CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / a3-rl-DCAgent_mix_h4_binary_easy-50-8B
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

a3-rl-DCAgent_mix_h4_binary_easy-50-8B

Date: 2026-11-15Commit: 1815975Signed: 2DC28CC7B26A283B ✓

Model with 8.2B parameters. Safetensors weights, 16.5 GB in all. Published by laion under Apache-2.0.

8.2B params16.5GBa3-rl-DCAgent_mix_h4_binary_easy-50-8Bsafetensorspermissive
FactsParams8.2BSize16.5 GBFormatssafetensorsTasknot taggedLicenseApache-2.0From sourcepermissive
$ fw get laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B
# manifest sha256 e11258c002ac… · 16.5 GB · 31 files
$ fw verify ./a3-rl-DCAgent_mix_h4_binary_easy-50-8B laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B
From sourceHosted (signed)laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8BLast check: 2026-11-15 04:25 UTC
Run at homeGet help

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

Fine-tune of GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink.

Runs withBentoMLCTranslate2ExLlamaV2LitServeLocalAItinygradTransformersTriton Inference ServerFine-tune withAccelerateDeepSpeedJAXKerasPyTorch Lightningsd-scriptsSimpleTunerConvert withCore ML ToolsExecuTorchOliveONNXOptimum QuantoOptimumsafetensorstorchaoScan withModelScanpicklescan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
16.5 GB
Weights
16.4 GB (safetensors)
Parameters
8.2B
Formats
safetensors
Task
not tagged
License
Apache-2.0 (permissive)
Files
31, each with a sha256
Publisher
laion
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink

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 04:25 UTCpassed

Model card

From the publisher at commit 1815975. Shown as plain text with links; images open at the publisher.

a3-rl-DCAgent_mix_h4_binary_easy-50-8B#

RL (SkyRL) checkpoint trained on the DCAgent/mix_h4_binary_easy task mix, starting from the a3 GLM-SFT base laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink.

  • Run: a3-rl-DCAgent_mix_h4_binary_easy (Jupiter chain 573271→573276)
  • Training: 2 epochs, completed at global_step 67 (max_steps=80 was a ceiling; 67 = epoch-data completion, a legit deployable endpoint — not collapse).
  • Checkpoint selected: global_step 50 by trailing-5 EMA (α=1/3) of reward/avg_raw_reward across the full chain.
    • EMA at step 50 = 0.4991 (highest of all aligned eligible checkpoints)
    • raw avg_raw_reward at step 50 = 0.529
    • pass@8 at step 50 = 0.672
  • hf_save_interval=5

Training Traces#

Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: open-athena/a3-rl-DCAgent_mix_h4_binary_easy

The dataset contains the last episode of each trial (per make_and_upload_trace_dataset --episodes last) — the same rollouts the policy was trained on after rollback / truncation.

Training Logs#

See training_logs/ for the parsed metrics (metrics.csv, report.md, reward_plot.png) and the raw chain .out logs (Jupiter has no W&B network access).

