Instructions to use khadim-hussain/qwen3-14b-stem-qa-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use khadim-hussain/qwen3-14b-stem-qa-merged with Transformers:

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

pipe = pipeline("text-generation", model="khadim-hussain/qwen3-14b-stem-qa-merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("khadim-hussain/qwen3-14b-stem-qa-merged")
model = AutoModelForCausalLM.from_pretrained("khadim-hussain/qwen3-14b-stem-qa-merged", 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 khadim-hussain/qwen3-14b-stem-qa-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "khadim-hussain/qwen3-14b-stem-qa-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "khadim-hussain/qwen3-14b-stem-qa-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/khadim-hussain/qwen3-14b-stem-qa-merged

SGLang

How to use khadim-hussain/qwen3-14b-stem-qa-merged 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 "khadim-hussain/qwen3-14b-stem-qa-merged" \
    --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": "khadim-hussain/qwen3-14b-stem-qa-merged",
		"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 "khadim-hussain/qwen3-14b-stem-qa-merged" \
        --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": "khadim-hussain/qwen3-14b-stem-qa-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use khadim-hussain/qwen3-14b-stem-qa-merged with Docker Model Runner:
```
docker model run hf.co/khadim-hussain/qwen3-14b-stem-qa-merged
```

Qwen3-14B STEM Q&A (Merged)

This is the merged full model (LoRA weights merged into base model) for standalone use.

Author: Khadim Hussain

For the LoRA adapter version (smaller download), see: khadim-hussain/qwen3-14b-stem-qa

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "khadim-hussain/qwen3-14b-stem-qa-merged",
    torch_dtype="auto",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("khadim-hussain/qwen3-14b-stem-qa-merged")

prompt = "<|im_start|>user\nWhat is DNA?<|im_end|>\n<|im_start|>assistant\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Model Details

Base Model: Qwen/Qwen3-14B
Type: Merged (LoRA merged into base weights)
Size: ~28GB (bf16)
Training: QLoRA fine-tuning on STEM Q&A dataset

Training Metrics

Metric	Value
Train Loss	0.461
Eval Loss	0.692
Training Examples	4,260
Evaluation Examples	474

Acknowledgments

Qwen Team (Alibaba) - Qwen3-14B base model
Unsloth - Fast fine-tuning framework
Hugging Face - TRL, PEFT, Transformers

License

Apache 2.0 (inherited from Qwen3)

Downloads last month: 5

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for khadim-hussain/qwen3-14b-stem-qa-merged

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Finetuned

(318)

this model