alt.freeweights.text / jtd-d5-69-30B

From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

jtd-d5-69-30B

Date: 2026-11-15Commit: 1310831Signed: 2DC28CC7B26A283B ✓

Reinforcement learning model with 30.5B parameters. Safetensors weights, 61.6 GB in all. Published by laion under Apache-2.0.

30.5B params61.6GBjtd-d5-69-30Bsafetensorspermissive

FactsParams30.5BSize61.6 GBFormatssafetensorsTaskreinforcement learningLicenseApache-2.0From sourcepermissive

$ fw get laion/jtd-d5-69-30B
# manifest sha256 fd5099b593b6… · 61.6 GB · 69 files
$ fw verify ./jtd-d5-69-30B laion/jtd-d5-69-30B

From sourceHosted (signed)laion/jtd-d5-69-30BLast check: 2026-11-15 04:21 UTC

Run at home Get 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

Run8 Fine-tune7 Convert8 Scan2

Runs with

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

Transformers LocalAI tinygrad Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Overview

Size: 61.6 GB
Weights: 61.1 GB (safetensors)
Parameters: 30.5B
Formats: safetensors
Task: reinforcement learning
License: Apache-2.0 (permissive)
Files: 69, 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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 04:21 UTC	passed

Model card

From the publisher at commit 1310831. Shown as plain text with links; images open at the publisher.

laion/jtd-d5-69-30B#

GSPO checkpoint (step 69; the run closed at step 73 of 80 when its restart chain was sealed at close-out — the final links ran through the 2026-08-28 GPFS/Daytona platform degradation) from the Jupiter TaskTrove DAPO campaign, arm D5 — the D0 plain-GRPO control with the objective swapped to GSPO: policy_loss_type: gspo, eps 3e-4/4e-4 (paper range), loss_reduction: sequence_mean, use_tis: false, no dynamic sampling, no KL.

Base model: Qwen/Qwen3-Coder-30B-A3B-Instruct
Training data: laion/codeforces-v2 (10,000 competitive-programming tasks, sandboxed agent rollouts via Harbor/Daytona, terminus-2 harness, FSDP2 fully-async trainer on 16x GH200)
Checkpoint selection: trailing-5 EMA of reward/avg_raw_reward (0.2784 at step 69 vs 0.2481 at step 72; the same step wins on EMA of reward/avg_pass_at_8, 0.4845 vs 0.4723)
Launch config: rl_config.yaml in this repo
Metrics + logs: training_logs/ in this repo (per-link metrics CSVs, trial results, report, all 17 job logs + the checkpoint-export job log)

Training Traces#

Training-time Daytona/Harbor rollouts: open-athena/jtd-d5 (the last episode of each trial — the rollouts the policy trained on after rollback/truncation). This trace dataset conserves a deterministic 25% subsample of the full trial set (17,722 of 70,886 trials; every 4th trial of the sorted list) = 15,880 rows / 93 shards, per a storage-conservation decision at cleanup time.

Files

69 files · 61.6 GBWeights 61.1 GB (safetensors). Sizes and sha256 from the signed manifest.

