Instructions to use llamafactory/tiny-random-Llama-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llamafactory/tiny-random-Llama-4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="llamafactory/tiny-random-Llama-4")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("llamafactory/tiny-random-Llama-4")
model = AutoModelForMultimodalLM.from_pretrained("llamafactory/tiny-random-Llama-4", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use llamafactory/tiny-random-Llama-4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llamafactory/tiny-random-Llama-4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llamafactory/tiny-random-Llama-4",
		"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/llamafactory/tiny-random-Llama-4

SGLang

How to use llamafactory/tiny-random-Llama-4 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 "llamafactory/tiny-random-Llama-4" \
    --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": "llamafactory/tiny-random-Llama-4",
		"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 "llamafactory/tiny-random-Llama-4" \
        --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": "llamafactory/tiny-random-Llama-4",
		"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 llamafactory/tiny-random-Llama-4 with Docker Model Runner:
```
docker model run hf.co/llamafactory/tiny-random-Llama-4
```

tiny-random-Llama-4 / config.json

kingsley01

Update config.json

4021658 verified 6 months ago

Raw History Blame Contribute Delete

2.03 kB

{
  "architectures": [
    "Llama4ForConditionalGeneration"
  ],
  "boi_token_index": 200080,
  "eoi_token_index": 200081,
  "image_token_index": 200092,
  "model_type": "llama4",
  "text_config": {
    "_attn_implementation_autoset": true,
    "attention_bias": false,
    "attention_chunk_size": 8192,
    "attention_dropout": 0.0,
    "attn_scale": 0.1,
    "attn_temperature_tuning": true,
    "floor_scale": 8192,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 512,
    "initializer_range": 0.02,
    "interleave_moe_layer_step": 1,
    "intermediate_size": 1024,
    "intermediate_size_mlp": 1024,
    "max_position_embeddings": 131072,
    "model_type": "llama4_text",
    "moe_layers": [
      0,
      1,
      2,
      3
    ],
    "no_rope_layers": [
      1,
      1,
      1,
      0
    ],
    "num_attention_heads": 8,
    "num_experts_per_tok": 1,
    "num_hidden_layers": 4,
    "num_key_value_heads": 2,
    "num_local_experts": 2,
    "output_router_logits": false,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 500000,
    "router_aux_loss_coef": 0.001,
    "router_jitter_noise": 0.0,
    "use_cache": true,
    "use_qk_norm": true,
    "vocab_size": 202048
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.51.0",
  "vision_config": {
    "_attn_implementation_autoset": true,
    "attention_dropout": 0.0,
    "hidden_act": "gelu",
    "hidden_size": 1408,
    "image_size": 336,
    "initializer_range": 0.02,
    "intermediate_size": 5632,
    "model_type": "llama4_vision_model",
    "multi_modal_projector_bias": false,
    "norm_eps": 1e-05,
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 4,
    "patch_size": 14,
    "pixel_shuffle_ratio": 0.5,
    "projector_dropout": 0.0,
    "projector_input_dim": 4096,
    "projector_output_dim": 4096,
    "rope_theta": 10000,
    "vision_feature_layer": -1,
    "vision_feature_select_strategy": "default",
    "vision_output_dim": 4096
  }
}

	{
	"architectures": [
	"Llama4ForConditionalGeneration"
	],
	"boi_token_index": 200080,
	"eoi_token_index": 200081,
	"image_token_index": 200092,
	"model_type": "llama4",
	"text_config": {
	"_attn_implementation_autoset": true,
	"attention_bias": false,
	"attention_chunk_size": 8192,
	"attention_dropout": 0.0,
	"attn_scale": 0.1,
	"attn_temperature_tuning": true,
	"floor_scale": 8192,
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 512,
	"initializer_range": 0.02,
	"interleave_moe_layer_step": 1,
	"intermediate_size": 1024,
	"intermediate_size_mlp": 1024,
	"max_position_embeddings": 131072,
	"model_type": "llama4_text",
	"moe_layers": [
	0,
	1,
	2,
	3
	],
	"no_rope_layers": [
	1,
	1,
	1,
	0
	],
	"num_attention_heads": 8,
	"num_experts_per_tok": 1,
	"num_hidden_layers": 4,
	"num_key_value_heads": 2,
	"num_local_experts": 2,
	"output_router_logits": false,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 500000,
	"router_aux_loss_coef": 0.001,
	"router_jitter_noise": 0.0,
	"use_cache": true,
	"use_qk_norm": true,
	"vocab_size": 202048
	},
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.51.0",
	"vision_config": {
	"_attn_implementation_autoset": true,
	"attention_dropout": 0.0,
	"hidden_act": "gelu",
	"hidden_size": 1408,
	"image_size": 336,
	"initializer_range": 0.02,
	"intermediate_size": 5632,
	"model_type": "llama4_vision_model",
	"multi_modal_projector_bias": false,
	"norm_eps": 1e-05,
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 4,
	"patch_size": 14,
	"pixel_shuffle_ratio": 0.5,
	"projector_dropout": 0.0,
	"projector_input_dim": 4096,
	"projector_output_dim": 4096,
	"rope_theta": 10000,
	"vision_feature_layer": -1,
	"vision_feature_select_strategy": "default",
	"vision_output_dim": 4096
	}
	}