alt.freeweights.text / sarashina2.2-0.5b-instruct-v0.1-ONNX
From: onnx-community <huggingface.co/onnx-community>Newsgroups: alt.freeweights.textSubject:

sarashina2.2-0.5b-instruct-v0.1-ONNX

Date: 2026-11-15Commit: 5569f34Signed: 2DC28CC7B26A283B ✓

Text generation model. Onnx weights, 7.40 GB in all. Published by onnx-community under MIT.

text7.40GBsarashina2.2-0.5b-instruct-v0.1-ONNXonnxpermissive
FactsParamsnot statedSize7.40 GBFormatsonnxTasktext generationLicenseMITFrom sourcepermissive
$ fw get onnx-community/sarashina2.2-0.5b-instruct-v0.1-ONNX
# manifest sha256 1d52c71b506a… · 7.40 GB · 11 files
$ fw verify ./sarashina2.2-0.5b-instruct-v0.1-ONNX onnx-community/sarashina2.2-0.5b-instruct-v0.1-ONNX
From sourceHosted (signed)onnx-community/sarashina2.2-0.5b-instruct-v0.1-ONNXLast check: 2026-11-15 05:22 UTC

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

Quantized of sarashina2.2-0.5b-instruct-v0.1.

Works with

Runs with

Ranked by fit to this model (onnx), then by GitHub stars.

Convert with

Overview

Size
7.40 GB
Weights
795 MB (smallest of 6 ONNX variants)
Parameters
not stated
Formats
onnx
Task
text generation
License
MIT (permissive)
Files
11, each with a sha256
Publisher
onnx-community
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: sbintuitions/sarashina2.2-0.5b-instruct-v0.1

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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:22 UTCpassed

Model card

From the publisher at commit 5569f34. Shown as plain text with links; images open at the publisher.

sarashina2.2-0.5b-instruct-v0.1 (ONNX)#

This is an ONNX version of sbintuitions/sarashina2.2-0.5b-instruct-v0.1. It was automatically converted and uploaded using this Hugging Face Space.

Usage with Transformers.js#

See the pipeline documentation for text-generation: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.TextGenerationPipeline


sbintuitions/sarashina2.2-0.5b-instruct-v0.1#

Model Summary#

This repository provides Japanese language models trained by SB Intuitions.

Model Details#

  • Model type: Autoregressive Language Model
  • Language(s): Japanese

Evaluation in Japanese and English Tasks#

ModelElyza-tasks-100Japanese MT BenchEnglish MT Bench
Qwen/Qwen2.5-0.5B-instruct1.532.954.98
sarashina2.2-0.5B-instruct-v0.12.384.555.09
Rakuten/RakutenAI-2.0-mini-instruct2.414.495.13
SakanaAI/TinySwallow-1.5B-Instruct2.815.246.31
Qwen/Qwen2.5-1.5B-instruct2.284.066.99
llm-jp/llm-jp-3-1.8b-instruct32.534.624.83
sarashina2.2-1B-instruct-v0.12.885.096.46
google/gemma-2-2b-jpn-it3.025.197.56
Qwen/Qwen2.5-3B-instruct2.995.687.88
llm-jp/llm-jp-3-3.7b-instruct32.794.985.44
sarashina2.2-3B-instruct-v0.13.756.517.71

How to Use#

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, set_seed

# モデルのロード
model_name = "sbintuitions/sarashina2.2-0.5b-instruct-v0.1"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)
chat_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
set_seed(123)

# ユーザーの入力
user_input = [{"role": "user", "content": "こんにちは。あなたの名前を教えて"}]

# モデルによる応答生成
responses = chat_pipeline(
    user_input,
    max_length=50,
    do_sample=True,
    num_return_sequences=3,
)

# 応答を表示
for i, response in enumerate(responses, 1):
    print(f"Response {i}: {response['generated_text']}")

# Response 1: [{'role': 'user', 'content': 'こんにちは。あなたの名前を教えて'}, {'role': 'assistant', 'content': 'Sarashina2と言います。本日のご要件を教えて下さい。'}]
# Response 2: [{'role': 'user', 'content': 'こんにちは。あなたの名前を教えて'}, {'role': 'assistant', 'content': 'こんにちは!私の名前はSarashina2です。今日はどうしましたか?'}]
# Response 3: [{'role': 'user', 'content': 'こんにちは。あなたの名前を教えて'}, {'role': 'assistant', 'content': 'Sarashina2と言います。本日のご要件を教えて下さい。'}]

Limitations#

This model has limited safety training. Therefore, it might generate some meaningless sequences, some inaccurate instances, or biased/objectionable outputs. Before using it, we would like developers to tune models based on human preferences and safety considerations.

