Instructions to use yotisstudios/Warrior-Qwen3.5-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yotisstudios/Warrior-Qwen3.5-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="yotisstudios/Warrior-Qwen3.5-4B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("yotisstudios/Warrior-Qwen3.5-4B")
model = AutoModelForMultimodalLM.from_pretrained("yotisstudios/Warrior-Qwen3.5-4B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yotisstudios/Warrior-Qwen3.5-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yotisstudios/Warrior-Qwen3.5-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yotisstudios/Warrior-Qwen3.5-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/yotisstudios/Warrior-Qwen3.5-4B

SGLang

How to use yotisstudios/Warrior-Qwen3.5-4B 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 "yotisstudios/Warrior-Qwen3.5-4B" \
    --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": "yotisstudios/Warrior-Qwen3.5-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "yotisstudios/Warrior-Qwen3.5-4B" \
        --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": "yotisstudios/Warrior-Qwen3.5-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use yotisstudios/Warrior-Qwen3.5-4B with Docker Model Runner:
```
docker model run hf.co/yotisstudios/Warrior-Qwen3.5-4B
```

Warrior-Qwen3.5-4B

Training Configuration

Parameter	Value
Training Mode	SFT
Base Model	`Lazarus-Ai/ReAligned-Qwen3.5-4B`
Learning Rate	0.0002
Epochs	2
Batch Size	1
Gradient Accumulation	16
Effective Batch Size	16
Max Sequence Length	8192
Optimizer	paged_adamw_8bit
LR Scheduler	cosine
Warmup Ratio	0.05
Weight Decay	0.01
Max Grad Norm	0.3
Seed	42
LoRA Rank (r)	64
LoRA Alpha	128
LoRA Dropout	0.05
Target Modules	up_proj, down_proj, gate_proj, k_proj, q_proj, v_proj, o_proj
Quantization	4-bit (NF4)
GPU	NVIDIA GB10

Reproduce this training run

This model was trained with Merlina. Credentials are not included — Merlina will use your own HF_TOKEN and WANDB_API_KEY from .env or the form.

Paste this code into Merlina's Load Configuration → From Code to rebuild the exact training setup:

merlina-config-v1:H4sIACtMgGoC_61VTY_jNgz9K4HOScbxZgczuU0L9NKZw3a36KEoBMambTWSpdVHstnF_PeSspVk0C-g6I2maOrx8ZH6JqTBCC1EELtvYgSDYid-Ae-V9asPJxzfrd-vtt-JpWgxNF65qOxIIZ88qFGN_aKxY6f65IEPFmEAj-2i89YsYPGCXqsRVpGDyW1si3pNuSL0Qex-_W0pQjOgobuFmWLv4px4NSUWJUQe0Yd892ZZgq8-Ua_rdSVel2IPAWW-iLzP8BV8CqsndfcTPmnVE4q3VdkUXYrynwpPlFBbTyCjT7gUbEsvdvfb2QbtBjrd1A-zo_XWUWKxq9bVe67W9xgZVNLIdYvkpPP2d2bVnsZi9xCx2IdifC7GsRh2Moi8OaOMVgY44sRoRhAhHGQ8Oy7q-6efPz49y-cX-lcjeGZXUr8w46uqeinGZCQ62wyErmYOYzPIoL5iZrv30Coco4SmSSbp3GoZIjoK39wTDvgiNY59HMTuYfNYTx5CaVy8HGyqepshoy7IIEXLaphbnttG7tBF8u6RNVmtCYCGPf0UjLVxoLiMm-kyJkcQxSzggJE1HGzyDV6tctmQ-p5-7oAOl8JTuVK15D_bqEKIqVU23BUBfPzhEyvPaUU5J4D8HT2CyQg60AFvPPINZ8RqRVqEtlXMFRD4jGUWPR4vnv8VJ6X9Dyg76w1k6iarAIn2gCNFesqJI-w1QST6D7eZuYOyxYhNvDnkOXktvZ5H699HkQae5pnmBEOAnmRdgE1j12KbqM4mC3e-PvuQpMhy7s90zSy6ZrABuWURQ5zrJdGQlsKZhGuKOGfFdUprieQ4_40cqZqASG3YzuLmmZAjAeS875biBN7QVOc1WOZ-avM0JtW6njbJdq8uJfH3CcZ2fynIpTDwOA_p6qNl108bSO6ROEFJPFhoS5ah43CqSB1vuSE3Ux8cC-mtfLihX5wlrvs-dZc_-EN-TjBOEsib6sNW_ihfeNkcEF2Ol53b3F-1NaSuI2lcJnACdULVD5Gk0cC5UK-95F3OO8sXkTU20NMgbpYMRTQHZ9UYL1ripZaH4rJ0aAvSS2RYnSWTI820kp4yc5IPTDLPHxjJe2TDEB5vHHV2PBYXJVU6vy24qh6yk-YvWi898ro7Yr75KvvLeWiAinfgiepIo_LniFkZJKn4F6eZoHkbr6r1m7sbrRxNlccwWE3t3vDWgxhHqYzTaIgtmJ_jeZPmp0r1jGPijdLQvDekdaWv0sjCzCsc_BUUbfaoZO_S7TzlxK9_AKT0_tMnCAAA

