CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / tasktrove-dq-stack-pytest-step25-30b-a3b
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

tasktrove-dq-stack-pytest-step25-30b-a3b

Date: 2026-11-15Commit: eaed133Signed: 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-stack-pytest-step25-30b-a3bsafetensorspermissive
FactsParams30.5BSize61.1 GBFormatssafetensorsTaskreinforcement learningLicenseApache-2.0From sourcepermissive
$ fw get laion/tasktrove-dq-stack-pytest-step25-30b-a3b
# manifest sha256 17ec9e22b160… · 61.1 GB · 33 files
$ fw verify ./tasktrove-dq-stack-pytest-step25-30b-a3b laion/tasktrove-dq-stack-pytest-step25-30b-a3b
From sourceHosted (signed)laion/tasktrove-dq-stack-pytest-step25-30b-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 eaed133. Shown as plain text with links; images open at the publisher.

tasktrove-dq-stack-pytest (step 25)#

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_25
  • Source run: rl-tasktrove-dq-sweep-30b-terminus2-qwen-20260725-155627-3eb19d
  • 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_stack_pytest_step25_30b_a3b_20260730_053956

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
.gitattributes1.71 KBc86e6663173a6d5d5f435dcdcea92cc16621801c87fdc4b629ca474a970f9c48
README.md2.53 KB02f71b754a704f06b281ab940df6c6dae788a9a931d1e0219418ce6e4150a341
chat_template.jinja6.21 KB5a38bfa05833266240066aedc497decc9b00cc0d3e3b8cceea98cf530196ab06
config.json1.02 KB3580b33db4d9c872e3d297884e3a07509a136f5399e878f53259cddb2c4f0eb6
generation_config.json216 Bf2a80a84a116bc7a296bbddfea4e48cf69a12f46e1925fe912b59c21a3651a90
model-00001-of-00016.safetensors4.00 GB9d8d11fd0222363af10ef20a3a26eb2a8621c997ade4f55140ac6aa6995dde6e
model-00002-of-00016.safetensors4.00 GB4d97cc0a02a08b07a8065a0b60030898a98a03b8163585a794fd6d3c0f321669
model-00003-of-00016.safetensors4.00 GB34e71bfaabb56cf205c724c346a5ee12e1c46c273637bcb4944f66a10fb10258
model-00004-of-00016.safetensors4.00 GB06827efa3b34d01be76643b7ae9a8463832028dabadbf4383def9357fccebcd0
model-00005-of-00016.safetensors4.00 GB7128951238c8ddc1954012ee90a70aa77a89fa998a5590ab1d9214c13ea93884
model-00006-of-00016.safetensors4.00 GB327a3281a15991de541cd4256c68f6963625080ac0470fe9164c088922c6cd87
model-00007-of-00016.safetensors4.00 GBc49ab0c8d86e8337c70da8ac502e159f6096c60bae684ef59efaa7de19a04534
model-00008-of-00016.safetensors4.00 GB1b5837dfe5f279d8abd4511355bc38b709405c7a365ca1dea9d487349292133b
model-00009-of-00016.safetensors4.00 GB374ed3eede0084928cc124d81bf53f56a569e640c452d00cf13b46c5d7ff7a2a
model-00010-of-00016.safetensors4.00 GB3b63a9c9a4c1b009b083fd31b35e77c75b685bfa70b1dff503a9dcf3b7692084
model-00011-of-00016.safetensors4.00 GB333731f220b714b6945b914a0e54ae586f835827972a09369939ec55bc461529
model-00012-of-00016.safetensors3.99 GBd28656174e95fc1b601295d0022af15938ec6cd585c4aae330aaf8bcca7c9f3d
model-00013-of-00016.safetensors4.00 GBd11a5f6395f557c07c9c15d6b8fa08eeb35d63f37c9645a4301c9d0386c5a3bf
model-00014-of-00016.safetensors4.00 GB72de4a8bc0196ebdb294b019d75cd37026efdaa0d0d6ac632ca06581178fb5b9
model-00015-of-00016.safetensors4.00 GBedd7b2398d3481a103b852b36eeb5899b9667cb103b6daa480aeef928bc2177b
model-00016-of-00016.safetensors1.09 GBe8d0c902bfd02ba7b716869a2862c579ef2f1ef8594bebeafdc2916d8d451fb0
model.safetensors.index.json1.78 MBa27467f2774e58ef6d5c342e6fed6851f238a187bcc8f3085e815d26f472b747
tokenizer.json11.4 MBbe75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
tokenizer_config.json695 Bf6f4c67578d26ccdf6535fa0bc88683b9a0e7acb6797aca1f4759ad3330c22e9
training_logs/20260730_095924_metrics_finelog.csv30.2 KB797a09492c21e46ea82a7dc45ceeb6708b8a8af5bbe63ab0381115f25f7084b8
training_logs/20260730_095924_metrics_table.csv30.7 KB23b7413a372e977be189706389ddc5e554392092eb4f916051551869734db646
training_logs/20260730_095924_vllm_metrics_finelog.csv587 KBfa336debb45be24569cd6c51024d3f4c14cea7ce7d27153f393d491fb3f8ad36
training_logs/20260730_095924_vllm_metrics_table.csv648 KBd069ef70b6b992ce945ca22bd52755f2a6613d7c34e12f0cc9b1b03bd5b425ac
training_logs/3eb19d_trainer.log21.5 MB786a9c32e37efc9fbed0c36a7bddc79c66f324ab1ec01af7c6ecea99e01c7004
training_logs/metrics.csv30.7 KB23b7413a372e977be189706389ddc5e554392092eb4f916051551869734db646
training_logs/report.md14.5 KBe53e5f0856e02f84e00aaca6e184adf98bc0bd4c381e90e309ad09844d32e91c
training_logs/reward_plot.png187 KB37ee4ab6de4e112db2e25a6f6e500bcb2d079936508f57229b7ad1b7654f0172
training_logs/vllm_metrics.csv648 KBd069ef70b6b992ce945ca22bd52755f2a6613d7c34e12f0cc9b1b03bd5b425ac
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
eaed133c9a pinned now2026-11-15 04:19 UTC33 files · 61.1 GB

