https://huggingface.co/qnguyen3/nanoLLaVA with ONNX weights to be compatible with Transformers.js.
Usage (Transformers.js)
NOTE: nanoLLaVA support is experimental and requires you to install Transformers.js v3 from source.
If you haven't already, you can install the Transformers.js JavaScript library from GitHub using:
npm install xenova/transformers.js#v3
Example:
import { AutoProcessor, AutoTokenizer, LlavaForConditionalGeneration, RawImage } from '@xenova/transformers';
// Load tokenizer, processor and model
const model_id = 'Xenova/nanoLLaVA';
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const processor = await AutoProcessor.from_pretrained(model_id);
const model = await LlavaForConditionalGeneration.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 reads "Small but mighty".
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 context of the image is that of a playful and humorous illustration of a mouse holding a weightlifting bar. The text "Small but mighty" is a playful reference to the mouse's size and strength.
Demos:
We also released an online demo, which you can try yourself: https://huggingface.co/spaces/Xenova/experimental-nanollava-webgpu
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx
).
- Downloads last month
- 47
Model tree for Xenova/nanoLLaVA
Base model
qnguyen3/nanoLLaVA