CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / jtd-d1-18-30B
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

jtd-d1-18-30B

Date: 2026-11-15Commit: 167fa47Signed: 2DC28CC7B26A283B ✓

Reinforcement learning model with 30.5B parameters. Safetensors weights, 61.3 GB in all. Published by laion under Apache-2.0.

30.5B params61.3GBjtd-d1-18-30Bsafetensorspermissive
FactsParams30.5BSize61.3 GBFormatssafetensorsTaskreinforcement learningLicenseApache-2.0From sourcepermissive
$ fw get laion/jtd-d1-18-30B
# manifest sha256 493123f0a8fa… · 61.3 GB · 59 files
$ fw verify ./jtd-d1-18-30B laion/jtd-d1-18-30B
From sourceHosted (signed)laion/jtd-d1-18-30BLast check: 2026-11-15 04:22 UTC
Run at homeGet help

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

Fine-tune of Qwen3-Coder-30B-A3B-Instruct.

Works with

Run8Fine-tune7Convert8Scan2

Runs with

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

TransformersLocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
61.3 GB
Weights
61.1 GB (safetensors)
Parameters
30.5B
Formats
safetensors
Task
reinforcement learning
License
Apache-2.0 (permissive)
Files
59, each with a sha256
Publisher
laion
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-Coder-30B-A3B-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 04:22 UTCpassed

Model card

From the publisher at commit 167fa47. Shown as plain text with links; images open at the publisher.

laion/jtd-d1-18-30B#

Jupiter TaskTrove DAPO campaign, arm D1 — DAPO-core arm — D0 + clip-higher (eps 0.2/0.4) + dynamic sampling (filter, default cap). Dataset: laion/codeforces-v2 (10,000 competitive-programming tasks; ckpt_interval 1). Base model Qwen/Qwen3-Coder-30B-A3B-Instruct; FSDP2 fully-async trainer, 16 policy GPUs (4 nodes x 4 GH200) + 4 vLLM engines (TP2); Harbor/Daytona sandboxed terminus-2 rollouts.

  • Checkpoint: step 18 of 80, selected by trailing-5 EMA of reward/avg_raw_reward over the arm's full step series (campaign ended early on platform degradation + data-quality grounds; final banked step 18).
  • Launch config: rl_config.yaml in this repo; metrics + per-link logs in training_logs/.
  • pass@8 reads 1.0 on the dynamic-sampling arms (d1/d2/d4) are post-filter by construction; use reward/avg_raw_reward series in training_logs/ for cross-arm comparison.

Training Traces#

Training-time Daytona/Harbor rollouts: open-athena/jtd-d1 — the last episode of each trial, conserved at a 25% subsample: every 4th trial dir of the arm's full trace store (31104 enumerated at upload; 156 shards, 27571 rows). Owner-instructed conservation quota for this campaign's cleanup, not the uploader default.