Prefer JSON? The same config, expanded

Save this to data/configs/<name>.json, or import it via the Load Configuration dialog.

{
  "_metadata": {
    "name": "Warrior-Qwen3.5-4B",
    "description": "Training configuration shared from a Merlina-trained model.",
    "tags": [],
    "schema": "merlina/training-config",
    "schema_version": 1,
    "merlina_version": "2.2.0"
  },
  "base_model": "Lazarus-Ai/ReAligned-Qwen3.5-4B",
  "output_name": "Warrior-Qwen3.5-4B",
  "use_lora": true,
  "lora_r": 64,
  "lora_alpha": 128,
  "lora_dropout": 0.05,
  "target_modules": [
    "up_proj",
    "down_proj",
    "gate_proj",
    "k_proj",
    "q_proj",
    "v_proj",
    "o_proj"
  ],
  "modules_to_save": [],
  "lora_task_type": "CAUSAL_LM",
  "learning_rate": 0.0002,
  "num_epochs": 2,
  "batch_size": 1,
  "gradient_accumulation_steps": 16,
  "max_length": 8192,
  "max_prompt_length": 1024,
  "model_type": "auto",
  "training_mode": "sft",
  "beta": 0.1,
  "label_smoothing": 0.0,
  "gamma": 0.5,
  "dataset": {
    "source": {
      "source_type": "huggingface",
      "repo_id": "yotisstudios/Warrior-SFT",
      "split": "train",
      "streaming": false,
      "streaming_batch_size": 10000
    },
    "additional_sources": [],
    "eval_source": {
      "source_type": "huggingface",
      "repo_id": "yotisstudios/Warrior-SFT",
      "split": "val",
      "streaming": false,
      "streaming_batch_size": 10000
    },
    "format": {
      "format_type": "tokenizer",
      "enable_thinking": false,
      "auto_detect_thinking": true
    },
    "model_name": "Lazarus-Ai/ReAligned-Qwen3.5-4B",
    "convert_messages_format": true,
    "deduplicate": false,
    "dedupe_strategy": "prompt_chosen",
    "test_size": 0.01,
    "system_prompt_mode": "fill_empty",
    "training_mode": "sft"
  },
  "seed": 42,
  "max_grad_norm": 0.3,
  "warmup_ratio": 0.05,
  "eval_steps": 0.2,
  "use_4bit": true,
  "use_wandb": false,
  "push_to_hub": false,
  "merge_lora_before_upload": true,
  "hf_hub_private": false,
  "hf_namespace": "yotisstudios",
  "export_gguf": false,
  "gguf_quant_types": [
    "Q4_K_M"
  ],
  "keep_gguf_fp16": false,
  "shuffle_dataset": true,
  "weight_decay": 0.01,
  "lr_scheduler_type": "cosine",
  "gradient_checkpointing": true,
  "logging_steps": 1,
  "optimizer_type": "paged_adamw_8bit",
  "adam_beta1": 0.9,
  "adam_beta2": 0.999,
  "adam_epsilon": 1e-08,
  "adafactor_relative_step": false,
  "adafactor_scale_parameter": false,
  "adafactor_warmup_init": false,
  "adafactor_decay_rate": -0.8,
  "adafactor_clip_threshold": 1.0,
  "attn_implementation": "auto",
  "use_liger": true,
  "torch_compile": false,
  "eval_on_start": false,
  "multi_gpu_strategy": "auto"
}