Image-Text-to-Text
Transformers
Safetensors
gemma3
Generated from Trainer
trl
sft
conversational
text-generation-inference
Instructions to use CocoRoF/POLAR_4b_Copywriter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CocoRoF/POLAR_4b_Copywriter with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="CocoRoF/POLAR_4b_Copywriter") 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("CocoRoF/POLAR_4b_Copywriter") model = AutoModelForMultimodalLM.from_pretrained("CocoRoF/POLAR_4b_Copywriter", 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 CocoRoF/POLAR_4b_Copywriter with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CocoRoF/POLAR_4b_Copywriter" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CocoRoF/POLAR_4b_Copywriter", "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/CocoRoF/POLAR_4b_Copywriter
- SGLang
How to use CocoRoF/POLAR_4b_Copywriter 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 "CocoRoF/POLAR_4b_Copywriter" \ --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": "CocoRoF/POLAR_4b_Copywriter", "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 "CocoRoF/POLAR_4b_Copywriter" \ --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": "CocoRoF/POLAR_4b_Copywriter", "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 CocoRoF/POLAR_4b_Copywriter with Docker Model Runner:
docker model run hf.co/CocoRoF/POLAR_4b_Copywriter
| { | |
| "architectures": [ | |
| "Gemma3ForConditionalGeneration" | |
| ], | |
| "boi_token_index": 255999, | |
| "eoi_token_index": 256000, | |
| "eos_token_id": [ | |
| 1, | |
| 106 | |
| ], | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2", | |
| "3": "LABEL_3", | |
| "4": "LABEL_4", | |
| "5": "LABEL_5", | |
| "6": "LABEL_6", | |
| "7": "LABEL_7", | |
| "8": "LABEL_8", | |
| "9": "LABEL_9", | |
| "10": "LABEL_10", | |
| "11": "LABEL_11", | |
| "12": "LABEL_12", | |
| "13": "LABEL_13", | |
| "14": "LABEL_14", | |
| "15": "LABEL_15", | |
| "16": "LABEL_16" | |
| }, | |
| "image_token_index": 262144, | |
| "initializer_range": 0.02, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_10": 10, | |
| "LABEL_11": 11, | |
| "LABEL_12": 12, | |
| "LABEL_13": 13, | |
| "LABEL_14": 14, | |
| "LABEL_15": 15, | |
| "LABEL_16": 16, | |
| "LABEL_2": 2, | |
| "LABEL_3": 3, | |
| "LABEL_4": 4, | |
| "LABEL_5": 5, | |
| "LABEL_6": 6, | |
| "LABEL_7": 7, | |
| "LABEL_8": 8, | |
| "LABEL_9": 9 | |
| }, | |
| "mm_tokens_per_image": 256, | |
| "model_type": "gemma3", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "cache_implementation": "hybrid", | |
| "final_logit_softcapping": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "max_position_embeddings": 131072, | |
| "model_type": "gemma3_text", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 34, | |
| "num_key_value_heads": 4, | |
| "query_pre_attn_scalar": 256, | |
| "rms_norm_eps": 1e-06, | |
| "rope_local_base_freq": 10000.0, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "rope_type": "linear" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 1024, | |
| "sliding_window_pattern": 6, | |
| "use_cache": true, | |
| "vocab_size": 262208 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.50.0", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 896, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "patch_size": 14, | |
| "vision_use_head": false | |
| } | |
| } | |