Files

59 files · 61.3 GBWeights 61.1 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 59 files with their sha256
FileSizesha256
.gitattributes2.22 KB94466f5a6c0b80bd9748614c5561998bafa8612d8ad0efbf0205419d8fd529d6
README.md1.48 KB36001e0ad4038257aa526e14339b94a26eef597fa9aa69cdc0d119c9a8b39f72
chat_template.jinja6.21 KB5a38bfa05833266240066aedc497decc9b00cc0d3e3b8cceea98cf530196ab06
config.json1.02 KBe58feff12a5ed7fce42eb6ae6054502ba786843a515a2f6f4053adf5fb75f2bd
generation_config.json217 B2cb42f3bbca69b7dbf925354f69a3a8c5ef2184f33f8c2cd744d24aaa8e6ca69
model-00001-of-00002.safetensors50.0 GB85fe18968dcf1c753ee1af7dc6c1f1a4dd65bfd1668e0c57c7a376e24d88051c
model-00002-of-00002.safetensors11.1 GB6c53edbcd720da12bea4da2b1375104c6d6826caaf41479892b588c31978f63e
model.safetensors.index.json1.70 MB8056f5e61a77bcc39322368320783ace12dfd0877cf642821620e33341d5d25e
rl_config.yaml15.8 KB096e72eab51e9fa9220a28af002381efa41acaced3dd46fbf785e97e0478c7e1
tokenizer.json11.4 MBbe75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
tokenizer_config.json694 B700f87d8a901e6213c9b339ae3a0ff3f1deb2bfc39f1f66c85de3669a566fa84
training_logs/20260901_001450_metrics_jtd-d1_10_jtd-d1_1457840.csv3.79 KBf35e672dd09b32a40b66606d10c04417a76c42f1be27c1b1c774ab915ed48257
training_logs/20260901_001450_metrics_jtd-d1_11_jtd-d1_1461200.csv5.65 KB4329d8cbdf5768e96d8691f54fef8129cddfec34ff12619aa5ba6cea37150617
training_logs/20260901_001450_metrics_jtd-d1_11_jtd-d1_1461201.csv4.39 KB7adaec44805eb19afb592ab3dccfa14b99142831f623e80f1ef21f6abfa7d4cd
training_logs/20260901_001450_metrics_jtd-d1_11_jtd-d1_1461202.csv4.39 KB4bf45b17b75ca0e595974042cda9b7ebdea61cf57fbc0cc78604434132a5b8f7
training_logs/20260901_001450_metrics_jtd-d1_12_jtd-d1_1531075.csv4.51 KBe0a32e862671e58b594890eedf217c28064b730c5852ba6c58c71a003bdebf52
training_logs/20260901_001450_metrics_jtd-d1_12_jtd-d1_1531076.csv5.22 KB0df70538a598069e5b7d28019f60c56f3477db9c83de38e4d553302880c351ab
training_logs/20260901_001450_metrics_jtd-d1_12_jtd-d1_1531080.csv3.85 KB13cbadfc7369d5a4e6756937d6f2ed401515a29fb4711eee0a339dad35d7213d
training_logs/20260901_001450_metrics_jtd-d1_8_jtd-d1_1440143.csv3.59 KB46973c9da935d48ae82ec9b77635b7752399f62b508716aca782942060d90c71
training_logs/20260901_001450_metrics_jtd-d1_9_jtd-d1_1447018.csv6.11 KBdf81d72400ede56ee371a97b5e9f139c5fe997063beeb035908c86d762a2448d
training_logs/20260901_001450_metrics_jtd-d1_9_jtd-d1_1447020.csv3.36 KBac378a867106e0c56874da2d65dfc1d2b28b3cf855af8b89c4b59e54a4362abe
training_logs/20260901_001450_metrics_report.md29.4 KBfd5f56a8c18590d9ff63159db669085d1c3f7533de807cf99d273cc62c715fd6
training_logs/20260901_001450_metrics_table.csv18.0 KB8ace957815e7d1fda23aea3fef0a88e0f78f8c03e35b180a7b3a50898ca93f9d
training_logs/20260901_001450_reward_vs_steps.png199 KBd1c9ee24b3fb33052d2d5aa755c54817bf1a71168a4c35551dbb47eaa3a39626
training_logs/20260901_001450_trial_results.csv9.67 MB13496f2bfe4d6ef41b18e9274c6b162ab9bf305263fe75261bc24b88c3f5df2a
training_logs/20260901_001450_turn_count_distribution.png156 KBda33ecf9f8f047bfde9bb12adbd5dbafe944b40b2323f3803e148a75042d83c6
training_logs/20260901_001450_vllm_metrics_jtd-d1_10_jtd-d1_1457840.csv397 KB6ea43060ded042b870d06eb2360568746cd9e13dda684c6c951b69a23677e5dc
training_logs/20260901_001450_vllm_metrics_jtd-d1_11_jtd-d1_1461200.csv676 KB974b183ca286e761f3bdd3f0dad8f152d5dd00996be99f80e6f02585f53e4a70
training_logs/20260901_001450_vllm_metrics_jtd-d1_11_jtd-d1_1461201.csv691 KB8e4992ea5763ab52facc6f4292f9dc9fb8f7a2c54d2c244ed7bb0e479be4d008
training_logs/20260901_001450_vllm_metrics_jtd-d1_11_jtd-d1_1461202.csv691 KB234e6c931661923977c382f82a84df3010b390b28cb55431326ba29f338c09f3
