CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / Sky-T1-32B-Preview
From: NovaSky-AI <huggingface.co/NovaSky-AI>Newsgroups: alt.freeweights.textSubject:

Sky-T1-32B-Preview

Date: 2026-11-15Commit: 1e3f4c6Signed: 2DC28CC7B26A283B ✓

Text generation model with 32.8B parameters. Safetensors weights, 65.5 GB in all. Published by NovaSky-AI under Apache-2.0.

32.8B params65.5GBSky-T1-32B-Previewsafetensorspermissive
FactsParams32.8BSize65.5 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get NovaSky-AI/Sky-T1-32B-Preview
# manifest sha256 5da7de28ab84… · 65.5 GB · 24 files
$ fw verify ./Sky-T1-32B-Preview NovaSky-AI/Sky-T1-32B-Preview
From sourceHosted (signed)NovaSky-AI/Sky-T1-32B-PreviewLast check: 2026-11-15 03:57 UTC
Run at homeGet help

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

Fine-tune of Qwen2.5-32B-Instruct.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
65.5 GB
Weights
65.5 GB (safetensors)
Parameters
32.8B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
24, each with a sha256
Publisher
NovaSky-AI
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: Qwen/Qwen2.5-32B-Instruct

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 03:57 UTCpassed

Model card

From the publisher at commit 1e3f4c6. Shown as plain text with links; images open at the publisher.

Model Details#

Model Description#

This is a 32B reasoning model trained from Qwen2.5-32B-Instruct with 17K data. The performance is on par with o1-preview model on both math and coding. Please see our blog post for more details.

  • Developed by: NovaSky Team from Sky Computing Lab at UC Berkeley.

Training Details#

Training Data#

17K verified correct responses from Qwen/QwQ-32B-Preview on coding, math. In addition, we add the science portion from the Still-2 paper.

Training Procedure#

We perform supervised fine tuning on the data, with a batch size of 96.

Speeds#

We use Llama-Factory for training. On 8 H100, the training takes 19 hours with DeepSpeed Zero-3 Offload.

Evaluation#

Sky-T1-32B-PreviewQwen-2.5-32B-InstructQwQo1-preview
Math50082.476.285.481.4
AIME202443.316.750.040.0
LiveCodeBench-Easy86.384.690.792.9
LiveCodeBench-Medium56.840.856.354.9
LiveCodeBench-Hard17.99.817.116.3
GPQA-Diamond56.845.552.575.2

Acknowledgement#

We would like to thanks the compute resources from Lambda Lab and AnyScale. We would like to thanks the academic feedback and support from the Still-2 Team, and Junyang Lin from the Qwen Team.

Citation#

Please considering citing our blog post if you found it useful for your research. Thank you!

@misc{sky_t1_2025,
  author       = {NovaSky Team},
  title        = {Sky-T1: Fully open-source reasoning model with o1-preview performance in $450 budget},
  howpublished = {https://novasky-ai.github.io/posts/sky-t1},
  note         = {Accessed: 2025-01-09},
  year         = {2025}
}

