alt.freeweights.text / ERNIE-4.5-0.3B-ONNX

From:

onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.textSubject:

ERNIE-4.5-0.3B-ONNX

Date: 2026-11-15Commit: d9d10b7Signed: 2DC28CC7B26A283B ✓

Text generation model. Onnx weights, 5.23 GB in all. Published by onnx-community under Apache-2.0.

text

5.23GBERNIE-4.5-0.3B-ONNXonnxpermissive

FactsParamsnot statedSize5.23 GBFormatsonnxTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get onnx-community/ERNIE-4.5-0.3B-ONNX
# manifest sha256 6694803595f9… · 5.23 GB · 26 files
$ fw verify ./ERNIE-4.5-0.3B-ONNX onnx-community/ERNIE-4.5-0.3B-ONNX

From sourceHosted (signed)onnx-community/ERNIE-4.5-0.3B-ONNXLast check: 2026-11-15 05:27 UTC

Fine-tune in Studio Get help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of ERNIE-4.5-0.3B-PT.

Runs withgpu-unlock

ONNX Runtime GenAI OpenVINO

Transformers.js UltralyticsConvert with

Olive ONNX

OptimumEvaluate withAutoevals DeepEval

Evaluate HELM

LightEval lm-evaluation-harness OpenCompass Opik Ragas

simple-evals SWE-bench TruLens WeaveScan withAgentDojo AI Fairness 360 DeepTeam Detoxify Fairlearn garak Giskard Guardrails MCP Scanner ModelScan NeMo Guardrails promptfooWorks with

Agent Development Kit AG2 Google AI Edge Gallery Aider any-llm AnythingLLM BAML browser-use CAMEL

Hugging Face Chat UI Chatbox Cherry Studio Cline

Codex CLI Cognee CrewAI DeerFlow DSPy Enchanted Gemini CLI GitHub MCP Server goose GPT Researcher Gradio Graphiti Guidance Hollama Instructor Kilo Code Langflow LangGraph LiteLLM LlamaIndex LLM LocalAGI LoLLMs WebUI MCP Python SDK Mem0 MetaGPT NextChat

Ollama JavaScript

Ollama Python

OpenAI Agents SDK opencode OpenHands oterm Outlines Page Assist

Playwright MCP Portkey AI Gateway PrivateGPT Qwen Code RWKV Runner

Semantic Kernel

smolagents Strands Agents Vane XGrammar

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 5.23 GB
Weights: 389 MB (smallest of 8 ONNX variants)
Parameters: not stated
Formats: onnx
Task: text generation
License: Apache-2.0 (permissive)
Files: 26, each with a sha256
Publisher: onnx-community
Added: 2026-11-15
Section: alt.freeweights.text

Lineage

Original release from the publisher.

Base model: baidu/ERNIE-4.5-0.3B-PT

Where these bytes come from

Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 05:27 UTC	passed

Model card

From the publisher at commit d9d10b7. Shown as plain text with links; images open at the publisher.

https://huggingface.co/baidu/ERNIE-4.5-0.3B-PT with ONNX weights to be compatible with Transformers.js.

Usage (Transformers.js)#

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

You can then generate text as follows:

import { pipeline, TextStreamer } from "@huggingface/transformers";

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/ERNIE-4.5-0.3B-ONNX",
  { dtype: "fp32" }, // Options: "fp32", "fp16", "q8", "q4", "q4f16"
);

// Define the list of messages
const messages = [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "What is the capital of France?" },
];

// Generate a response
const output = await generator(messages, {
    max_new_tokens: 512,
    do_sample: false,
    streamer: new TextStreamer(generator.tokenizer, { skip_prompt: true, skip_special_tokens: true}),
});
console.log(output[0].generated_text.at(-1).content);
// The capital of France is Paris.

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).

Files

26 files · 5.23 GBWeights 389 MB (smallest of 8 ONNX variants). Sizes and sha256 from the signed manifest.