training_logs/20260901_001450_vllm_metrics_jtd-d1_11_jtd-d1_1461203.csv402 KB023840653deaa5254232c555253a29e582ee8c3dce2769fdc7c833660e0a8f7a
training_logs/20260901_001450_vllm_metrics_jtd-d1_11_jtd-d1_1461204.csv274 KB23910ffdc3124f712f01929d9cfc5e8917d3f8a2d51be0b7e0695e07b3dcc8f6
training_logs/20260901_001450_vllm_metrics_jtd-d1_11_jtd-d1_1461205.csv350 KB703ffcf6d13374c6b9d67112a04f3d03413d9824d316f068e9accf4efec67c49
training_logs/20260901_001450_vllm_metrics_jtd-d1_12_jtd-d1_1531075.csv676 KB5e213048f4ba7372f853450c8f486990a0a80fc2725b8cac71ae29588c12d860
training_logs/20260901_001450_vllm_metrics_jtd-d1_12_jtd-d1_1531076.csv672 KB3d0144a3451d1dbc9c8ec9d4fa6d35566747af4540a3680df0d23577f83cd7cf
training_logs/20260901_001450_vllm_metrics_jtd-d1_12_jtd-d1_1531077.csv408 KBaee8d5d50e0d2e844f4716e1f41cfd5794e462f24c60c3fa21c17f50e0b12178
training_logs/20260901_001450_vllm_metrics_jtd-d1_12_jtd-d1_1531080.csv655 KBe1c7f7e0509fdf7f941e2c2e4aa7aa478212324c9dd17cda55d8c5f20b09fc8d
training_logs/20260901_001450_vllm_metrics_jtd-d1_8_jtd-d1_1440143.csv387 KB81069395095ed38297e814af186b2849ccf15e075fc0a9e9ebeddd2bad00f042
training_logs/20260901_001450_vllm_metrics_jtd-d1_9_jtd-d1_1447018.csv670 KB7828daaa80a73fd46a3365924a7886ddcbe44feccb9405b9d4ff8dd9e205156c
training_logs/20260901_001450_vllm_metrics_jtd-d1_9_jtd-d1_1447020.csv402 KB8f3b49d2f4942ca22197513f57f6cf607aa1f5241a8130f6382a7ff2be9ee5de
training_logs/20260901_001450_vllm_metrics_jtd-d1_9_jtd-d1_1447021.csv109 KB969a35de39000a9c0975121d0f20c94b26370e23b521b90bf4962c389124203e
training_logs/20260901_001450_vllm_metrics_table.csv9.60 MB81bc40bf4ce6aa910efad814706c4b2b1f4f4a45a8a3692b1086aa508fd7102e
training_logs/jtd-d1_10_jtd-d1_1457840.out4.70 MBd65587e6a34f7c462654af79a917902a6c8efdcce1eb5af0be1f2f77ee315bb3
training_logs/jtd-d1_11_jtd-d1_1461200.out6.72 MB2184aadd4935a72588a6a4a8e1320413036f9f4c88df67b083cab3e92516f226
training_logs/jtd-d1_11_jtd-d1_1461201.out6.43 MBb3a8f51ac2ba274c446f274b795b43f15babe69bf1f08de1d003c403f8314aee
training_logs/jtd-d1_11_jtd-d1_1461202.out6.48 MBf55de172a9bf47a12a95df54fe9d43e482c233599d1d8ebb838d0f06b163de0d
training_logs/jtd-d1_11_jtd-d1_1461203.out49.9 MB714551d0c811fee1fd1871773b16996164153e216f4fde8707d2c85fa5e64f69
training_logs/jtd-d1_11_jtd-d1_1461204.out28.6 MB92a2bd717396abbfe90084fc8fe7dc6f833b951dc219b3c43787d8aea0e34d8b
training_logs/jtd-d1_11_jtd-d1_1461205.out3.14 MBa7b9df3a3b663b2c653153714acf7984a56e66b5ea888c26843f6eb9a6f5af7b
training_logs/jtd-d1_12_jtd-d1_1531075.out15.4 MBc2f0e4f6bde67dd2efe69e94b4a54faea4982e2bfe2b99fcaced3fb0dea04fcd
training_logs/jtd-d1_12_jtd-d1_1531076.out23.4 MB579a44fe27758594acde32c7001e846ccac9f26af5a388292bdbf396b2ebdebc
training_logs/jtd-d1_12_jtd-d1_1531077.out26.9 MBc4df5298d11d5f957153d720814a746887d486582ef7075b7843321e4bf7c15e
training_logs/jtd-d1_12_jtd-d1_1531078.out169 KB1434051220dc7facc2bec57d34b50edffc7f7a737ac82834278265acc5662ca9
training_logs/jtd-d1_12_jtd-d1_1531080.out46.9 MB86474723dbec1f7bd6f8a080f7b14638dbb8c94bf64ba70eef55b2903ccbbb4c
training_logs/jtd-d1_12_jtd-d1_1531081.out25.9 KBaf425fd4b127c23c2f5bd76f63bb6eb53dbf0f380facf48feb6cb2c23ae16c5d
training_logs/jtd-d1_8_jtd-d1_1440143.out3.34 MBc8b57a00bc1e2bbfda1e3ebf3e127b304d525f32ddd4b2bd558d42cb76c0ffd9
training_logs/jtd-d1_9_jtd-d1_1447018.out6.88 MBe4ed0cf5da9ae1e80fd93c9f98cab07f6c2d0f3132a32c288167cbea2244195a
training_logs/jtd-d1_9_jtd-d1_1447020.out4.28 MBf5c4e442a8f24a0213975ba6461a60ce6af24a519195f92ce4fb88be7cafeb34
training_logs/jtd-d1_9_jtd-d1_1447021.out1.16 MB5103d11ca6f78baef4a8dd65f6524fe0e904270176ffc87a235ce377b68a3d81
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
167fa475a1 pinned now2026-11-15 04:22 UTC59 files · 61.3 GB

