+  - qwen
+  - python
+  - coding-assistant
+  - transformers
+  - peft
+  - 3b-parameter-model
+model_index:
+  - name: Stack X Ultimate
+    results:
+      - task:
+          type: text-generation
+          description: Agentic coding assistant with tool-use capabilities
+        dataset:
+          type: openai/openai_humaneval
+          name: HumanEval
+        metrics:
+          - type: pass@1
+            value: TBD
+---
 # Stack X Ultimate
 **A state-of-the-art agentic coding model built on Qwen2.5-Coder-3B-Instruct**
 Base model:        Qwen/Qwen2.5-Coder-3B-Instruct
 LoRA rank:         32 (59M trainable params)
 LoRA alpha:        64
+Target modules:    q_proj, k_proj, v_proj, o_proj,
+                   gate_proj, up_proj, down_proj
 Learning rate:     2e-4 (cosine decay)
 Warmup:            150 steps
 Batch size:        1 × gradient_accumulation=16