Instructions to use gimarchetti/llama32-rocov2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gimarchetti/llama32-rocov2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="gimarchetti/llama32-rocov2")
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("gimarchetti/llama32-rocov2")
model = AutoModelForImageTextToText.from_pretrained("gimarchetti/llama32-rocov2")
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 gimarchetti/llama32-rocov2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gimarchetti/llama32-rocov2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gimarchetti/llama32-rocov2",
		"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/gimarchetti/llama32-rocov2

SGLang

How to use gimarchetti/llama32-rocov2 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 "gimarchetti/llama32-rocov2" \
    --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": "gimarchetti/llama32-rocov2",
		"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 "gimarchetti/llama32-rocov2" \
        --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": "gimarchetti/llama32-rocov2",
		"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 gimarchetti/llama32-rocov2 with Docker Model Runner:
```
docker model run hf.co/gimarchetti/llama32-rocov2
```

llama32-rocov2

This model is a fine-tuned version of meta-llama/Llama-3.2-11B-Vision-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.5308

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: reduce_lr_on_plateau
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.9044	0.3057	1000	1.4144
0.8406	0.6115	2000	1.3676
1.191	0.9172	3000	1.2214
0.6385	1.2229	4000	1.3376
0.653	1.5286	5000	1.3327
0.6588	1.8344	6000	1.3117
0.2798	2.1401	7000	1.5337
0.2596	2.4458	8000	1.5558
0.2668	2.7516	9000	1.5308

Framework versions

Transformers 4.45.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.1

Downloads last month: 2

Safetensors

Model size

11B params

Tensor type

BF16

Model tree for gimarchetti/llama32-rocov2

Base model

meta-llama/Llama-3.2-11B-Vision-Instruct

Finetuned

(164)

this model