CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.glm / SWE-Dev-32B
From: zai-org <huggingface.co/zai-org>Newsgroups: alt.freeweights.glmSubject:

SWE-Dev-32B

Date: 2026-11-14Commit: 6f8669bSigned: 2DC28CC7B26A283B ✓

Text generation model with 32.8B parameters. Safetensors weights, 65.5 GB in all. Published by zai-org under MIT.

32.8B params65.5GBSWE-Dev-32Bsafetensorspermissive
FactsParams32.8BSize65.5 GBFormatssafetensorsTasktext generationLicenseMITFrom sourcepermissive
$ fw get zai-org/SWE-Dev-32B
# manifest sha256 9cd8945cb0b4… · 65.5 GB · 25 files
$ fw verify ./SWE-Dev-32B zai-org/SWE-Dev-32B
From sourceHosted (signed)zai-org/SWE-Dev-32BLast check: 2026-11-14 21:26 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-Coder-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
MIT (permissive)
Files
25, each with a sha256
Publisher
zai-org
Added
2026-11-14
Section
alt.freeweights.glm
Lineage

Original release from the publisher.

Base model: Qwen/Qwen2.5-Coder-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.co2026-11-14 21:26 UTCpassed

Model card

From the publisher at commit 6f8669b. Shown as plain text with links; images open at the publisher.

📝 Paper | 🌐 Github

🚀 SWE-Dev, an open-source Agent for Software Engineering tasks! This repository contains the SWE-Dev-32B model as presented in the paper SWE-Dev: Building Software Engineering Agents with Training and Inference Scaling.

💡 We develop a comprehensive pipeline for creating developer-oriented datasets from GitHub repositories, including issue tracking, code localization, test case generation, and evaluation.

🔧 Based on open-source frameworks (OpenHands) and models, SWE-Dev-7B and 32B achieved solve rates of 23.4% and 36.6% on SWE-bench-Verified, respectively, even approaching the performance of GPT-4o.

📚 We find that training data scaling and inference scaling can both effectively boost the performance of models on SWE-bench. Moreover, higher data quality further improves this trend when combined with reinforcement fine-tuning (RFT). For inference scaling specifically, the solve rate on SWE-Dev increased from 34.0% at 30 rounds to 36.6% at 75 rounds.

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.md1.60 KB45110eeea0173b59b54069211ac5058544ff3ef0a46fa9e15bce8224da7901f2
added_tokens.json605 B58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
config.json770 B76cc16454a4813846f405950b5e305a35a3d8462f7e344c9b026497882165ab3
generation_config.json243 B519a8db66fcfd0d18731eb75169ff8393a6f9c479fd50142fb5ee2580bb9ae64
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00014.safetensors4.89 GB8997f50b4093721bc8b8ae89a9b46e9db13a6d72c93065611707c690c8c9be20
model-00002-of-00014.safetensors4.88 GB2463bb5058fee9148a7b93c82371cad562d62b30ef85298457acd0cb0d824b46
model-00003-of-00014.safetensors4.88 GB8dc93378b213ad1fb3e3316f312709ed34360a2277318ae802597da8099890fb
model-00004-of-00014.safetensors4.88 GBb5361a36394fa1cf8393b7eb8ecde17faf70b0543b7fafb63b6b4559e07a3215
model-00005-of-00014.safetensors4.88 GB3afe1abb8dadaf85afafc7bf1bd4d8ebea36604290a86c0bdc857ab6aee453a3
model-00006-of-00014.safetensors4.88 GBd1bae5fedf087ca6fae7a14df3c672c8fcee512c663f7e50fd51638c3d19a9f2
model-00007-of-00014.safetensors4.88 GB983809e4d7e6ab11a51f3be4cf5aec81a5707878196049c6332683bd60928fde
model-00008-of-00014.safetensors4.88 GB61f38bf4e5ba65309f1d59fff9c661091f33d4e900675ec68f76c6d25013b985
model-00009-of-00014.safetensors4.88 GB18b204c26eef4e2d80e174dc268eeaef74ab120577c75a8610912bc667f5aa0b
model-00010-of-00014.safetensors4.88 GBb9916e90b5347aff496cc53afa3c682ccc502b36730e91886000ed12b32d800c
model-00011-of-00014.safetensors4.88 GBb7b45c0e02195a0f2e03191cfb30a05fe44e65bbafa2a5f955a73549410fb996
model-00012-of-00014.safetensors4.88 GB6cc993507e1a88359a342923bebb9aea0a0d960fe8862ecbe75f53110fa0f310
model-00013-of-00014.safetensors4.88 GB1da8a6dfea7af0028adc554203f451ea03a508d6aa0e1fee9cf7d4aefe8c4505
model-00014-of-00014.safetensors2.12 GB49dcf9810052d1e6f7202869f165074c76d403c15805bc1d4eeef4c5231cd3eb
model.safetensors.index.json63.2 KBe6548816f7ae8cd9fc353a20737f640ad32db6eff13a8c097246084c3207300f
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MB39c6e691f06e7cdc842ecff7f318e21437784a1c34c13b24f4cd0a981a99fe05
tokenizer_config.json7.31 KB7e88129d9769a0b14b1587a7d5e829fe93ac0e1511636471fdfc0811951418e6
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
6f8669b846 pinned now manifest updated, same commit2026-11-14 21:26 UTC25 files · 65.5 GB
6f8669b8462026-11-14 21:26 UTC25 files · 65.5 GB