Files

31 files · 16.5 GBWeights 16.4 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 31 files with their sha256
FileSizesha256
.gitattributes1.84 KB4cb554a4c8419eb92855270fb233f90d31d09deb8cf888228bddc94a99a47f81
README.md1.56 KBd3592cda244737c4f179a800f26ade272429653f41edfe7b5645968f3b74d92f
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja4.17 KBa55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
config.json1.54 KBed36641e183b3d95dcefad8906aa22d183c445e4b582c8a0ca7d71a713c85f2d
generation_config.json188 B3b101cd89b140b757d0bca469e75570e75789a2423ada90a33ec17707dfacf08
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00004.safetensors4.90 GB581d9593c28b5a285ba1cf944754808d43abb9ad6d33660a6cd7f734fadc1c4e
model-00002-of-00004.safetensors4.92 GB327667fcf965db01787c891b209ec589a0111ff38897ee63db71b415c0131644
model-00003-of-00004.safetensors4.98 GBf2b25bf453fa6f8514f70f75fb05406552e48cf7c6b24d76640d3d3bb57fa601
model-00004-of-00004.safetensors1.58 GB6f1722e2bad49f139d0bb2ce578299f4bbd1beeee90d801c539d0c55fb094c5c
model.safetensors.index.json32.9 KBe7e4bdc58d3302c97357f27979b270987dd620cf0cd9b1c130e3a51c9d64df95
rl_config.json8.23 KBbc3900637cb7679e9418bc0bb67235c19b48f1b246d6a878466063e3a65ec2fe
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.43 KB3e27b302e9844c5b9648a8dbc1958fbbf3bda640e07302f53c17ac7a3192def5
training_logs/20260605_113340_metrics_job_573271.csv23.2 KB6a59e2956f8cb31ac70cb7aa75ea8d785b544696afca78c42ca367338fa319ce
training_logs/20260605_113340_metrics_job_573272.csv9.79 KBd83e0bbf113a3032f5cdc3bc19134df7b697b7b6bb1030fdf23056043000081b
training_logs/20260605_113340_metrics_report.md16.8 KB0bc5d2509b2b6024f73f825a3465d2efc35e0072821f5f30d375a76e93c8e5d4
training_logs/20260605_113340_metrics_table.csv31.9 KB9c53f117b8637c3f01cbc48d3c5223b2c95ab9394f2b7c2448aad220192cee5e
training_logs/20260605_113340_reward_vs_steps.png255 KB22dccdf65c9118b5d6484ba5d81d412415d00676070849bd37c6bb03a0f40d3c
training_logs/20260605_113340_vllm_metrics_job_573271.csv680 KB2807ce5860d1fe49a9a99270e03df713a24249095e099eb8b2648369927bc265
training_logs/20260605_113340_vllm_metrics_job_573272.csv399 KBc3a007529bfd85822b3056a915c36e87480bcfa07d181a7102a2ddc108ddbde4
training_logs/20260605_113340_vllm_metrics_table.csv1.23 MB57fc12910d31a5866852b31402616d90089df18d1c9749664c016c01f94c82f6
training_logs/a3-rl-DCAgent_mix_h4_binary_easy_573271.out80.8 MBd3175c8efe875e40d6104b05c199d0d411fe907ea88eb44d9f7b3889f57b35b8
training_logs/a3-rl-DCAgent_mix_h4_binary_easy_573272.out48.7 MBfc00cba381671f056b9266354870d103bba3cc40edb8cbe05c3751ebb8f32182
training_logs/a3-rl-DCAgent_mix_h4_binary_easy_573273.out246 KB45ed6b38411996a600f9fbf1ebb0f663ffa125cacec1b35a25e82f7622a65d6f
training_logs/a3-rl-DCAgent_mix_h4_binary_easy_573274.out223 KB40f40de8eb24fd77c42c8f30e74b751105813f16dcbfd031c26cab39d7e3c79f
training_logs/a3-rl-DCAgent_mix_h4_binary_easy_573275.out214 KB42686b4b70bd9db00f86515f536a16044d88e519417f8a2ddb62e123964e1a11
training_logs/a3-rl-DCAgent_mix_h4_binary_easy_573276.out211 KBbb9cee874f3b7baf9e326f3bc5968287dc57d2b2586c60aeb0dcb1822db6e14b
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
1815975b89 pinned now2026-11-15 04:25 UTC31 files · 16.5 GB

Use it

$ fw get laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B
# manifest sha256 e11258c002ac… · 16.5 GB · 31 files
$ fw verify ./a3-rl-DCAgent_mix_h4_binary_easy-50-8B laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B.json --dir ./a3-rl-DCAgent_mix_h4_binary_easy-50-8B $ python3 fw.py verify ./a3-rl-DCAgent_mix_h4_binary_easy-50-8B ./laion__a3-rl-DCAgent_mix_h4_binary_easy-50-8B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B --revision 1815975b89b0c675674d74c5febfa3f543c3d743 --local-dir ./a3-rl-DCAgent_mix_h4_binary_easy-50-8B
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
d3592cda244737c4f179a800f26ade272429653f41edfe7b5645968f3b74d92f
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: a3-rl-DCAgent_mix_h4_binary_easy-50-8BDate: 2026-11-15Commit: 1815975Signed: 2DC28CC7B26A283B ✓
Upstream
laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B
Pinned commit
1815975b89b0c675674d74c5febfa3f543c3d743
Manifest
a3-rl-DCAgent_mix_h4_binary_easy-50-8B.json · .minisig
Manifest sha256
e11258c002ac27fad12b9b0548298c2f93e2b8140996c4b4ad8b6ce256917d23
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:25 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B.json $ curl -O https://freeweights.allternit.com/manifests/laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B.json.minisig $ minisign -Vm a3-rl-DCAgent_mix_h4_binary_easy-50-8B.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

laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink · 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/a3-rl-DCAgent_mix_h4_binary_easy-50-8B
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. a3-rl-DCAgent_mix_h4_binary_easy-50-8B.json. Provenance. Takedown history: none.
Source
huggingface.co/laion/a3-rl-DCAgent_mix_h4_binary_easy-50-8B

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