CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / tasktrove-dq-unitsyn-python-step20-30b-a3b
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

tasktrove-dq-unitsyn-python-step20-30b-a3b

Date: 2026-11-15Commit: d7a75b5Signed: 2DC28CC7B26A283B ✓

Reinforcement learning model with 30.5B parameters. Safetensors weights, 61.1 GB in all. Published by laion under Apache-2.0.

30.5B params61.1GBtasktrove-dq-unitsyn-python-step20-30b-a3bsafetensorspermissive
FactsParams30.5BSize61.1 GBFormatssafetensorsTaskreinforcement learningLicenseApache-2.0From sourcepermissive
$ fw get laion/tasktrove-dq-unitsyn-python-step20-30b-a3b
# manifest sha256 2e2081de06fd… · 61.1 GB · 33 files
$ fw verify ./tasktrove-dq-unitsyn-python-step20-30b-a3b laion/tasktrove-dq-unitsyn-python-step20-30b-a3b
From sourceHosted (signed)laion/tasktrove-dq-unitsyn-python-step20-30b-a3bLast check: 2026-11-15 04:19 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
61.1 GB
Weights
61.1 GB (safetensors)
Parameters
30.5B
Formats
safetensors
Task
reinforcement learning
License
Apache-2.0 (permissive)
Files
33, 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 04:19 UTCpassed

Model card

From the publisher at commit d7a75b5. Shown as plain text with links; images open at the publisher.

tasktrove-dq-unitsyn-python (step 20)#

RL checkpoint from the TaskTrove data-quality sweep, trained with SkyRL from Qwen/Qwen3-Coder-30B-A3B-Instruct using RLOO over agentic software-engineering tasks executed by OpenCode in sandboxed environments.

  • Base model: Qwen/Qwen3-Coder-30B-A3B-Instruct (Qwen3 MoE, 48 layers)
  • Checkpoint: global_step_20
  • Source run: rl-tasktrove-dq-sweep-30b-terminus2-qwen-20260725-163115-1ae770
  • Weights: 16 safetensors shards, 61.1 GB

What this is for#

The sweep measures dataset quality, not model quality. Each arm trains the same base model on a different TaskTrove source so the sources can be compared. These checkpoints are research artifacts for that comparison. None has been evaluated as a general-purpose model, and no benchmark numbers are claimed here.

Training configuration#

RLOO (advantage_estimator: rloo_n) with megatron backend, tensor-parallel 4, pipeline-parallel 2, expert-parallel 4, across 32 H100s. The objective is deliberately unregularized: use_kl_loss: false, use_entropy_loss: false, and policy_update_steps: 1, which leaves the PPO clip ratio inert at 0.0. That choice makes entropy dynamics the primary failure mode across the sweep, and it is why several arms ended early.

Provenance#

Exported from a torch.distributed.checkpoint megatron checkpoint by re-running the trainer's own export path (bridge.save_hf_weights) at the checkpoint's own step, so no offline conversion was involved. Shard count, index total_size and weight_map completeness were verified against the object store before upload.

Training Traces#

Training-time OpenCode/Harbor rollouts for this run are published as a companion dataset: laion/terminal_bench_2_tasktrove_dq_unitsyn_python_step20_30b_a3b_20260730_014827

The dataset contains the last episode of each trial (per make_and_upload_trace_dataset --episodes last) -- the rollouts the policy was trained on.

Training Logs#

training_logs/ holds the parsed metric surface for this run -- per-step training metrics, vLLM engine metrics, a summary report, and the reward-vs-steps plot -- alongside the raw trainer log. Capability tokens have been redacted from the logs.

