Instructions to use DoppelReflEx/Qwen3-14B-Dawnwhisper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DoppelReflEx/Qwen3-14B-Dawnwhisper with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("DoppelReflEx/Qwen3-14B-Dawnwhisper")
model = AutoModelForMultimodalLM.from_pretrained("DoppelReflEx/Qwen3-14B-Dawnwhisper")
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 DoppelReflEx/Qwen3-14B-Dawnwhisper with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DoppelReflEx/Qwen3-14B-Dawnwhisper

SGLang

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

Docker Model Runner
How to use DoppelReflEx/Qwen3-14B-Dawnwhisper with Docker Model Runner:
```
docker model run hf.co/DoppelReflEx/Qwen3-14B-Dawnwhisper
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

What is this?

Qwen 3 14B merge, test with some languages and the result is good for this model styles. English and Chinese is the main languages that perform best, following by Japanese and Vietnamese and Russia. Other languages haven't tested.

Good for co-writing btw, roleplay is also good but it's talk for user several times.

ChatML is the template. You should add `/no_think` or any method to disable thinking process for best result in writing.

Configuration

The following YAML configuration was used to produce this model:


models:
  - model: nbeerbower/Vitus-Qwen3-14B
    parameters:
      density: 0.9
      weight: 1
  - model: ReadyArt/The-Omega-Directive-Qwen3-14B-v1.1
    parameters:
      density: 0.8
      weight: 0.8
merge_method: dare_ties
base_model: nbeerbower/Vitus-Qwen3-14B
parameters:
  normalize: true
  rescale: true
tokenizer_source: nbeerbower/Vitus-Qwen3-14B
dtype: bfloat16