Instructions to use trl-internal-testing/tiny-Qwen2_5_VLForConditionalGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use trl-internal-testing/tiny-Qwen2_5_VLForConditionalGeneration 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-Qwen2_5_VLForConditionalGeneration") 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-Qwen2_5_VLForConditionalGeneration") model = AutoModelForImageTextToText.from_pretrained("trl-internal-testing/tiny-Qwen2_5_VLForConditionalGeneration") 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-Qwen2_5_VLForConditionalGeneration 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-Qwen2_5_VLForConditionalGeneration" # 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-Qwen2_5_VLForConditionalGeneration", "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-Qwen2_5_VLForConditionalGeneration
- SGLang
How to use trl-internal-testing/tiny-Qwen2_5_VLForConditionalGeneration 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-Qwen2_5_VLForConditionalGeneration" \ --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-Qwen2_5_VLForConditionalGeneration", "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-Qwen2_5_VLForConditionalGeneration" \ --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-Qwen2_5_VLForConditionalGeneration", "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-Qwen2_5_VLForConditionalGeneration with Docker Model Runner:
docker model run hf.co/trl-internal-testing/tiny-Qwen2_5_VLForConditionalGeneration
File size: 2,513 Bytes
ece60a1 2a6d098 aab7dd7 2a6d098 a907de7 ece60a1 2a6d098 ece60a1 a907de7 2a6d098 a907de7 2a6d098 ece60a1 2a6d098 ece60a1 2a6d098 aab7dd7 2a6d098 ece60a1 776e91c a907de7 ece60a1 2a6d098 ece60a1 2a6d098 ece60a1 2a6d098 ece60a1 b0b2701 ece60a1 2a6d098 ece60a1 a907de7 2a6d098 ece60a1 a907de7 2a6d098 ece60a1 87fdfd1 ece60a1 2a6d098 ece60a1 2a6d098 ece60a1 a907de7 776e91c ece60a1 2a6d098 ece60a1 2a6d098 ece60a1 1b6f2c8 ad1c417 2a6d098 ece60a1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 | {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 16,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 128000,
"max_window_layers": 70,
"model_type": "qwen2_5_vl",
"num_attention_heads": 4,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
1,
1
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"text_config": {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 16,
"image_token_id": null,
"initializer_range": 0.02,
"intermediate_size": 11008,
"layer_types": [
"full_attention",
"full_attention"
],
"max_position_embeddings": 128000,
"max_window_layers": 70,
"model_type": "qwen2_5_vl_text",
"num_attention_heads": 4,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
1,
1
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"use_cache": true,
"use_sliding_window": false,
"video_token_id": null,
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 151936
},
"transformers_version": "4.56.2",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"depth": 2,
"fullatt_block_indexes": [
7,
15,
23,
31
],
"hidden_act": "silu",
"hidden_size": 16,
"in_channels": 3,
"in_chans": 3,
"initializer_range": 0.02,
"intermediate_size": 3420,
"model_type": "qwen2_5_vl",
"num_heads": 4,
"out_hidden_size": 16,
"patch_size": 14,
"spatial_merge_size": 2,
"spatial_patch_size": 14,
"temporal_patch_size": 2,
"tokens_per_second": 2,
"window_size": 112
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 151936
}
|