Instructions to use winglian/qwen25-coder-triton with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use winglian/qwen25-coder-triton with Transformers:

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

pipe = pipeline("text-generation", model="winglian/qwen25-coder-triton")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("winglian/qwen25-coder-triton")
model = AutoModelForCausalLM.from_pretrained("winglian/qwen25-coder-triton")
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/qwen25-coder-triton with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "winglian/qwen25-coder-triton"
# 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/qwen25-coder-triton",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/winglian/qwen25-coder-triton

SGLang

How to use winglian/qwen25-coder-triton 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/qwen25-coder-triton" \
    --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/qwen25-coder-triton",
		"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/qwen25-coder-triton" \
        --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/qwen25-coder-triton",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use winglian/qwen25-coder-triton with Docker Model Runner:
```
docker model run hf.co/winglian/qwen25-coder-triton
```

See axolotl config

axolotl version: 0.8.0

base_model: Qwen/Qwen2.5-Coder-14B
strict: false       

plugins:             
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
  - axolotl.integrations.liger.LigerPlugin
                                                               
cut_cross_entropy: true
  # liger_rope: true
liger_rms_norm: true
liger_layer_norm: true

# gemma3 doesn't seem to play nice with ddp
ddp_find_unused_parameters: true
                                                               
chat_template: qwen_25
datasets:           
  - path: winglian/gpumode-py2triton-reasoning
    type: chat_template
                                                               
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./outputs/out-fft
save_safetensors: true
save_only_model: true

sequence_len: 32768
sample_packing: true 
pad_to_sequence_len: true
                                                               
sequence_parallel_degree: 1

# unfrozen_parameters:
#   - language_model.model

wandb_project: qwen25-kernel-llm
wandb_entity: axolotl-ai
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 3
num_epochs: 3
optimizer: adamw_8bit
lr_scheduler: rex
learning_rate: 3.0e-6
lr_groups:
  - name: embeddings
    lr: 3.0e-5
    modules:
      - lm_head
      - embed_tokens

train_on_inputs: false
group_by_length: false
bf16: true
tf32: true

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

warmup_ratio: 0.1
evals_per_epoch: 1
saves_per_epoch: 1
  # deepspeed: deepspeed_configs/zero1.json
weight_decay: 0.0
deepspeed: deepspeed_configs/zero1.json
tokens:
 - <think>
 - </think>
special_tokens:
  eos_token: <|im_end|>
fix_untrained_tokens:
  - 151665
  - 151666

outputs/out-fft

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-14B on the winglian/gpumode-py2triton-reasoning dataset.

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: 3e-06
train_batch_size: 3
eval_batch_size: 3
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 24
total_eval_batch_size: 24
optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 27
num_epochs: 3.0

Training results

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1

Downloads last month: 2

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for winglian/qwen25-coder-triton

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-Coder-14B

Finetuned

(16)

this model