NanoTranslator-XXL2

NanoTranslator-XXL2

English | 简体中文

Introduction

This is the xx-large-2 model of the NanoTranslator, currently supported only in English to Chinese.

The ONNX version of the model is also available in the repository.

All models are collected in the NanoTranslator Collection.

• P. - Parameters (in million)
• V. - vocab size
• H. - hidden size
• I. - intermediate size
• L. - num layers
• A.H. - num attention heads
• K.H. - num kv heads
• Tie - tie word embeddings

How to use

Prompt format as follows：

<|im_start|> {English Text} <|endoftext|>

Directly using transformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_path = 'Mxode/NanoTranslator-XXL2'

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path)

def translate(text: str, model, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.55),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    prompt = "<|im_start|>" + text + "<|endoftext|>"
    model_inputs = tokenizer([prompt], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response

text = "Each step of the cell cycle is monitored by internal."

response = translate(text, model, max_new_tokens=64, do_sample=False)
print(response)

ONNX

It has been measured that reasoning with ONNX models will be 2-10 times faster than reasoning directly with transformers models.

You should switch to onnx branch manually and download to local.

reference docs:

• Export to ONNX
• Inference pipelines with the ONNX Runtime accelerator

Using ORTModelForCausalLM

from optimum.onnxruntime import ORTModelForCausalLM
from transformers import AutoTokenizer

model_path = "your/folder/to/onnx_model"

ort_model = ORTModelForCausalLM.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)

text = "Each step of the cell cycle is monitored by internal."

response = translate(text, ort_model, max_new_tokens=64, do_sample=False)
print(response)

Using pipeline

from optimum.pipelines import pipeline

model_path = "your/folder/to/onnx_model"
pipe = pipeline("text-generation", model=model_path, accelerator="ort")

text = "Each step of the cell cycle is monitored by internal."

response = pipe(text, max_new_tokens=64, do_sample=False)
response