Use it

$ fw get laion/jtd-d1-18-30B
# manifest sha256 493123f0a8fa… · 61.3 GB · 59 files
$ fw verify ./jtd-d1-18-30B laion/jtd-d1-18-30B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/jtd-d1-18-30B.json --dir ./jtd-d1-18-30B $ python3 fw.py verify ./jtd-d1-18-30B ./laion__jtd-d1-18-30B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/jtd-d1-18-30B --revision 167fa475a108a8deb926d66a363481a251c12376 --local-dir ./jtd-d1-18-30B
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
36001e0ad4038257aa526e14339b94a26eef597fa9aa69cdc0d119c9a8b39f72
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.textSubject: jtd-d1-18-30BDate: 2026-11-15Commit: 167fa47Signed: 2DC28CC7B26A283B ✓
Upstream
laion/jtd-d1-18-30B
Pinned commit
167fa475a108a8deb926d66a363481a251c12376
Manifest
jtd-d1-18-30B.json · .minisig
Manifest sha256
493123f0a8fa5da124da51aad9967128fa9600f41302899e3acdc9465ccedcb6
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:22 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/jtd-d1-18-30B.json $ curl -O https://freeweights.allternit.com/manifests/laion/jtd-d1-18-30B.json.minisig $ minisign -Vm jtd-d1-18-30B.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-Coder-30B-A3B-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 laion/jtd-d1-18-30B
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. jtd-d1-18-30B.json. Provenance. Takedown history: none.
Source
huggingface.co/laion/jtd-d1-18-30B

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