Files

33 files · 61.1 GBWeights 61.1 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 33 files with their sha256
FileSizesha256
.gitattributes1.64 KBde80bb6edf1a833ee29462d6cd72903a73880454d897febf28a9959c3c4c42a8
README.md2.53 KB376f1f36931720b864394beb0be88eeefe00d35ad0ba9fa9c13f3e3145ad6460
chat_template.jinja6.21 KB5a38bfa05833266240066aedc497decc9b00cc0d3e3b8cceea98cf530196ab06
config.json1.02 KB3580b33db4d9c872e3d297884e3a07509a136f5399e878f53259cddb2c4f0eb6
generation_config.json216 Bf2a80a84a116bc7a296bbddfea4e48cf69a12f46e1925fe912b59c21a3651a90
model-00001-of-00016.safetensors4.00 GBe2af3530fb56d6f10de19a9d6811e35542d902c7a17aa8fc18dc36dd5fb2c159
model-00002-of-00016.safetensors4.00 GBa8a7aeb394b49d17628bb78aff0ea2b60db08f928dbb831020e6fa5122d3600d
model-00003-of-00016.safetensors4.00 GBd401c43d209b7fc3d61aa8c73f39d9fab5fc5db05137dce1d213005018833ea6
model-00004-of-00016.safetensors4.00 GB9f04e63ecc2c571fdab50955c1192ac3c4194d78d1fd79cacff78335e1285ccc
model-00005-of-00016.safetensors4.00 GB3c8f69c2dd903456d2da1d17611a4a83113439503fcf5d6394ebcceac53f6d9f
model-00006-of-00016.safetensors4.00 GB85c5d3eb0fe7e4a62506c2edd8f68f5eb98f347b96bd8648787c9d5993a3733a
model-00007-of-00016.safetensors4.00 GB1cd55a89f900e4edad9082fc61c798bcedab0d715776cdf877a6a51b894d07d2
model-00008-of-00016.safetensors4.00 GBea1fee4d476a54f414088d27246965612df8bf623bd94890dcab77f06543ffb0
model-00009-of-00016.safetensors4.00 GB1561327864bc215778d66c8b43b873610e911f62c99f75970401478d8f410b27
model-00010-of-00016.safetensors4.00 GB9594f7af988ba1875a5aa543d1cd01c21c40dc0cbd07bca5490dee9f1035a3bc
model-00011-of-00016.safetensors4.00 GB1c921188b5be212aa88ec418f14feaca731da64a2d198fe1e28297e7724b86a3
model-00012-of-00016.safetensors3.99 GB8450f23150216b6bcdccaf28bb854c3822f49a640d47666c8ff10a978f8f7fc5
model-00013-of-00016.safetensors4.00 GB48d9fe344c17fd0fa93e30c7a4db762556c685ffcf757a17da23a93e18f1cac2
model-00014-of-00016.safetensors4.00 GB49b929e277a5df692f4c32b0a8f6fe48899b9bd7a5931b87e309b3b863a8df44
model-00015-of-00016.safetensors4.00 GB15493b9381167ee4756f5f547c271010f34399ca6e4f988016c8425e6af85291
model-00016-of-00016.safetensors1.09 GBc25379e7fa3cd92aac5653375ac8985cd91b92416f80038942d67b5a0da303e9
model.safetensors.index.json1.78 MB053afcb6a564d45a3504152429c4d2ebff469d76fd922cfbd6ad65c42a47edfd
tokenizer.json11.4 MBbe75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
tokenizer_config.json695 Bf6f4c67578d26ccdf6535fa0bc88683b9a0e7acb6797aca1f4759ad3330c22e9
training_logs/1ae770_trainer.log4.37 MB31019bd3ac0685252784e4281203edbb8b7a6bee14f1ab833edb317689012f35
training_logs/20260730_100022_metrics_finelog.csv9.03 KBe2bccfd8467c077f3e76539c4aa170abb0c956a5c50bd7132ecb079906725381
training_logs/20260730_100022_metrics_table.csv9.18 KBaf0cb6cf4b5d3928c7363d9bbb02ae7de4906c9f665983df005bf8d2305028b2
training_logs/20260730_100022_vllm_metrics_finelog.csv121 KBb410acb1fc15f68a990b93bdd1e45bcd4c28ab584a0fb72f4bdc16a8bd629527
training_logs/20260730_100022_vllm_metrics_table.csv133 KB530b3217ad585d337e21eeed2ca179cc1cdd1fb195ddc4cabafd52432f4219b2
training_logs/metrics.csv9.18 KBaf0cb6cf4b5d3928c7363d9bbb02ae7de4906c9f665983df005bf8d2305028b2
training_logs/report.md10.3 KBb1767f0c3e4f348bf46d20bbe2d36473a40058d2191aa4626dc1d565f4125a5a
training_logs/reward_plot.png158 KB98d88bd579f64703945e2999e3db73a2b679b31c13ef9764bec88e2cb23fa492
training_logs/vllm_metrics.csv133 KB530b3217ad585d337e21eeed2ca179cc1cdd1fb195ddc4cabafd52432f4219b2
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
d7a75b503d pinned now2026-11-15 04:19 UTC33 files · 61.1 GB

Use it

$ fw get laion/tasktrove-dq-unitsyn-python-step20-30b-a3b
# manifest sha256 2e2081de06fd… · 61.1 GB · 33 files
$ fw verify ./tasktrove-dq-unitsyn-python-step20-30b-a3b laion/tasktrove-dq-unitsyn-python-step20-30b-a3b
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/tasktrove-dq-unitsyn-python-step20-30b-a3b.json --dir ./tasktrove-dq-unitsyn-python-step20-30b-a3b $ python3 fw.py verify ./tasktrove-dq-unitsyn-python-step20-30b-a3b ./laion__tasktrove-dq-unitsyn-python-step20-30b-a3b.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/tasktrove-dq-unitsyn-python-step20-30b-a3b --revision d7a75b503de1b1370ab4f9d59014ecf0bfe6a854 --local-dir ./tasktrove-dq-unitsyn-python-step20-30b-a3b
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
376f1f36931720b864394beb0be88eeefe00d35ad0ba9fa9c13f3e3145ad6460
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: tasktrove-dq-unitsyn-python-step20-30b-a3bDate: 2026-11-15Commit: d7a75b5Signed: 2DC28CC7B26A283B ✓
Upstream
laion/tasktrove-dq-unitsyn-python-step20-30b-a3b
Pinned commit
d7a75b503de1b1370ab4f9d59014ecf0bfe6a854
Manifest
tasktrove-dq-unitsyn-python-step20-30b-a3b.json · .minisig
Manifest sha256
2e2081de06fdde68509417b0782f1067de2b5183c26482d0f3869c57abdc4ef6
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:19 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/tasktrove-dq-unitsyn-python-step20-30b-a3b.json $ curl -O https://freeweights.allternit.com/manifests/laion/tasktrove-dq-unitsyn-python-step20-30b-a3b.json.minisig $ minisign -Vm tasktrove-dq-unitsyn-python-step20-30b-a3b.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/tasktrove-dq-unitsyn-python-step20-30b-a3b
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. tasktrove-dq-unitsyn-python-step20-30b-a3b.json. Provenance. Takedown history: none.
Source
huggingface.co/laion/tasktrove-dq-unitsyn-python-step20-30b-a3b

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