Instructions to use trl-internal-testing/tiny-Gemma4ForConditionalGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use trl-internal-testing/tiny-Gemma4ForConditionalGeneration 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-Gemma4ForConditionalGeneration") 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-Gemma4ForConditionalGeneration") model = AutoModelForImageTextToText.from_pretrained("trl-internal-testing/tiny-Gemma4ForConditionalGeneration") 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-Gemma4ForConditionalGeneration 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-Gemma4ForConditionalGeneration" # 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-Gemma4ForConditionalGeneration", "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-Gemma4ForConditionalGeneration
- SGLang
How to use trl-internal-testing/tiny-Gemma4ForConditionalGeneration 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-Gemma4ForConditionalGeneration" \ --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-Gemma4ForConditionalGeneration", "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-Gemma4ForConditionalGeneration" \ --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-Gemma4ForConditionalGeneration", "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-Gemma4ForConditionalGeneration with Docker Model Runner:
docker model run hf.co/trl-internal-testing/tiny-Gemma4ForConditionalGeneration
| { | |
| "architectures": [ | |
| "Gemma4ForConditionalGeneration" | |
| ], | |
| "audio_config": null, | |
| "audio_token_id": 258881, | |
| "boa_token_id": 256000, | |
| "boi_token_id": 255999, | |
| "dtype": "bfloat16", | |
| "eoa_token_id": 258883, | |
| "eoa_token_index": 258883, | |
| "eoi_token_id": 258882, | |
| "eos_token_id": [ | |
| 1, | |
| 106 | |
| ], | |
| "image_token_id": 258880, | |
| "initializer_range": 0.02, | |
| "model_type": "gemma4", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_k_eq_v": false, | |
| "bos_token_id": 2, | |
| "dtype": "bfloat16", | |
| "enable_moe_block": false, | |
| "eos_token_id": 1, | |
| "expert_intermediate_size": null, | |
| "final_logit_softcapping": 30.0, | |
| "global_head_dim": 8, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 16, | |
| "hidden_size_per_layer_input": 16, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 131072, | |
| "model_type": "gemma4_text", | |
| "moe_intermediate_size": null, | |
| "num_attention_heads": 4, | |
| "num_experts": null, | |
| "num_global_key_value_heads": null, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 2, | |
| "num_kv_shared_layers": 0, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 1000000.0, | |
| "rope_type": "proportional" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sliding_window": 512, | |
| "tie_word_embeddings": true, | |
| "top_k_experts": null, | |
| "use_bidirectional_attention": null, | |
| "use_cache": true, | |
| "use_double_wide_mlp": true, | |
| "vocab_size": 262144, | |
| "vocab_size_per_layer_input": 262144 | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.5.0", | |
| "video_token_id": 258884, | |
| "vision_config": { | |
| "_name_or_path": "", | |
| "architectures": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "chunk_size_feed_forward": 0, | |
| "default_output_length": 70, | |
| "dtype": "bfloat16", | |
| "embed_dim": 64, | |
| "global_head_dim": 64, | |
| "head_dim": 64, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 16, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "max_position_embeddings": 131072, | |
| "model_type": "gemma4_vision", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 2, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "patch_size": 16, | |
| "pooling_kernel_size": 3, | |
| "position_embedding_size": 630, | |
| "problem_type": null, | |
| "return_dict": true, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 100.0, | |
| "rope_type": "default" | |
| }, | |
| "standardize": false, | |
| "use_clipped_linears": true | |
| }, | |
| "vision_soft_tokens_per_image": 280 | |
| } | |