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

Libraries

How to use trl-internal-testing/tiny-InternVLForConditionalGeneration 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-InternVLForConditionalGeneration")
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("trl-internal-testing/tiny-InternVLForConditionalGeneration")
model = AutoModelForImageTextToText.from_pretrained("trl-internal-testing/tiny-InternVLForConditionalGeneration")
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 trl-internal-testing/tiny-InternVLForConditionalGeneration 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-InternVLForConditionalGeneration"
# 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-InternVLForConditionalGeneration",
		"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-InternVLForConditionalGeneration

SGLang

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

qgallouedec HF Staff commited on Sep 20, 2025

Commit

baa16f6

verified ·

1 Parent(s): d77a85b

Upload InternVLForConditionalGeneration

Browse files

Files changed (3) hide show

config.json +5 -30
generation_config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -3,6 +3,7 @@
     "InternVLForConditionalGeneration"
   ],
   "downsample_ratio": 0.5,
   "image_seq_length": 256,
   "image_token_id": 151667,
   "model_type": "internvl",
@@ -13,38 +14,13 @@
     ],
     "attention_dropout": 0.0,
     "bos_token_id": 151643,
     "eos_token_id": 151645,
     "hidden_act": "silu",
     "hidden_size": 16,
     "initializer_range": 0.02,
     "intermediate_size": 18944,
     "layer_types": [
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
       "full_attention",
       "full_attention"
     ],
@@ -62,13 +38,11 @@
     },
     "rope_theta": 1000000.0,
     "sliding_window": null,
-    "torch_dtype": "bfloat16",
     "use_cache": true,
     "use_sliding_window": false,
     "vocab_size": 151674
   },
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.56.0.dev0",
   "vision_config": {
     "architectures": [
       "InternVisionModel"
@@ -76,6 +50,8 @@
     "attention_bias": true,
     "attention_dropout": 0.0,
     "dropout": 0.0,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.0,
     "hidden_size": 16,
@@ -99,7 +75,6 @@
       14
     ],
     "projection_dropout": 0.0,
-    "torch_dtype": "bfloat16",
     "use_absolute_position_embeddings": true,
     "use_mask_token": false,
     "use_mean_pooling": true,

     "InternVLForConditionalGeneration"
   ],
   "downsample_ratio": 0.5,
+  "dtype": "bfloat16",
   "image_seq_length": 256,
   "image_token_id": 151667,
   "model_type": "internvl",
     ],
     "attention_dropout": 0.0,
     "bos_token_id": 151643,
+    "dtype": "bfloat16",
     "eos_token_id": 151645,
     "hidden_act": "silu",
     "hidden_size": 16,
     "initializer_range": 0.02,
     "intermediate_size": 18944,
     "layer_types": [
       "full_attention",
       "full_attention"
     ],
     },
     "rope_theta": 1000000.0,
     "sliding_window": null,
     "use_cache": true,
     "use_sliding_window": false,
     "vocab_size": 151674
   },
+  "transformers_version": "4.57.0.dev0",
   "vision_config": {
     "architectures": [
       "InternVisionModel"
     "attention_bias": true,
     "attention_dropout": 0.0,
     "dropout": 0.0,
+    "dtype": "bfloat16",
+    "embed_dim": 32,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.0,
     "hidden_size": 16,
       14
     ],
     "projection_dropout": 0.0,
     "use_absolute_position_embeddings": true,
     "use_mask_token": false,
     "use_mean_pooling": true,

generation_config.json CHANGED Viewed

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
-  "transformers_version": "4.56.0.dev0"
 }

   "_from_model_config": true,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
+  "transformers_version": "4.57.0.dev0"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed5c180bbebb66356d2b6e59fa050007814e5192ae347c8cb0fd178578e88ec0
 size 13956416

 version https://git-lfs.github.com/spec/v1
+oid sha256:ac4ed3cf0838f9202013909fc3c8a6c701744bfce8b283c64ab908a202327caf
 size 13956416