Instructions to use prithivMLmods/Octans-Qwen3-UI-Code-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Octans-Qwen3-UI-Code-4B with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Octans-Qwen3-UI-Code-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Octans-Qwen3-UI-Code-4B")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Octans-Qwen3-UI-Code-4B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use prithivMLmods/Octans-Qwen3-UI-Code-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Octans-Qwen3-UI-Code-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Octans-Qwen3-UI-Code-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Octans-Qwen3-UI-Code-4B

SGLang

How to use prithivMLmods/Octans-Qwen3-UI-Code-4B 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 "prithivMLmods/Octans-Qwen3-UI-Code-4B" \
    --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": "prithivMLmods/Octans-Qwen3-UI-Code-4B",
		"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 "prithivMLmods/Octans-Qwen3-UI-Code-4B" \
        --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": "prithivMLmods/Octans-Qwen3-UI-Code-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/Octans-Qwen3-UI-Code-4B with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Octans-Qwen3-UI-Code-4B
```

prithivMLmods commited on Oct 10, 2025

Commit

e82192d

verified ·

1 Parent(s): 5be599f

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -1

README.md CHANGED Viewed

@@ -2,8 +2,19 @@
 license: apache-2.0
 base_model:
 - prithivMLmods/Muscae-Qwen3-UI-Code-4B
 ---
 # **Octans-Qwen3-UI-Code-4B**
 > **Octans-Qwen3-UI-Code-4B** is an **optimized successor** of **Muscae-Qwen3-UI-Code-4B**, fine-tuned for enhanced **UI reasoning precision**, **layout structuring**, and **frontend code synthesis**.
@@ -87,4 +98,4 @@ print(response)
 * Research-focused model – not fine-tuned for production-critical pipelines
 * Specialized for **UI code** – not suitable for general text generation or long-form reasoning
 * May exhibit variability with **cross-framework** or **overextended prompts**
-* Prioritizes **code structure and logic clarity** over aesthetic or creative expression

 license: apache-2.0
 base_model:
 - prithivMLmods/Muscae-Qwen3-UI-Code-4B
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- trl
+- text-generation-inference
+- code
+- ui
 ---
+![1](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/gAI7CTwtuWea7lSqzxtzT.png)
 # **Octans-Qwen3-UI-Code-4B**
 > **Octans-Qwen3-UI-Code-4B** is an **optimized successor** of **Muscae-Qwen3-UI-Code-4B**, fine-tuned for enhanced **UI reasoning precision**, **layout structuring**, and **frontend code synthesis**.
 * Research-focused model – not fine-tuned for production-critical pipelines
 * Specialized for **UI code** – not suitable for general text generation or long-form reasoning
 * May exhibit variability with **cross-framework** or **overextended prompts**
+* Prioritizes **code structure and logic clarity** over aesthetic or creative expression.