Instructions to use hf-internal-testing/tiny-random-llama4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-llama4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="hf-internal-testing/tiny-random-llama4")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("hf-internal-testing/tiny-random-llama4")
model = AutoModelForImageTextToText.from_pretrained("hf-internal-testing/tiny-random-llama4")
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

vLLM

How to use hf-internal-testing/tiny-random-llama4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hf-internal-testing/tiny-random-llama4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/tiny-random-llama4",
		"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/hf-internal-testing/tiny-random-llama4

SGLang

How to use hf-internal-testing/tiny-random-llama4 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 "hf-internal-testing/tiny-random-llama4" \
    --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": "hf-internal-testing/tiny-random-llama4",
		"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 "hf-internal-testing/tiny-random-llama4" \
        --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": "hf-internal-testing/tiny-random-llama4",
		"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 hf-internal-testing/tiny-random-llama4 with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-llama4
```

Xenova HF Staff commited on Apr 7, 2025

Commit

5dfe498

verified ·

1 Parent(s): da2decb

Update README.md

Browse files

Files changed (1) hide show

README.md +52 -0

README.md CHANGED Viewed

@@ -8,6 +8,58 @@ tags: []
 <!-- Provide a quick summary of what the model is/does. -->
 ## Model Details

 <!-- Provide a quick summary of what the model is/does. -->
+## Conversion code
+```py
+from transformers import (
+    AutoProcessor,
+    Llama4ForConditionalGeneration,
+    Llama4VisionConfig,
+    Llama4TextConfig,
+    Llama4Config,
+)
+import torch
+torch.manual_seed(0)
+model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
+torch_dtype = torch.bfloat16  # or torch.float32
+intermediate_size_mlp = 64
+config = Llama4Config.from_pretrained(
+    model_id,
+    text_config=Llama4TextConfig.from_pretrained(
+        model_id,
+        head_dim=8,
+        hidden_size=16,
+        intermediate_size=32,
+        intermediate_size_mlp=intermediate_size_mlp,
+        moe_layers=[0,1,2,3,4],
+        no_rope_layers=[1,1,1,0,1],
+        num_attention_heads=10,
+        num_experts_per_tok=1,
+        num_hidden_layers=5,
+        num_key_value_heads=2,
+        num_local_experts=4,
+    ),
+    vision_config=Llama4VisionConfig.from_pretrained(
+        model_id,
+        hidden_size=16,
+        intermediate_size=intermediate_size_mlp,
+        num_attention_heads=4,
+        num_hidden_layers=2,
+        projector_input_dim=128,
+        projector_output_dim=128,
+        vision_output_dim=128,
+    ),
+)
+model = Llama4ForConditionalGeneration(config).to(torch_dtype)
+print(model.num_parameters())  # 6571696
+processor = AutoProcessor.from_pretrained(model_id)
+```
 ## Model Details