Edit model card

INT8 ONNX version of Locutusque/TinyMistral-248M to use with Transformers.js.

Example usage

Pipeline API

import { pipeline } from '@xenova/transformers';

const generator = await pipeline('text-generation', 'Felladrin/onnx-int8-TinyMistral-248M');
const output =  await generator('Once upon a time,', { add_special_tokens: true, max_new_tokens: 60, repetition_penalty: 1.2});
console.log(output);
// 'Once upon a time, the world was in turmoil. The United States had been on an unprecedented hiatus since 1970 and it seemed that America’s role as a global powerhouse would be at risk if we were to continue with our current political system.\n\nThe US has become'

Auto Classes

import { AutoModelForCausalLM, AutoTokenizer } from '@xenova/transformers';

const model_path = 'Felladrin/onnx-int8-TinyMistral-248M';
const model = await AutoModelForCausalLM.from_pretrained(model_path);
const tokenizer = await AutoTokenizer.from_pretrained(model_path);

const prompt = 'Once upon a time,';
const { input_ids } = tokenizer(prompt);
const tokens = await model.generate(input_ids, { max_new_tokens: 60, repetition_penalty: 1.2});
console.log(tokenizer.decode(tokens[0], { skip_special_tokens: true }));
// 'Once upon a time, the world was in turmoil. The United States had been on an unprecedented hiatus since 1970 and it seemed that America’s role as a global powerhouse would be at risk if we were to continue with our current political system.\n\nThe US has become'
Downloads last month
3
Inference API
Input a message to start chatting with Felladrin/onnx-TinyMistral-248M.
Inference API (serverless) does not yet support transformers.js models for this pipeline type.

Finetuned from