Show all 69 files with their sha256

File	Size	sha256
.gitattributes	1.89 KB	ddf34cedcab1e8ef0175c0b0014c80495790cb801ffeef2378ccafbc61c93744
README.md	1.72 KB	bbb820fc02c4f60aa8e9160bfb5970be3f5078fdfebe18607790597506bf2fb0
chat_template.jinja	6.21 KB	5a38bfa05833266240066aedc497decc9b00cc0d3e3b8cceea98cf530196ab06
config.json	1.02 KB	e58feff12a5ed7fce42eb6ae6054502ba786843a515a2f6f4053adf5fb75f2bd
generation_config.json	217 B	2cb42f3bbca69b7dbf925354f69a3a8c5ef2184f33f8c2cd744d24aaa8e6ca69
model-00001-of-00002.safetensors	50.0 GB	6e139ac79d1e0b93d8f16cca74a2aca35222aa70512d34df1c670329a8b4c4f6
model-00002-of-00002.safetensors	11.1 GB	c4a72553e1d6fa4bb694e040047fb0ea1cb69ee9f7bf6b893a12f5e5faca2681
model.safetensors.index.json	1.70 MB	8056f5e61a77bcc39322368320783ace12dfd0877cf642821620e33341d5d25e
rl_config.yaml	14.3 KB	877252865d6e6bde4155951b97e0ff9041cf637f90dcb04365e540571dc0f51a
tokenizer.json	11.4 MB	be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
tokenizer_config.json	694 B	700f87d8a901e6213c9b339ae3a0ff3f1deb2bfc39f1f66c85de3669a566fa84
training_logs/20260829_025105_metrics_jtd-d5_1468466.csv	6.08 KB	76f89dfbe211a4733b863f05ae83e8bec1c84138adae94c700b92bbff9fea831
training_logs/20260829_025105_metrics_jtd-d5_1468467.csv	3.47 KB	1bd9c205a9a78c7b5324809f5264adc24b2bd9a50574679928623a0001cecf94
training_logs/20260829_025105_metrics_jtd-d5_1468468.csv	6.55 KB	4ceff6fa2064638a081c972a33a5259a2020ab8dc19afea6ab08e9020f3aca48
training_logs/20260829_025105_metrics_jtd-d5_1468469.csv	2.96 KB	fd693ad53893fba23b0f4d9c373806041e56cb30ccae947a244fd6b4e386e63a
training_logs/20260829_025105_metrics_jtd-d5_1468470.csv	4.96 KB	2ff9c848b147c68ea2b0a159f4c3fad68216efe9196255614ac3a8ab5b7f04c8
training_logs/20260829_025105_metrics_jtd-d5_1468471.csv	5.49 KB	787bd63ab5e474e46935e8dc8ace8cd38913a84d746ab239e0cd77fdc772bd69
training_logs/20260829_025105_metrics_jtd-d5_1477132.csv	4.08 KB	09dfacfc1bb4eb1f2c6f5d348cb2c2e6b15cbfa1ef7d8c4a55b0b2cbd030cd70
training_logs/20260829_025105_metrics_jtd-d5_1477135.csv	6.68 KB	fb16fddf24e1d8a4a70b35954d6f765d7ae3ee46541e2836f06f17af2c366ef0
training_logs/20260829_025105_metrics_jtd-d5_1477136.csv	6.55 KB	4009bc0c14c277d30938232aeeaf252e093d1afc5e0c0db1f7b78b297f216327
training_logs/20260829_025105_metrics_jtd-d5_1487670.csv	6.01 KB	a48b6bb84b3235a8c05a05158d17f46594e5b42ced2254e73cc929c5aa42a6db
training_logs/20260829_025105_metrics_jtd-d5_1487671.csv	5.14 KB	d3da9670f4916bcf6465adcc574a030e7af7a2224d1aa2508cde3c9324632a66
training_logs/20260829_025105_metrics_jtd-d5_1506708.csv	5.45 KB	5079d16e37ff816aa9b5c3cbec95ce389046e89c6ced5731c5bd2b22df5038ac
training_logs/20260829_025105_metrics_jtd-d5_1506709.csv	4.33 KB	d8954ef679e9dccee19d5fdbccc58ecd1f31c351961d3fafdf1c4357162fc639
training_logs/20260829_025105_metrics_jtd-d5_1506710.csv	7.10 KB	d6a154ba9844ccc1513f83be6e4774d54f580fe1fec8344875129762e9d7c8d7
training_logs/20260829_025105_metrics_jtd-d5_1506711.csv	9.76 KB	23aae70cc7c7c356d301fa4c8623b7ca1fbd96bc9fe8b3f13a7ca86f6d5cb20c
training_logs/20260829_025105_metrics_jtd-d5_1506712.csv	7.10 KB	5a2a5e0f45681726ceb9404649dcedccf8810b71fd57bff7436752b6f0deacec
training_logs/20260829_025105_metrics_jtd-d5_1520450.csv	6.78 KB	d0957c9dc3d9257876926ee3ebe09a2ef08ff957d934d6b616f009e9db2b506e
training_logs/20260829_025105_metrics_report.md	35.7 KB	e8b5d78309a4e3234d9f6f373c4595542ab79da2fab8fee3510694bb507ed40c
training_logs/20260829_025105_metrics_table.csv	58.0 KB	50d21ee3050ffa668f8249f8fcf22b9799cae483f23b0a474f1cb4a1acac1c6a
training_logs/20260829_025105_reward_vs_steps.png	287 KB	1bc3042dc8a14b8be04457ea1e584155884e6238cf6ed40efcff375bfa86ed3e
training_logs/20260829_025105_trial_results.csv	5.40 MB	b190f4824b4664318d35e53459f025f47bfd01629aaf897fd4849883640d1acb
training_logs/20260829_025105_turn_count_distribution.png	140 KB	2a8bebee2ad3ec24c495e95ca5445c219b4abac1802d3e09cac96c301260e2a7
training_logs/20260829_025105_vllm_metrics_jtd-d5_1468466.csv	276 KB	4e9be533d23de6fce340b075dbb2b932066f62cacc9b2bc32dba94bcbdd604b4
training_logs/20260829_025105_vllm_metrics_jtd-d5_1468467.csv	148 KB	7011316ddc803b9d9cbf0345d696d015c9a2f5f847467bb5195db2256c63027d
