Add transformers.js tags and example code (#7)

- Add transformers.js tags and example code (097a868a7a83d9b1368b225b7635fa24f3ffc0d5)


Co-authored-by: Joshua <[email protected]>

README.md

@@ -6,11 +6,13 @@ license: apache-2.0
 tags:
 - vision
 - image-text-to-text
+- transformers.js
 datasets:
 - lmms-lab/LLaVA-OneVision-Data
 pipeline_tag: image-text-to-text
 inference: false
 arxiv: 2408.03326
+library_name: transformers
 ---
 # LLaVA-Onevision Model Card
 
@@ -156,6 +158,86 @@ model = LlavaOnevisionForConditionalGeneration.from_pretrained(
 ).to(0)
 ```
 
+
+### Usage w/ Transformers.js
+
+If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
+```bash
+npm i @huggingface/transformers
+```
+
+**Example:** Multi-round conversations w/ PKV caching
+```js
+import { AutoProcessor, AutoTokenizer, LlavaOnevisionForConditionalGeneration, RawImage } from '@huggingface/transformers';
+
+// Load tokenizer, processor and model
+const model_id = 'llava-hf/llava-onevision-qwen2-0.5b-ov-hf';
+
+const tokenizer = await AutoTokenizer.from_pretrained(model_id);
+const processor = await AutoProcessor.from_pretrained(model_id);
+const model = await LlavaOnevisionForConditionalGeneration.from_pretrained(model_id, {
+    dtype: {
+        embed_tokens: 'fp16', // or 'fp32' or 'q8'
+        vision_encoder: 'fp16', // or 'fp32' or 'q8'
+        decoder_model_merged: 'q4', // or 'q8'
+    },
+    // device: 'webgpu',
+});
+
+// Prepare text inputs
+const prompt = 'What does the text say?';
+const messages = [
+    { role: 'system', content: 'Answer the question.' },
+    { role: 'user', content: `<image>\n${prompt}` }
+]
+const text = tokenizer.apply_chat_template(messages, { tokenize: false, add_generation_prompt: true });
+const text_inputs = tokenizer(text);
+
+// Prepare vision inputs
+const url = 'https://huggingface.co/qnguyen3/nanoLLaVA/resolve/main/example_1.png';
+const image = await RawImage.fromURL(url);
+const vision_inputs = await processor(image);
+
+// Generate response
+const { past_key_values, sequences } = await model.generate({
+    ...text_inputs,
+    ...vision_inputs,
+    do_sample: false,
+    max_new_tokens: 64,
+    return_dict_in_generate: true,
+});
+
+// Decode output
+const answer = tokenizer.decode(
+    sequences.slice(0, [text_inputs.input_ids.dims[1], null]),
+    { skip_special_tokens: true },
+);
+console.log(answer);
+// The text says "small but mighty" in a playful font.
+
+const new_messages = [
+    ...messages,
+    { role: 'assistant', content: answer },
+    { role: 'user', content: 'How does the text correlate to the context of the image?' }
+]
+const new_text = tokenizer.apply_chat_template(new_messages, { tokenize: false, add_generation_prompt: true });
+const new_text_inputs = tokenizer(new_text);
+
+// Generate another response
+const output = await model.generate({
+    ...new_text_inputs,
+    past_key_values,
+    do_sample: false,
+    max_new_tokens: 256,
+});
+const new_answer = tokenizer.decode(
+    output.slice(0, [new_text_inputs.input_ids.dims[1], null]),
+    { skip_special_tokens: true },
+);
+console.log(new_answer);
+// The text "small but mighty" is likely a playful or humorous reference to the image of the blue mouse with the orange dumbbell. It could be used as a motivational phrase or a playful way to express the idea that even small things can be impressive or powerful.
+```
+
 # Citation
 ```
 @misc{li2024llavaonevisioneasyvisualtask,