Use it

$ fw get zai-org/SWE-Dev-32B
# manifest sha256 9cd8945cb0b4… · 65.5 GB · 25 files
$ fw verify ./SWE-Dev-32B zai-org/SWE-Dev-32B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/zai-org/SWE-Dev-32B.json --dir ./SWE-Dev-32B $ python3 fw.py verify ./SWE-Dev-32B ./zai-org__SWE-Dev-32B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download zai-org/SWE-Dev-32B --revision 6f8669b846e9e879a48460b33944ebf4ac6bee57 --local-dir ./SWE-Dev-32B
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("zai-org/SWE-Dev-32B", revision="6f8669b846e9e879a48460b33944ebf4ac6bee57") model = AutoModelForCausalLM.from_pretrained("zai-org/SWE-Dev-32B", revision="6f8669b846e9e879a48460b33944ebf4ac6bee57", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve zai-org/SWE-Dev-32B --revision 6f8669b846e9e879a48460b33944ebf4ac6bee57
Run at home

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-14
Text in
README.md
Text sha256
45110eeea0173b59b54069211ac5058544ff3ef0a46fa9e15bce8224da7901f2
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: zai-org <huggingface.co/zai-org>Newsgroups: alt.freeweights.glmSubject: SWE-Dev-32BDate: 2026-11-14Commit: 6f8669bSigned: 2DC28CC7B26A283B ✓
Upstream
zai-org/SWE-Dev-32B
Pinned commit
6f8669b846e9e879a48460b33944ebf4ac6bee57
Manifest
SWE-Dev-32B.json · .minisig
Manifest sha256
9cd8945cb0b43b3ef956e9ec92fec9099be793730cecd168b4db7d5526fbdcd7
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:26 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/zai-org/SWE-Dev-32B.json $ curl -O https://freeweights.allternit.com/manifests/zai-org/SWE-Dev-32B.json.minisig $ minisign -Vm SWE-Dev-32B.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-Coder-32B-Instruct · 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 zai-org/SWE-Dev-32B
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. SWE-Dev-32B.json. Provenance. Takedown history: none.
Source
huggingface.co/zai-org/SWE-Dev-32B

Related models

All of alt.freeweights.glm →
From: bartowski <huggingface.co/bartowski>Subject: arcee-ai_GLM-4-32B-Base-32K-GGUF
From: ggml-org <huggingface.co/ggml-org>Subject: AutoGLM-Phone-9B-GGUF
From: zai-org <huggingface.co/zai-org>Subject: cogagent-chat-hf
From: zai-org <huggingface.co/zai-org>Subject: CogView3-Plus-3B
From: zai-org <huggingface.co/zai-org>Subject: cogvlm-base-490-hf
From: laion <huggingface.co/laion>Subject: dev_set_part1_10k_glm_4_7_traces_jupiter