Show all 26 files with their sha256

File	Size	sha256
.gitattributes	2.02 KB	ad7dffa3c538cf3c6bb7f6a539db2db6137e368054c4c4661c5702c14643a0ce
README.md	1.63 KB	ef561d3fe8de1e8db8efa72d31ff31ec31b52c93fb7917867b801b7bb95ce304
added_tokens.json	25.2 KB	08ab98258652553a53455b164c258488ce840322f0949877676d962a1d958cad
chat_template.jinja	754 B	471fb571976770318fe6f27749e37940be8d29c0a7770558140f141f5906f2a2
config.json	1.20 KB	7e970614a7d9913fe7ce9efa9d8e1a1812903282fe80430fb4c43d15c2b8b5de
generation_config.json	221 B	45f942a35ef1ee432ba5b366b1327ce6f7344e029d2cfa0e9cd07ace7a9ff3b4
onnx/model.onnx	127 KB	c0b863498e9bb352a50d013c75a6976671a38777ebd38616237f4fbe3757ad4f
onnx/model.onnx_data	1.51 GB	b5e2e04379876c8c6d44f877ae2af2edb9e2519616f1268230182bbd1d986c9e
onnx/model_bnb4.onnx	162 KB	177e7101189f6a7b5955e890cb60320b7baefbec1be5c0fa36476e5ee3f2d131
onnx/model_bnb4.onnx_data	634 MB	064b92a089d338778cba32d166242bfc3062109fd4af273ae3b7d724214e053e
onnx/model_fp16.onnx	127 KB	a68d39a03da7a012217f4b107ec887afc7999b59210e0968f9c60d70b7f49032
onnx/model_fp16.onnx_data	755 MB	1730b3445daf10ffb7e82d97723faed35043886377887b8306432c3260636139
onnx/model_int8.onnx	318 KB	762c4737fe9301d9cd422b12e978d6a0593fc653cf4e65e78db6ce27857a8718
onnx/model_int8.onnx_data	428 MB	3e93a00070de08475978dbab1e8183e7d1f5a940e39acaac09c4c68021e88720
onnx/model_q4.onnx	163 KB	a5a3233b1737f8e24b64d8f8dec9c91a185caf59726b814c24f64315cdfd0f64
onnx/model_q4.onnx_data	650 MB	71ca26370e40afba183da4384967bd17c2a291b5ca6d72cee76fc184c2c4ae05
onnx/model_q4f16.onnx	164 KB	d03043842ef06c7810e451803b67f0f2b9b0e20285d3453135f92bbf7c325e98
onnx/model_q4f16.onnx_data	389 MB	af5888a06e48f737fd8e0acd973e251a4ecaf7c855445b9e24bf31f1a3a58963
onnx/model_quantized.onnx	322 KB	1946e512630076518f4142bbb6ac469121aedbc3adfb022b4dfd04243fb846b8
onnx/model_quantized.onnx_data	428 MB	42810c89b57039ee5883ba9972e86f358c52a7af7cc2ba0da18d9250c6fa18d5
onnx/model_uint8.onnx	321 KB	858118d7ee7039ba3e7d081805d0ded190bfea099be581cf005dc51deb7a9d44
onnx/model_uint8.onnx_data	428 MB	42810c89b57039ee5883ba9972e86f358c52a7af7cc2ba0da18d9250c6fa18d5
special_tokens_map.json	19.3 KB	9555ebfd6201518803e3857a141c25291d2a892d3c5951bb6fa2548c92e059e7
tokenizer.json	5.90 MB	62591218cac47828261edfd24e36eb137f15ff17115b16b92ea168b2ccdb3903
tokenizer.model	1.61 MB	34ef7db83df785924fb83d7b887b6e822a031c56e15cff40aaf9b982988180df
tokenizer_config.json	201 KB	d17367c8838436c17355d555f930e6d9f1ba6d1fb181140e28c18c462941d0ef

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
d9d10b7de8 pinned now	2026-11-15 05:27 UTC	26 files · 5.23 GB

Use it

$ fw get onnx-community/ERNIE-4.5-0.3B-ONNX
# manifest sha256 6694803595f9… · 5.23 GB · 26 files
$ fw verify ./ERNIE-4.5-0.3B-ONNX onnx-community/ERNIE-4.5-0.3B-ONNX

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/onnx-community/ERNIE-4.5-0.3B-ONNX.json --dir ./ERNIE-4.5-0.3B-ONNX
$ python3 fw.py verify ./ERNIE-4.5-0.3B-ONNX ./onnx-community__ERNIE-4.5-0.3B-ONNX.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/ERNIE-4.5-0.3B-ONNX --revision d9d10b7de8dfc9f5434dc14c4d2ab05c3bd32389 --local-dir ./ERNIE-4.5-0.3B-ONNX

Fine-tune in Studio

License

Name: Apache License 2.0
Id: Apache-2.0
Class: Permissive
Redistribution: yes
Listing: Hosted (signed)
Decided: Inherited from the base model baidu/ERNIE-4.5-0.3B-PT: the strictest license along the lineage applies. 2026-11-15
Text in: README.md
Text sha256: ef561d3fe8de1e8db8efa72d31ff31ec31b52c93fb7917867b801b7bb95ce304
Terms gate: No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From:

onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.textSubject: ERNIE-4.5-0.3B-ONNXDate: 2026-11-15Commit: d9d10b7Signed: 2DC28CC7B26A283B ✓

Upstream: onnx-community/ERNIE-4.5-0.3B-ONNX
Pinned commit: d9d10b7de8dfc9f5434dc14c4d2ab05c3bd32389
Manifest: ERNIE-4.5-0.3B-ONNX.json · .minisig
Manifest sha256: 6694803595f91ad010252041e98da9e0662f0f07ac98f76c22f444ebea5c1f1a
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:27 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/onnx-community/ERNIE-4.5-0.3B-ONNX.json
$ curl -O https://freeweights.allternit.com/manifests/onnx-community/ERNIE-4.5-0.3B-ONNX.json.minisig
$ minisign -Vm ERNIE-4.5-0.3B-ONNX.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file>   # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

baidu/ERNIE-4.5-0.3B-PT · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it

Download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/ERNIE-4.5-0.3B-ONNX

Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest

minisign, key 2DC28CC7B26A283B. ERNIE-4.5-0.3B-ONNX.json. Provenance. Takedown history: none.

Source

huggingface.co/onnx-community/ERNIE-4.5-0.3B-ONNX

Related models

All of alt.freeweights.text →

From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B

From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B