Instructions to use trl-internal-testing/tiny-Idefics3ForConditionalGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-Idefics3ForConditionalGeneration with Transformers:

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

pipe = pipeline("image-text-to-text", model="trl-internal-testing/tiny-Idefics3ForConditionalGeneration")
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("trl-internal-testing/tiny-Idefics3ForConditionalGeneration")
model = AutoModelForMultimodalLM.from_pretrained("trl-internal-testing/tiny-Idefics3ForConditionalGeneration")
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 trl-internal-testing/tiny-Idefics3ForConditionalGeneration with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trl-internal-testing/tiny-Idefics3ForConditionalGeneration"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trl-internal-testing/tiny-Idefics3ForConditionalGeneration",
		"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/trl-internal-testing/tiny-Idefics3ForConditionalGeneration

SGLang

How to use trl-internal-testing/tiny-Idefics3ForConditionalGeneration 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 "trl-internal-testing/tiny-Idefics3ForConditionalGeneration" \
    --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": "trl-internal-testing/tiny-Idefics3ForConditionalGeneration",
		"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 "trl-internal-testing/tiny-Idefics3ForConditionalGeneration" \
        --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": "trl-internal-testing/tiny-Idefics3ForConditionalGeneration",
		"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 trl-internal-testing/tiny-Idefics3ForConditionalGeneration with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-Idefics3ForConditionalGeneration
```

qgallouedec HF Staff commited on Sep 20, 2025

Commit

0d62778

verified ·

1 Parent(s): 722c4a6

Upload Idefics3ForConditionalGeneration

Browse files

Files changed (3) hide show

config.json +5 -3
generation_config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -2,6 +2,7 @@
   "architectures": [
     "Idefics3ForConditionalGeneration"
   ],
   "image_token_id": 128257,
   "model_type": "idefics3",
   "pad_token_id": 128002,
@@ -19,6 +20,7 @@
       "AutoModelForCausalLM": "modeling_idefics3.Idefics3ForVisionText2Text"
     },
     "bos_token_id": 128000,
     "eos_token_id": [
       128001,
       128008,
@@ -29,6 +31,7 @@
     "hidden_size": 16,
     "initializer_range": 0.02,
     "intermediate_size": 14336,
     "max_position_embeddings": 131072,
     "mlp_bias": false,
     "model_type": "llama",
@@ -120,17 +123,16 @@
       "rope_type": "llama3"
     },
     "rope_theta": 500000.0,
-    "torch_dtype": "bfloat16",
     "use_cache": true,
     "use_resampler": false,
     "vocab_size": 128259
   },
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.56.0.dev0",
   "use_cache": true,
   "vision_config": {
     "attention_dropout": 0.0,
     "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 16,
     "image_size": 364,

   "architectures": [
     "Idefics3ForConditionalGeneration"
   ],
+  "dtype": "bfloat16",
   "image_token_id": 128257,
   "model_type": "idefics3",
   "pad_token_id": 128002,
       "AutoModelForCausalLM": "modeling_idefics3.Idefics3ForVisionText2Text"
     },
     "bos_token_id": 128000,
+    "dtype": "bfloat16",
     "eos_token_id": [
       128001,
       128008,
     "hidden_size": 16,
     "initializer_range": 0.02,
     "intermediate_size": 14336,
+    "layer_types": null,
     "max_position_embeddings": 131072,
     "mlp_bias": false,
     "model_type": "llama",
       "rope_type": "llama3"
     },
     "rope_theta": 500000.0,
     "use_cache": true,
     "use_resampler": false,
     "vocab_size": 128259
   },
   "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
   "use_cache": true,
   "vision_config": {
     "attention_dropout": 0.0,
+    "embed_dim": 32,
     "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 16,
     "image_size": 364,

generation_config.json CHANGED Viewed

@@ -7,5 +7,5 @@
     128009
   ],
   "pad_token_id": 128002,
-  "transformers_version": "4.56.0.dev0"
 }

     128009
   ],
   "pad_token_id": 128002,
+  "transformers_version": "4.57.0.dev0"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a661eb4c15afccb9c68e712860b057ce8fdf886c5a0ee655c130a44d406dfc07
 size 11682096

 version https://git-lfs.github.com/spec/v1
+oid sha256:b27ea2b8b1c0a8ec9a57b425e85c05f8832cfcf202d0945a879ffd675143c3db
 size 11682096