Instructions to use mdomina/Qwen3-Coder-Next-Cyber with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mdomina/Qwen3-Coder-Next-Cyber with Transformers:

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

pipe = pipeline("text-generation", model="mdomina/Qwen3-Coder-Next-Cyber")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mdomina/Qwen3-Coder-Next-Cyber")
model = AutoModelForCausalLM.from_pretrained("mdomina/Qwen3-Coder-Next-Cyber")
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 mdomina/Qwen3-Coder-Next-Cyber with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mdomina/Qwen3-Coder-Next-Cyber

SGLang

How to use mdomina/Qwen3-Coder-Next-Cyber 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 "mdomina/Qwen3-Coder-Next-Cyber" \
    --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": "mdomina/Qwen3-Coder-Next-Cyber",
		"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 "mdomina/Qwen3-Coder-Next-Cyber" \
        --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": "mdomina/Qwen3-Coder-Next-Cyber",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mdomina/Qwen3-Coder-Next-Cyber with Docker Model Runner:
```
docker model run hf.co/mdomina/Qwen3-Coder-Next-Cyber
```

Qwen3-Coder-Next-Cyber / args.json

mdomina

Qwen3-Coder-Next instruct + cyber experts via self-distillation (544 experts)

ab154df verified about 15 hours ago

Raw

History Blame Contribute Delete

6.1 kB

	{
	"use_ray": false,
	"ray_exp_name": null,
	"device_groups": null,
	"model": "/workspace/models/instruct-cyber-544-clean",
	"model_type": "qwen3_next",
	"model_revision": null,
	"task_type": "causal_lm",
	"torch_dtype": "bfloat16",
	"attn_impl": null,
	"experts_impl": "eager",
	"new_special_tokens": [],
	"num_labels": null,
	"problem_type": null,
	"rope_scaling": null,
	"device_map": null,
	"max_memory": {},
	"max_model_len": null,
	"local_repo_path": null,
	"init_strategy": null,
	"template": "qwen3_coder",
	"system": null,
	"max_length": 262144,
	"truncation_strategy": "delete",
	"max_pixels": null,
	"agent_template": null,
	"norm_bbox": null,
	"use_chat_template": true,
	"padding_side": "right",
	"padding_free": false,
	"loss_scale": "default",
	"sequence_parallel_size": 1,
	"is_binary_loss_scale": null,
	"template_backend": "swift",
	"response_prefix": null,
	"enable_thinking": null,
	"preserve_thinking": null,
	"add_non_thinking_prefix": true,
	"disable_ignore_empty_think": false,
	"dataset": [],
	"val_dataset": [],
	"cached_dataset": [],
	"cached_val_dataset": [],
	"split_dataset_ratio": 0.0,
	"data_seed": 42,
	"dataset_num_proc": 1,
	"load_from_cache_file": false,
	"dataset_shuffle": true,
	"val_dataset_shuffle": false,
	"streaming": false,
	"interleave_prob": null,
	"stopping_strategy": "first_exhausted",
	"shuffle_buffer_size": 1000,
	"download_mode": "reuse_dataset_if_exists",
	"columns": {},
	"strict": false,
	"remove_unused_columns": true,
	"disable_auto_column_mapping": false,
	"model_name": null,
	"model_author": null,
	"custom_dataset_info": [],
	"quant_method": null,
	"quant_bits": null,
	"hqq_axis": null,
	"bnb_4bit_compute_dtype": "bfloat16",
	"bnb_4bit_quant_type": "nf4",
	"bnb_4bit_use_double_quant": true,
	"bnb_4bit_quant_storage": null,
	"max_new_tokens": null,
	"temperature": null,
	"top_k": null,
	"top_p": null,
	"repetition_penalty": null,
	"num_beams": 1,
	"stream": false,
	"stop_words": [],
	"logprobs": false,
	"top_logprobs": null,
	"structured_outputs_regex": null,
	"tuner_backend": "peft",
	"tuner_type": "lora",
	"adapters": [],
	"external_plugins": [],
	"custom_register_path": [],
	"seed": 42,
	"model_kwargs": {},
	"enable_npu_model_patch": true,
	"load_args": true,
	"load_data_args": false,
	"packing": false,
	"packing_length": null,
	"packing_num_proc": 1,
	"packing_strategy": "binpack",
	"lazy_tokenize": false,
	"use_hf": false,
	"hub_token": null,
	"ddp_timeout": 18000000,
	"ddp_backend": null,
	"ignore_args_error": false,
	"use_swift_lora": false,
	"merge_lora": false,
	"safe_serialization": true,
	"max_shard_size": "5GB",
	"output_dir": "/workspace/models/final-hf",
	"quant_n_samples": 256,
	"quant_batch_size": 1,
	"group_size": 128,
	"to_cached_dataset": false,
	"template_mode": "train",
	"to_ollama": false,
	"to_mcore": false,
	"to_hf": true,
	"mcore_model": "/workspace/sd_out/v2-20260713-165316/checkpoint-1350",
	"mcore_adapter": null,
	"thread_count": null,
	"test_convert_precision": false,
	"test_convert_dtype": "float32",
	"push_to_hub": false,
	"hub_model_id": null,
	"hub_private_repo": false,
	"commit_message": "update files",
	"to_peft_format": false,
	"exist_ok": true,
	"swift_version": "4.4.1",
	"ckpt_dir": null,
	"rank": 0,
	"local_rank": 0,
	"global_world_size": 1,
	"local_world_size": 1,
	"model_suffix": "instruct-cyber-544-clean",
	"model_info": "ModelInfo(model_type='qwen3_next', model_dir='/workspace/models/instruct-cyber-544-clean', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'partial_rotary_factor': 0.25, 'rope_theta': 5000000, 'rope_type': 'default'}, is_moe_model=True, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
	"model_meta": "ModelMeta(model_type='qwen3_next', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-Next-80B-A3B-Instruct', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-Next-80B-A3B-Instruct-FP8', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_nothinking', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-Next-80B-A3B-Thinking', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-Next-80B-A3B-Thinking-FP8', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_thinking', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-Coder-Next-Base', hf_model_id='Qwen/Qwen3-Coder-Next-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-Coder-Next', hf_model_id='Qwen/Qwen3-Coder-Next', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-Coder-Next-FP8', hf_model_id='Qwen/Qwen3-Coder-Next-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_coder', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.register.ModelLoader'>, template=None, model_arch=None, mcore_model_type=None, architectures=['Qwen3NextForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57'], tags=[])",
	"model_dir": "/workspace/models/instruct-cyber-544-clean",
	"template_meta": "QwenTemplateMeta(template_type='qwen3_coder', prefix=[], prompt=['<\|im_start\|>user\\n{{QUERY}}<\|im_end\|>\\n<\|im_start\|>assistant\\n'], chat_sep=['<\|im_end\|>\\n'], suffix=['<\|im_end\|>\\n'], template_cls=<class 'swift.template.base.Template'>, system_prefix=['<\|im_start\|>system\\n{{SYSTEM}}<\|im_end\|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<\|endoftext\|>'], agent_template='qwen3_coder', is_thinking=False, thinking_prefix='', non_thinking_prefix='', history_thinking_prefix='')",
	"_val_dataset_exists": false,
	"hub": "<class 'swift.hub.hub.MSHub'>"
	}