Instructions to use winglian/qwen3-14b-math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use winglian/qwen3-14b-math with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("winglian/qwen3-14b-math")
model = AutoModelForCausalLM.from_pretrained("winglian/qwen3-14b-math")
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

vLLM

How to use winglian/qwen3-14b-math with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/winglian/qwen3-14b-math

SGLang

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

Docker Model Runner
How to use winglian/qwen3-14b-math with Docker Model Runner:
```
docker model run hf.co/winglian/qwen3-14b-math
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

See axolotl config

axolotl version: 0.10.0.dev0

base_model: Qwen/Qwen3-14B-Base

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

liger_rms_norm: true
liger_glu_activation: true

# torch_compile: true

dataloader_prefetch_factor: 4
dataloader_num_workers: 2
dataloader_pin_memory: true


chat_template: qwen3
datasets:
  - path: winglian/OpenThoughts-114k-math-correct
    type: chat_template
    split: train
    split_thinking: true
    eot_tokens:
      - "<|im_end|>"

dataset_prepared_path: last_run_prepared
val_set_size: 0.01
output_dir: ./outputs/model-out-math-14b

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project: kd-14b-tests
wandb_entity: axolotl-ai
wandb_name: sft-14b

gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 2
optimizer: adamw_torch_fused
adam_beta2: 0.99
lr_scheduler: rex
learning_rate: 1e-5
max_grad_norm: 0.1
save_safetensors: true

bf16: true
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
logging_steps: 1
flash_attention: true

warmup_steps: 100
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.1
special_tokens:
  eos_token: <|im_end|>
deepspeed: deepspeed_configs/zero2_torch_compile.json

outputs/model-out-math-14b

This model is a fine-tuned version of Qwen/Qwen3-14B-Base on the winglian/OpenThoughts-114k-math-correct dataset. It achieves the following results on the evaluation set:

Loss: 0.3439

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.99) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.5092	0.0016	1	0.5219
0.3572	0.2504	159	0.3653
0.3438	0.5008	318	0.3549
0.3345	0.7512	477	0.3491
0.3209	1.0016	636	0.3451
0.3013	1.2520	795	0.3465
0.2926	1.5024	954	0.3459
0.283	1.7528	1113	0.3439

Framework versions

Transformers 4.51.3
Pytorch 2.7.0+cu128
Datasets 3.5.1
Tokenizers 0.21.1

Downloads last month: 1,600

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for winglian/qwen3-14b-math

Base model

Qwen/Qwen3-14B-Base

Finetuned

(70)

this model

Quantizations

1 model

winglian
/

qwen3-14b-math

outputs/model-out-math-14b

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for winglian/qwen3-14b-math

Dataset used to train winglian/qwen3-14b-math