Instructions to use Leonardo6/llava-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Leonardo6/llava-sft with Transformers:

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

pipe = pipeline("image-text-to-text", model="Leonardo6/llava-sft")
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("Leonardo6/llava-sft")
model = AutoModelForMultimodalLM.from_pretrained("Leonardo6/llava-sft", 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 Leonardo6/llava-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Leonardo6/llava-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Leonardo6/llava-sft",
		"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/Leonardo6/llava-sft

SGLang

How to use Leonardo6/llava-sft 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 "Leonardo6/llava-sft" \
    --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": "Leonardo6/llava-sft",
		"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 "Leonardo6/llava-sft" \
        --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": "Leonardo6/llava-sft",
		"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 Leonardo6/llava-sft with Docker Model Runner:
```
docker model run hf.co/Leonardo6/llava-sft
```

Leonardo6 commited on Aug 7, 2025

Commit

d544ba3

verified ·

1 Parent(s): 78f3c31

Training in progress, step 10000, checkpoint

Browse files

Files changed (22) hide show

last-checkpoint/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
last-checkpoint/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
last-checkpoint/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
last-checkpoint/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
last-checkpoint/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
last-checkpoint/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
last-checkpoint/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
last-checkpoint/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
last-checkpoint/global_step10000/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
last-checkpoint/global_step10000/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
last-checkpoint/global_step10000/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
last-checkpoint/global_step10000/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
last-checkpoint/global_step10000/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
last-checkpoint/global_step10000/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
last-checkpoint/global_step10000/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
last-checkpoint/global_step10000/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
last-checkpoint/latest +1 -1
last-checkpoint/model-00001-of-00003.safetensors +1 -1
last-checkpoint/model-00002-of-00003.safetensors +1 -1
last-checkpoint/model-00003-of-00003.safetensors +1 -1
last-checkpoint/scheduler.pt +1 -1
last-checkpoint/trainer_state.json +0 -0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca267acc2e39e1a4c84ffa8b7a3a1723dc4354947a8c2db9d70934fb8acdc48d
 size 4992930688

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b87440b831cf1d35707b69f2a3eb5757faff518baaf40b7c8ae5ecea7136783
 size 4957878552

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238faf3c847127f7dbdb6239c1662be4c47cd122bdd3b2fa0ba1c9b384dde878
 size 4176137496

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a8840d6f3f71bffe3d56d2008785655da2c807fae69ae4a262b176dd70fbb4
 size 1064

+version https://git-lfs.github.com/spec/v1
+oid sha256:f15f6f5ace4108c8f7c39fc368b3913dce68a2dae3b712da617a93bab5ae45cf
+size 10595145612

+version https://git-lfs.github.com/spec/v1
+oid sha256:42edbc8c2531456a1a5a9ec4e3eb0a42231bf954457658804ddbb692bc93f08c
+size 382436

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@