Files

24 files · 65.5 GBWeights 65.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 24 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md2.54 KB537c1584d3318e9d45051d1db82f3b990c798154bdbc25ee02d63e805d077884
added_tokens.json605 B58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
config.json817 Bbc3a1551654824b12f27038dfa64662345569e68a971ef86415a295071b942d9
generation_config.json243 Bc71477a85f061ff54313cdaad39ead45f00942f4cbbcd9ab07bfc137cb7d38c2
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00014.safetensors4.89 GB3610073d11dbc86ee766252bc1375cd56996b93b9ab92148fd4e590a13d3cfbe
model-00002-of-00014.safetensors4.88 GB95d49642d3f0a71453f93188424908250b9f8174355a17edaab320364622e24e
model-00003-of-00014.safetensors4.88 GB94c8a0be767501ea8309f7acd63989179e25c90b2e8d5ebce41912fafb9c4bab
model-00004-of-00014.safetensors4.88 GB96c5c48f64c4c11c79aedb18398e4fc4a059da3ba8d48a1944bf5e76e52d692e
model-00005-of-00014.safetensors4.88 GB14ab6a6ba45cfaf5ad66c1ab4e30084b67fad70e191a1e624eb8d7366e4e5608
model-00006-of-00014.safetensors4.88 GBf4c9ec44a3d3d399d6a1c3226c0b6c4e3b5cef7df1df763c8cdb2df839d653f3
model-00007-of-00014.safetensors4.88 GBce5b22d65e4eb084e90a146e9d99867ed35e9b5f3c4fb5e0f922fe2229bffddb
model-00008-of-00014.safetensors4.88 GB7dc96cb8b71a96694fe2f9b272ce6d71401189fa94714d2ae579a26483de7168
model-00009-of-00014.safetensors4.88 GBf3b0532176fb008b934eccb6b0c61bfdc3d24a9cd16e177a661696ebbe25eda6
model-00010-of-00014.safetensors4.88 GB38119287c842e03398a88ddb716e0ec9f30cf6c8bc78133456e8d69226c04aac
model-00011-of-00014.safetensors4.88 GBbba0982ad93054038dbe5e7a0fb9283836243e95ee2aae40139ef1623bf32400
model-00012-of-00014.safetensors4.88 GBccca8b083083c1b466acbd9526168be3b1467d478f6d22a3bac07c5ad95209e9
model-00013-of-00014.safetensors4.88 GBa86f3751a6cc674a46b98b3f1b4b37c953447a7b2c132fc09ef40f7591fe02ef
model-00014-of-00014.safetensors2.12 GB7236a39325500d2f0f2eb684045b17b53d48d089faf2073bfd2353dab85e2d56
model.safetensors.index.json63.2 KBe6548816f7ae8cd9fc353a20737f640ad32db6eff13a8c097246084c3207300f
special_tokens_map.json616 B6676f091c8bc4d1b50146427cfde92073402866b87b6e39223227931b70083e9
tokenizer_config.json7.37 KB8864f53f85df92bc281866d42942bab86e7ea72c418c4de085d895ff5ff9d908
vocab.json3.38 MB87a257b04b17642a0688c98cd1df89c398bda4fee532d6f88b38a659ecb4ac8d
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
1e3f4c62a3 pinned now2026-11-15 03:57 UTC24 files · 65.5 GB

Use it

$ fw get NovaSky-AI/Sky-T1-32B-Preview
# manifest sha256 5da7de28ab84… · 65.5 GB · 24 files
$ fw verify ./Sky-T1-32B-Preview NovaSky-AI/Sky-T1-32B-Preview
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/NovaSky-AI/Sky-T1-32B-Preview.json --dir ./Sky-T1-32B-Preview $ python3 fw.py verify ./Sky-T1-32B-Preview ./NovaSky-AI__Sky-T1-32B-Preview.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download NovaSky-AI/Sky-T1-32B-Preview --revision 1e3f4c62a30c7ce70f4b3a3b952895d866943551 --local-dir ./Sky-T1-32B-Preview
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("NovaSky-AI/Sky-T1-32B-Preview", revision="1e3f4c62a30c7ce70f4b3a3b952895d866943551") model = AutoModelForCausalLM.from_pretrained("NovaSky-AI/Sky-T1-32B-Preview", revision="1e3f4c62a30c7ce70f4b3a3b952895d866943551", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve NovaSky-AI/Sky-T1-32B-Preview --revision 1e3f4c62a30c7ce70f4b3a3b952895d866943551
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
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
537c1584d3318e9d45051d1db82f3b990c798154bdbc25ee02d63e805d077884
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: NovaSky-AI <huggingface.co/NovaSky-AI>Newsgroups: alt.freeweights.textSubject: Sky-T1-32B-PreviewDate: 2026-11-15Commit: 1e3f4c6Signed: 2DC28CC7B26A283B ✓
Upstream
NovaSky-AI/Sky-T1-32B-Preview
Pinned commit
1e3f4c62a30c7ce70f4b3a3b952895d866943551
Manifest
Sky-T1-32B-Preview.json · .minisig
Manifest sha256
5da7de28ab84c19be792309913620db5e8509b0660a89e6eb13ceebe6e551aa2
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:57 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/NovaSky-AI/Sky-T1-32B-Preview.json $ curl -O https://freeweights.allternit.com/manifests/NovaSky-AI/Sky-T1-32B-Preview.json.minisig $ minisign -Vm Sky-T1-32B-Preview.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

Qwen/Qwen2.5-32B-Instruct · this model is a finetune of it

1 model in the catalog name this one as their parent.

Quantizations
1
Quantizations 1
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download NovaSky-AI/Sky-T1-32B-Preview
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Sky-T1-32B-Preview.json. Provenance. Takedown history: none.
Source
huggingface.co/NovaSky-AI/Sky-T1-32B-Preview

Variants

1 quantized or adapter build of Sky-T1-32B-Preview. Each has its own license check and page.

SubjectSizeParamsLicenseDate
Sky-T1-32B-Preview-GGUFHosted (signed) From: bartowski in alt.freeweights.text519 GB—Permissive2026-11-15

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