training_logs/20260829_025105_vllm_metrics_jtd-d5_1468468.csv	310 KB	281501512708adfa297f789e1a6a52e9cfccd4e7fa3136b29df5601ec07b4cb2
training_logs/20260829_025105_vllm_metrics_jtd-d5_1468469.csv	121 KB	da93c62c298856321559697e915ced6735ab3e33b5483b0293d9c97ccb891d7e
training_logs/20260829_025105_vllm_metrics_jtd-d5_1468470.csv	223 KB	05a7526c343d18c311d6a0a0febb659c10e977e858c0da041e4cd7c4856beab6
training_logs/20260829_025105_vllm_metrics_jtd-d5_1468471.csv	218 KB	06dfc19413337dd4562f2e4911f76ba2ec3b2ef94413b6cdca857d3292211fef
training_logs/20260829_025105_vllm_metrics_jtd-d5_1477132.csv	54.0 KB	3d3f900dee8d83cec14a40e755e9e9300edf8c0281de35dea9af8fd10b73f3d8
training_logs/20260829_025105_vllm_metrics_jtd-d5_1477135.csv	297 KB	ac64a47df10051d3db4866c9e72789e6323b3cc461ed0330fd2a7571e0c1ddf7
training_logs/20260829_025105_vllm_metrics_jtd-d5_1477136.csv	269 KB	3f8e88b3f7d3479043c09ffed2718aa2256560fe6d5fb3023725f64378ca174e
training_logs/20260829_025105_vllm_metrics_jtd-d5_1487670.csv	233 KB	53955ea5f708e734f292b5d8d1b6a9e4878c00e19c28bb1c3aa1a6d67075eaea
training_logs/20260829_025105_vllm_metrics_jtd-d5_1487671.csv	108 KB	ed443c86b11a7d5389df507692ff047b8bbeaeb65de1b1f180c1955309a4ebe8
training_logs/20260829_025105_vllm_metrics_jtd-d5_1506708.csv	184 KB	942a840554ee8e5af8301f915a20a41d49efdd49844f2cca93d4a297a73a9e68
training_logs/20260829_025105_vllm_metrics_jtd-d5_1506709.csv	120 KB	37790d708abdd87c0ee789afe29f91b01a08454ccc4513d58e6bc307d6abe19c
training_logs/20260829_025105_vllm_metrics_jtd-d5_1506710.csv	253 KB	6f0f5a88f8495e6b26c6987d5d6124f185a6d8f56d8ddb7ac53b5b0111841c73
training_logs/20260829_025105_vllm_metrics_jtd-d5_1506711.csv	313 KB	d243bafd9a809d6835d73e6d8c0435684300f7c7fc742d2db4d8bf7daf4dd020
training_logs/20260829_025105_vllm_metrics_jtd-d5_1506712.csv	222 KB	0e9c271c5c7c8dec26a2dad58b819aba46971278c59dccabb87639403e7fb652
training_logs/20260829_025105_vllm_metrics_jtd-d5_1520450.csv	394 KB	99db8edfe8af4085d6f2d1203e507654c19d7141bd2146794b3322bf0f9145d7
training_logs/20260829_025105_vllm_metrics_table.csv	4.38 MB	6959ec2854d7ded33e478bedd6b2a2175ba2c8b2ebf79b2ae32bd7d88bae7d58
training_logs/jtd-d5-export_1528411.out	48.3 KB	05718a11495256a40a99a60a64c7372839cc52fc23699c8b0bbd417d98af6f38
training_logs/jtd-d5_1468466.out	3.39 MB	5be8fc36535e6467b1477e93ad68978695397afbe3b9d67524b6881b6bdc2faf
training_logs/jtd-d5_1468467.out	2.13 MB	3850b0cd9b040579ffe501cc6ca865a0ee6bb20a820221a225e8c65b0e8bb9ad
training_logs/jtd-d5_1468468.out	3.95 MB	80406079f5dcda5ecf77a56158b61001e6164423cd8c8521b8ca2a86d2558590
training_logs/jtd-d5_1468469.out	1.59 MB	73125128fcdd7df7cfa8bd31c0ffb0b3b010a9490c315a8fd027a9290d5786ce
training_logs/jtd-d5_1468470.out	2.75 MB	afe336957ffca403bdcfef304642120ff6020738b77fa96fdce993a952eab2dc
training_logs/jtd-d5_1468471.out	3.21 MB	7ce76dd99c40fb87847e95d810de12b682bdb60014185602bb2c61eb35760a21
training_logs/jtd-d5_1477132.out	87.9 MB	355922874d99f760e7e2fccfeb26f029807aff4ba64ebcb29e428234d6997c44
training_logs/jtd-d5_1477135.out	4.03 MB	7bf29b9dff79c284e871f1270afe489b3a5bf218ae447fce1211289cf03e054a
training_logs/jtd-d5_1477136.out	3.59 MB	0319ab9e30eb75fde9598301c052aa25132185325d3bded698615a25ea1774c1
training_logs/jtd-d5_1487670.out	3.04 MB	7cad28dec97d2b70200bb3246a3148245c767695cc3c75dd2accaf79d5237b92
training_logs/jtd-d5_1487671.out	395 MB	4966fba2cacabad0065470998397326ef255459e1cac4e63ac91ae0f62ae890c
training_logs/jtd-d5_1506708.out	3.17 MB	b8a23c008271ff6effa86e2f0af360b5ee02a0c99fa6dfa48d0056a30b5231d6
training_logs/jtd-d5_1506709.out	1.90 MB	cd0a78230cc13392cee74c98ff82e88295d3eecf93211e5cbea0fcdfc5a610af
training_logs/jtd-d5_1506710.out	3.67 MB	553c4467be7bbb65ebbf559b942bfd60206db6d14b27a84e4542e2e231d8c1fb
training_logs/jtd-d5_1506711.out	4.59 MB	7a6c69a7a4cc270b55e0a21008dc2ccec197f69577a8f79d60e686f7a6aa5757
training_logs/jtd-d5_1506712.out	3.42 MB	8dbdd3ac536f4f52c3cdc83a35d71d2ba4cec68e834a7592d0f21f40e74219d1
training_logs/jtd-d5_1520450.out	5.89 MB	df97b4acfc5716c7dd55ec63ddf209529eb5c16b1b821e739946a477b4e74689