License#

MIT License

Files

11 files · 7.40 GBWeights 795 MB (smallest of 6 ONNX variants). Sizes and sha256 from the signed manifest.
Hide all 11 files with their sha256
FileSizesha256
.gitattributes1.58 KBb2edd226c6b1cd2d01eef5665bd45729424086f88ce4e410e183a8795b917f21
README.md5.16 KB5d956d65894ba123fec1cbe09db7af1dfa293c896d30a054ca9c2962fa3c658e
config.json668 B2ba6a6eb9f9078cb94862af365865675d5c0c2c993bd3d3714eac4eb9cf4b396
generation_config.json170 B7a96e632399d82d66264d06a5703593a1e864e1253838bb40f8365b096fddbdc
onnx/model.onnx1.10 MB04c8f56424d08a56367dd64d64080cd608e1cb54aea63c3c76183a901bf22f2a
onnx/model.onnx_data3.17 GB3ebd0a83e63382befc94ec2153946f0dc76e32875bb555c816caf151e9906cdf
onnx/model_bnb4.onnx898 MB9e1a19e4a7e4238981d98efeac188b88420f8a79e466e6e335522fd88ec23b12
onnx/model_int8.onnx795 MBdf4b7587d98428c3ca8b363d177abcbf075de7da1cc16bb71ec3c97b25812041
onnx/model_q4.onnx939 MBbbe88e7dfa97a40b0e7a7c40154324f543749a42e0f2501eed48f9623efd1e65
onnx/model_quantized.onnx795 MBdf4b7587d98428c3ca8b363d177abcbf075de7da1cc16bb71ec3c97b25812041
onnx/model_uint8.onnx795 MBa958f17930e2d078807303dcb92e4f97f5c0036f138c4b721ae6cf61e3aca630
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
5569f34b3c pinned now2026-11-15 05:22 UTC11 files · 7.40 GB

Use it

$ fw get onnx-community/sarashina2.2-0.5b-instruct-v0.1-ONNX
# manifest sha256 1d52c71b506a… · 7.40 GB · 11 files
$ fw verify ./sarashina2.2-0.5b-instruct-v0.1-ONNX onnx-community/sarashina2.2-0.5b-instruct-v0.1-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/sarashina2.2-0.5b-instruct-v0.1-ONNX.json --dir ./sarashina2.2-0.5b-instruct-v0.1-ONNX $ python3 fw.py verify ./sarashina2.2-0.5b-instruct-v0.1-ONNX ./onnx-community__sarashina2.2-0.5b-instruct-v0.1-ONNX.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download onnx-community/sarashina2.2-0.5b-instruct-v0.1-ONNX --revision 5569f34b3c45c4c069f87fe3fac72a5f4dadbca9 --local-dir ./sarashina2.2-0.5b-instruct-v0.1-ONNX

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
5d956d65894ba123fec1cbe09db7af1dfa293c896d30a054ca9c2962fa3c658e
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: sarashina2.2-0.5b-instruct-v0.1-ONNXDate: 2026-11-15Commit: 5569f34Signed: 2DC28CC7B26A283B ✓
Upstream
onnx-community/sarashina2.2-0.5b-instruct-v0.1-ONNX
Pinned commit
5569f34b3c45c4c069f87fe3fac72a5f4dadbca9
Manifest
sarashina2.2-0.5b-instruct-v0.1-ONNX.json · .minisig
Manifest sha256
1d52c71b506a636801da4b0402111fca7ba7edbc91f1865069f1bec46d0a2b29
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:22 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/onnx-community/sarashina2.2-0.5b-instruct-v0.1-ONNX.json $ curl -O https://freeweights.allternit.com/manifests/onnx-community/sarashina2.2-0.5b-instruct-v0.1-ONNX.json.minisig $ minisign -Vm sarashina2.2-0.5b-instruct-v0.1-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

sbintuitions/sarashina2.2-0.5b-instruct-v0.1 · 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/sarashina2.2-0.5b-instruct-v0.1-ONNX
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. sarashina2.2-0.5b-instruct-v0.1-ONNX.json. Provenance. Takedown history: none.
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