ERNIE-4.5-0.3B-Onnx

fireicesion/ERNIE-4.5-0.3B-Onnx

ERNIE-4.5-0.3B-Onnx is a text generation model from fireicesion. Use it when you need the model to write or continue text. It is set up for onnxruntime-genai. The card lists the license as apache-2.0.

<div align="center" style="line-height: 1;" <a href="https://ernie.baidu.com/" target="blank" style="margin: 2px;" <img alt="Chat" src="https://img.shields.io/badge/🤖Chat-ERNIEBot-blue" style="display: inline-block;…

Downloads · 30 days

Access

Public

Updated May 28, 2026

Repo size

767 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.data755 MB · 98%

At a glance

Task: Text Generation
Library: onnxruntime-genai
License: apache-2.0
Access: Public
Created: May 28, 2026
Updated: May 28, 2026
SHA: 7d0695e1

Try a prompt

Base models

baidu/ERNIE-4.5-0.3B-PT

Model card

From the Hugging Face model README

ERNIE-4.5-0.3B

[!NOTE] Note: "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights.

ERNIE 4.5 Highlights

The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

Multimodal Heterogeneous MoE Pre-Training: Our models are jointly trained on both textual and visual modalities to better capture the nuances of multimodal information and improve performance on tasks involving text understanding and generation, image understanding, and cross-modal reasoning. To achieve this without one modality hindering the learning of another, we designed a heterogeneous MoE structure, incorporated modality-isolated routing, and employed router orthogonal loss and multimodal token-balanced loss. These architectural choices ensure that both modalities are effectively represented, allowing for mutual reinforcement during training.
Scaling-Efficient Infrastructure: We propose a novel heterogeneous hybrid parallelism and hierarchical load balancing strategy for efficient training of ERNIE 4.5 models. By using intra-node expert parallelism, memory-efficient pipeline scheduling, FP8 mixed-precision training and finegrained recomputation methods, we achieve remarkable pre-training throughput. For inference, we propose multi-expert parallel collaboration method and convolutional code quantization algorithm to achieve 4-bit/2-bit lossless quantization. Furthermore, we introduce PD disaggregation with dynamic role switching for effective resource utilization to enhance inference performance for ERNIE 4.5 MoE models. Built on PaddlePaddle, ERNIE 4.5 delivers high-performance inference across a wide range of hardware platforms.
Modality-Specific Post-Training: To meet the diverse requirements of real-world applications, we fine-tuned variants of the pre-trained model for specific modalities. Our LLMs are optimized for general-purpose language understanding and generation. The VLMs focuses on visuallanguage understanding and supports both thinking and non-thinking modes. Each model employed a combination of Supervised Fine-tuning (SFT), Direct Preference Optimization (DPO) or a modified reinforcement learning method named Unified Preference Optimization (UPO) for post-training.

Model Overview

ERNIE-4.5-0.3B is a text dense Post-trained model. The following are the model configuration details:

Key	Value
Modality	Text
Training Stage	Posttraining
Params	0.36B
Layers	18
Heads(Q/KV)	16 / 2
Context Length	131072

Quickstart

Using `transformers` library

Note: You'll need the transformers library (version 4.54.0 or newer) installed to use this model.

The following contains a code snippet illustrating how to use the model generate content based on given inputs.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "baidu/ERNIE-4.5-0.3B-PT"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)

# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], add_special_tokens=False, return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()

# decode the generated ids
generate_text = tokenizer.decode(output_ids, skip_special_tokens=True)
print("generate_text:", generate_text)

vLLM inference

vllm github library. Python-only build.

vllm serve baidu/ERNIE-4.5-0.3B-PT

License

Citation

If you find ERNIE 4.5 useful or wish to use it in your projects, please kindly cite our technical report:

@misc{ernie2025technicalreport,
      title={ERNIE 4.5 Technical Report},
      author={Baidu ERNIE Team},
      year={2025},
      eprint={},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={}
}

Task: Text Generation
Library: onnxruntime-genai
License: apache-2.0
Languages: en, zh
Created: May 28, 2026
Updated: May 28, 2026