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
1310831b86 pinned now	2026-11-15 04:21 UTC	69 files · 61.6 GB

Use it

$ fw get laion/jtd-d5-69-30B
# manifest sha256 fd5099b593b6… · 61.6 GB · 69 files
$ fw verify ./jtd-d5-69-30B laion/jtd-d5-69-30B

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/jtd-d5-69-30B.json --dir ./jtd-d5-69-30B
$ python3 fw.py verify ./jtd-d5-69-30B ./laion__jtd-d5-69-30B.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/jtd-d5-69-30B --revision 1310831b86aeb20e8c6f46c80df6ebec5ed9d212 --local-dir ./jtd-d5-69-30B

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: bbb820fc02c4f60aa8e9160bfb5970be3f5078fdfebe18607790597506bf2fb0
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-d5-69-30BDate: 2026-11-15Commit: 1310831Signed: 2DC28CC7B26A283B ✓

Upstream: laion/jtd-d5-69-30B
Pinned commit: 1310831b86aeb20e8c6f46c80df6ebec5ed9d212
Manifest: jtd-d5-69-30B.json · .minisig
Manifest sha256: fd5099b593b67671d7d2853c6b7b3970ee5f556c598a22af7d84fead8eacf5ef
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 04:21 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/jtd-d5-69-30B.json
$ curl -O https://freeweights.allternit.com/manifests/laion/jtd-d5-69-30B.json.minisig
$ minisign -Vm jtd-d5-69-30B.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-d5-69-30B

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. jtd-d5-69-30B.json. Provenance. Takedown history: none.

Source

huggingface.co/laion/jtd-d5-69-30B

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