CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-32B-NL2Bash-31step
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-32B-NL2Bash-31step

Date: 2026-11-15Commit: cea0d86Signed: 2DC28CC7B26A283B ✓

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

32.8B params65.5GBQwen3-32B-NL2Bash-31stepsafetensorspermissive
FactsParams32.8BSize65.5 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get laion/Qwen3-32B-NL2Bash-31step
# manifest sha256 c91fa104cf49… · 65.5 GB · 25 files
$ fw verify ./Qwen3-32B-NL2Bash-31step laion/Qwen3-32B-NL2Bash-31step
From sourceHosted (signed)laion/Qwen3-32B-NL2Bash-31stepLast check: 2026-11-15 04:30 UTC
Run at homeGet help

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

Fine-tune of Qwen3-32B.

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
25, each with a sha256
Publisher
laion
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-32B

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 04:30 UTCpassed

Model card

From the publisher at commit cea0d86. Shown as plain text with links; images open at the publisher.

Qwen3-32B-NL2Bash-31step#

RL-trained Qwen3-32B on NL2Bash terminal tasks.

Training Details#

  • Base model: Qwen/Qwen3-32B
  • Training method: RLOO (async)
  • Training data: 1,570 NL2Bash tasks (DCAgent2/nl2bash-tasks-cleaned-oracle)
  • Steps: 31 global steps (3 epochs)
  • Infrastructure: 17x4 GH200 GPU nodes (JSC), FSDP2 with TP=2 for inference engines (26 inference engines + 4 policy/ref nodes)
  • Sandbox environment: Beta9/Beam containers for code execution
  • Batch size: 64, 8 samples per prompt
  • Learning rate: 1e-5

Training Curve#

MetricStep 1Step 10Step 20Step 31
Avg Raw Reward0.2140.3140.4160.264
Pass@80.5630.5630.5940.422

License#

Apache 2.0

Files

25 files · 65.5 GBWeights 65.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 25 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.15 KB07f613d5bb3cd1e1cdd4e2a61f74f307a480f0802f2275981957749e4d113f29
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja4.17 KBa55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
config.json2.27 KBe76b96d0b312e0e8752014833e92605c730fdf8c2ac87b8a4d8bf9f6fed458f7
generation_config.json214 B19d9395705449004ddebeeaf62841338a48cc8df85cddb1ca0b2c60396d95c96
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00013.safetensors5.32 GB077033ea5111013cbc1f8db87c30688a712c2effaa31b63a9b5377147a938c1a
model-00002-of-00013.safetensors5.14 GB89016ba377867fabf783f371423cbdb2b06f362f3d38b17dc1c1127234c6c791
model-00003-of-00013.safetensors5.33 GBaaf2a693a60154b3f4310013d8949ca99007310c5c1e63afe5a0f7ae19193190
model-00004-of-00013.safetensors5.14 GB0aeff6ed5a9862ed1f7532bc4ae05c70925c6c6f422e145caa5f78269a04ac9e
model-00005-of-00013.safetensors5.14 GB37e1264c7c0c0579860a3c4f06c29973a70b55dfac02f0f4bbe82979c7f1f88d
model-00006-of-00013.safetensors5.33 GB3dede42b307b6f3990e8ba4610dcd05280fcb34f8904ae0722fc8a011c532574
model-00007-of-00013.safetensors5.14 GB5c13db5d1067d405444c1beacc9aac4735e81b8435b80ecbfcdcc694a3adce01
model-00008-of-00013.safetensors5.14 GBd31f6c5131acc725ecd8ea063c49013ed1c7b497f373999461e0200e491676c2
model-00009-of-00013.safetensors5.33 GB31d2c2e5c19a7423a18e9b15f753951eda67473d0f559bfedae38d32871340c3
model-00010-of-00013.safetensors5.14 GBa28065904868d4f502af864cf5ebecc511808e19bb73fc93383dd6a77d6a66b5
model-00011-of-00013.safetensors5.14 GBc0f90374c9ab100f574dba8fd2790f15207a2d6086c3cc0a188b5510d13c9982
model-00012-of-00013.safetensors5.33 GB01acfeaf31b1724bf1ca2e73bfda28ac9b58593958300800050e984fd9a4523a
model-00013-of-00013.safetensors2.93 GB1a7181e1956eb16a8176a1d50d71fd97eca7834471b31518b32c26b184d6bc53
model.safetensors.index.json58.3 KB046cb77526bba0b2b7ebdf21aa2a5796653675a98a2b268b79271c760b030c7b
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.40 KB443bfa629eb16387a12edbf92a76f6a6f10b2af3b53d87ba1550adfcf45f7fa0
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
cea0d86ef4 pinned now2026-11-15 04:30 UTC25 files · 65.5 GB

Use it

$ fw get laion/Qwen3-32B-NL2Bash-31step
# manifest sha256 c91fa104cf49… · 65.5 GB · 25 files
$ fw verify ./Qwen3-32B-NL2Bash-31step laion/Qwen3-32B-NL2Bash-31step
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/Qwen3-32B-NL2Bash-31step.json --dir ./Qwen3-32B-NL2Bash-31step $ python3 fw.py verify ./Qwen3-32B-NL2Bash-31step ./laion__Qwen3-32B-NL2Bash-31step.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/Qwen3-32B-NL2Bash-31step --revision cea0d86ef4bb705b7aa7fdc8392a618baa92d877 --local-dir ./Qwen3-32B-NL2Bash-31step
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("laion/Qwen3-32B-NL2Bash-31step", revision="cea0d86ef4bb705b7aa7fdc8392a618baa92d877") model = AutoModelForCausalLM.from_pretrained("laion/Qwen3-32B-NL2Bash-31step", revision="cea0d86ef4bb705b7aa7fdc8392a618baa92d877", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve laion/Qwen3-32B-NL2Bash-31step --revision cea0d86ef4bb705b7aa7fdc8392a618baa92d877
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
07f613d5bb3cd1e1cdd4e2a61f74f307a480f0802f2275981957749e4d113f29
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: laion <huggingface.co/laion>Newsgroups: alt.freeweights.qwenSubject: Qwen3-32B-NL2Bash-31stepDate: 2026-11-15Commit: cea0d86Signed: 2DC28CC7B26A283B ✓
Upstream
laion/Qwen3-32B-NL2Bash-31step
Pinned commit
cea0d86ef4bb705b7aa7fdc8392a618baa92d877
Manifest
Qwen3-32B-NL2Bash-31step.json · .minisig
Manifest sha256
c91fa104cf496b1fefa4283faa1136db084f5bdcbe6f7cc9a5f40561d577483d
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:30 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/Qwen3-32B-NL2Bash-31step.json $ curl -O https://freeweights.allternit.com/manifests/laion/Qwen3-32B-NL2Bash-31step.json.minisig $ minisign -Vm Qwen3-32B-NL2Bash-31step.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/Qwen3-32B · this model is a finetune of it

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

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/Qwen3-32B-NL2Bash-31step
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3-32B-NL2Bash-31step.json. Provenance. Takedown history: none.
Source
huggingface.co/laion/Qwen3-32B-NL2Bash-31step

Related models

All of alt.freeweights.qwen →
From: BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen
From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1
From: BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923
From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct
From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA
From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF