CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / tasktrove-dq-pymethods2test-step75-30b-a3b
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

tasktrove-dq-pymethods2test-step75-30b-a3b

Date: 2026-11-15Commit: 8f8a8a3Signed: 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-pymethods2test-step75-30b-a3bsafetensorspermissive
FactsParams30.5BSize61.1 GBFormatssafetensorsTaskreinforcement learningLicenseApache-2.0From sourcepermissive
$ fw get laion/tasktrove-dq-pymethods2test-step75-30b-a3b
# manifest sha256 f9fefd97e6ee… · 61.1 GB · 28 files
$ fw verify ./tasktrove-dq-pymethods2test-step75-30b-a3b laion/tasktrove-dq-pymethods2test-step75-30b-a3b
From sourceHosted (signed)laion/tasktrove-dq-pymethods2test-step75-30b-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
28, 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 8f8a8a3. Shown as plain text with links; images open at the publisher.

tasktrove-dq-pymethods2test (step 75)#

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_75
  • Source run: rl-tasktrove-dq-sweep-30b-terminus2-qwen-20260725-231748-4fe0b4
  • 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_pymethods2test_step75_30b_a3b_20260730_054052

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 retained trainer log for this run, and it is partial. The Iris log server retains only the run's first attempt (2026-07-25 23:20 to 07-26 09:48 UTC), during which the run resumed at global_step_29 and completed one optimizer step before stalling in generation. The job was preempted four times; the attempts that trained steps 30 through 75 left no retrievable log, on the log server or in the object store's archived Ray sessions.

Read training_logs/COVERAGE.md before using anything in that directory. metrics.csv has a single row and is not a learning curve. No metric trajectory exists for the span that produced these weights.

Files

28 files · 61.1 GBWeights 61.1 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 28 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md2.96 KB98015146b9a6b6afb2f6152dcef50050aa02b310176d71768d5cae25bbfdd558
chat_template.jinja6.21 KB5a38bfa05833266240066aedc497decc9b00cc0d3e3b8cceea98cf530196ab06
config.json1.02 KB3580b33db4d9c872e3d297884e3a07509a136f5399e878f53259cddb2c4f0eb6
generation_config.json216 Bf2a80a84a116bc7a296bbddfea4e48cf69a12f46e1925fe912b59c21a3651a90
model-00001-of-00016.safetensors4.00 GB8b5f31211ce683340c64d303fa71b8be30d30eaa514c99479ae78bbb63daefd7
model-00002-of-00016.safetensors4.00 GBf44c952c6e9ae1590fb1ba7f5e30ed68ed79851c6afc80dfd14a2bd641c3ed45
model-00003-of-00016.safetensors4.00 GBb75c8d1811d7e1eca6bfd6a71f36a450001fc25578c783aaf3584572b8cec5ef
model-00004-of-00016.safetensors4.00 GBd4c46d9ccc321f4a2d33271ef1457b8ccea6c77248eb5907be4cac98a1686da5
model-00005-of-00016.safetensors4.00 GB7de40143cd83569f4e637b1b4452cf33057a24cf4b4104c751aa17369f92661b
model-00006-of-00016.safetensors4.00 GBfaab97c33d898150b474b9cfcb032d2740e87a91887b4668140a7f30c9fa4612
model-00007-of-00016.safetensors4.00 GBb6ce1e899147ef48c26d4e063351036a7ab5dc37808fe5fd16e53520569d1a3e
model-00008-of-00016.safetensors4.00 GB6a1b19719e99b854ab8b9b453e3cd68da4bcd82d34029d84106ea7b9173a5fa8
model-00009-of-00016.safetensors4.00 GB3d810d0378d0825e6183f8b3b6b4f8164c0b417ec5fe7717b7b5f5266362cded
model-00010-of-00016.safetensors4.00 GBee150529b6c6f6ddb02974c8088b9fd686ac9a5aa739c4a31a2ac2198722b9b1
model-00011-of-00016.safetensors4.00 GBe50ff1b26465c0d60b363e0fe3c03369be3e4038e289573f6304b1ac41a41d2e
model-00012-of-00016.safetensors3.99 GB1b7d83a842c62d990afba590c16085d1a60f2ba59d3c55998ccf939e2147f044
model-00013-of-00016.safetensors4.00 GB6051d8a73f6c2ecf06f34fa2f3f07cc776564c6c856e476e6359dede79b110b5
model-00014-of-00016.safetensors4.00 GBdb038f1e4755bc482745fcc3e72bde50413438a0b6e0bf6e64bed60e10ea6be0
model-00015-of-00016.safetensors4.00 GB9344ab0245e584630dccd03b37c11068d859a92bdfdd77c9915504853b51dd8c
model-00016-of-00016.safetensors1.09 GBb072196323e6c2c49f77ae580b3f24ba4b8e541ac2bb3001a05d183cc077cc7f
model.safetensors.index.json1.78 MB3c3006ace6141b2584945343312649e7849e745ff2da0bf508856a14e60f878f
tokenizer.json11.4 MBbe75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
tokenizer_config.json695 Bf6f4c67578d26ccdf6535fa0bc88683b9a0e7acb6797aca1f4759ad3330c22e9
training_logs/4fe0b4_trainer_attempt1.log2.56 MB07145036657f94652031aa45d1f6b831df97f40c30fca1f0e8e1cad9ec4198e2
training_logs/COVERAGE.md1.92 KB5851b054f1b854e035befb72b89ada36329f7574ec2f252614e61ee0191293f1
training_logs/metrics.csv2.19 KB3d307d7a57c7cd7b0cca9fbc9f40576c5742c7f04dac3811e0d96d43b0ccad3a
training_logs/vllm_metrics.csv12.2 KBc7f88189162087128bf5ce46ce337af825b0aad519dc38eb531386ca68fdc6b7
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
8f8a8a3295 pinned now2026-11-15 04:19 UTC28 files · 61.1 GB

Use it

$ fw get laion/tasktrove-dq-pymethods2test-step75-30b-a3b
# manifest sha256 f9fefd97e6ee… · 61.1 GB · 28 files
$ fw verify ./tasktrove-dq-pymethods2test-step75-30b-a3b laion/tasktrove-dq-pymethods2test-step75-30b-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-pymethods2test-step75-30b-a3b.json --dir ./tasktrove-dq-pymethods2test-step75-30b-a3b $ python3 fw.py verify ./tasktrove-dq-pymethods2test-step75-30b-a3b ./laion__tasktrove-dq-pymethods2test-step75-30b-a3b.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/tasktrove-dq-pymethods2test-step75-30b-a3b --revision 8f8a8a3295d82a381b19667623bf4c9c729003ce --local-dir ./tasktrove-dq-pymethods2test-step75-30b-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
98015146b9a6b6afb2f6152dcef50050aa02b310176d71768d5cae25bbfdd558
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-pymethods2test-step75-30b-a3bDate: 2026-11-15Commit: 8f8a8a3Signed: 2DC28CC7B26A283B ✓
Upstream
laion/tasktrove-dq-pymethods2test-step75-30b-a3b
Pinned commit
8f8a8a3295d82a381b19667623bf4c9c729003ce
Manifest
tasktrove-dq-pymethods2test-step75-30b-a3b.json · .minisig
Manifest sha256
f9fefd97e6eee7708e7643a73e0476475c5d109a0c1c9d3325222d79aee64daf
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-pymethods2test-step75-30b-a3b.json $ curl -O https://freeweights.allternit.com/manifests/laion/tasktrove-dq-pymethods2test-step75-30b-a3b.json.minisig $ minisign -Vm tasktrove-dq-pymethods2test-step75-30b-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-pymethods2test-step75-30b-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-pymethods2test-step75-30b-a3b.json. Provenance. Takedown history: none.
Source
huggingface.co/laion/tasktrove-dq-pymethods2test-step75-30b-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