Use it

$ fw get laion/tasktrove-dq-stack-pytest-step25-30b-a3b
# manifest sha256 17ec9e22b160… · 61.1 GB · 33 files
$ fw verify ./tasktrove-dq-stack-pytest-step25-30b-a3b laion/tasktrove-dq-stack-pytest-step25-30b-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-stack-pytest-step25-30b-a3b.json --dir ./tasktrove-dq-stack-pytest-step25-30b-a3b $ python3 fw.py verify ./tasktrove-dq-stack-pytest-step25-30b-a3b ./laion__tasktrove-dq-stack-pytest-step25-30b-a3b.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/tasktrove-dq-stack-pytest-step25-30b-a3b --revision eaed133c9a6c59da7dfed10c05449747e3de5d0d --local-dir ./tasktrove-dq-stack-pytest-step25-30b-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
02f71b754a704f06b281ab940df6c6dae788a9a931d1e0219418ce6e4150a341
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-stack-pytest-step25-30b-a3bDate: 2026-11-15Commit: eaed133Signed: 2DC28CC7B26A283B ✓
Upstream
laion/tasktrove-dq-stack-pytest-step25-30b-a3b
Pinned commit
eaed133c9a6c59da7dfed10c05449747e3de5d0d
Manifest
tasktrove-dq-stack-pytest-step25-30b-a3b.json · .minisig
Manifest sha256
17ec9e22b16060e6204d21606b02322a3020336c7e056286f104309c913b99b6
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-stack-pytest-step25-30b-a3b.json $ curl -O https://freeweights.allternit.com/manifests/laion/tasktrove-dq-stack-pytest-step25-30b-a3b.json.minisig $ minisign -Vm tasktrove-dq-stack-pytest-step25-30b-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-stack-pytest-step25-30b-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-stack-pytest-step25-30b-a3b.json. Provenance. Takedown history: none.
Source
huggingface.co/laion/tasktrove-dq-stack-pytest-step25-30b-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