Instructions to use Sudnya/Qwen3-14B-legend-10K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sudnya/Qwen3-14B-legend-10K with Transformers:

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

pipe = pipeline("text-generation", model="Sudnya/Qwen3-14B-legend-10K")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sudnya/Qwen3-14B-legend-10K")
model = AutoModelForCausalLM.from_pretrained("Sudnya/Qwen3-14B-legend-10K", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Sudnya/Qwen3-14B-legend-10K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sudnya/Qwen3-14B-legend-10K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sudnya/Qwen3-14B-legend-10K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sudnya/Qwen3-14B-legend-10K

SGLang

How to use Sudnya/Qwen3-14B-legend-10K 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 "Sudnya/Qwen3-14B-legend-10K" \
    --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": "Sudnya/Qwen3-14B-legend-10K",
		"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 "Sudnya/Qwen3-14B-legend-10K" \
        --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": "Sudnya/Qwen3-14B-legend-10K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sudnya/Qwen3-14B-legend-10K with Docker Model Runner:
```
docker model run hf.co/Sudnya/Qwen3-14B-legend-10K
```

Qwen3-14B-legend-10K / README.md

Sudnya

Upload folder using huggingface_hub

8fd9ceb verified 6 months ago

preview code

Raw History Blame Contribute Delete

1.42 kB

	---
	license: apache-2.0
	language:
	- en
	tags:
	- text-to-legend
	- pure
	- legend
	- tokenformer
	- text-generation
	base_model: Qwen/Qwen3-14B
	library_name: transformers
	pipeline_tag: text-generation
	---

	# Legend Query Generation

	Fine-tuned from [Qwen/Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B) using
	[ScalarLM](https://github.com/supermassive-intelligence/scalarlm) with
	tokenformer adapters.

	## Model Details

	- Base model: Qwen/Qwen3-14B
	- Fine-tuning method: Tokenformer adapters (additive MLP adapters with learned attention)
	- Checkpoint step: 6656
	- Trained parameters: 442 (attention projections, layernorms, embeddings, tokenformer adapters)
	- Tokenformer config: num_heads=4, r=32

	## How to Use

	This model uses custom tokenformer adapter layers on top of the base model.
	It requires the `TokenformerAdapter` module for inference. Standard
	`AutoModelForCausalLM.from_pretrained` will not load the adapter weights
	correctly.

	See the [ScalarLM repository](https://github.com/supermassive-intelligence/scalarlm)
	for inference instructions.

	## Training

	Trained on Legend query generation data using the Qwen chat template format.

	Prompt format:
	```
	<\|im_start\|>user
	{question}

	Here is some schema information:
	{schema_text}

	First, plan how to write the query, then write it in a ```pure SQL``` code block.
	<\|im_end\|>
	<\|im_start\|>assistant
	```

	## License

	Apache 2.0