CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B

Date: 2026-11-15Commit: 1274e3cSigned: 2DC28CC7B26A283B ✓

Reinforcement learning model with 8.2B parameters. Safetensors weights, 16.4 GB in all. Published by laion under Apache-2.0.

8.2B params16.4GBa3-rl-DCAgent_exp_rpt_e2egit-v2-10-8Bsafetensorspermissive
FactsParams8.2BSize16.4 GBFormatssafetensorsTaskreinforcement learningLicenseApache-2.0From sourcepermissive
$ fw get laion/a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
# manifest sha256 26511246ee50… · 16.4 GB · 29 files
$ fw verify ./a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B laion/a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From sourceHosted (signed)laion/a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8BLast 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 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
16.4 GB
Weights
16.4 GB (safetensors)
Parameters
8.2B
Formats
safetensors
Task
reinforcement learning
License
Apache-2.0 (permissive)
Files
29, 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 04:19 UTCpassed

Model card

From the publisher at commit 1274e3c. Shown as plain text with links; images open at the publisher.

a3-rl-DCAgent_exp_rpt_e2egit-v2 (step 10, 8B)#

RL checkpoint from SkyRL (RLOO_n, FSDP2) trained on the exp_rpt_e2egit-v2 terminal-bench task set. This is the EMA-best checkpoint (global_step_10) selected from a legitimately-completed run (2 epochs x 7 steps/epoch = 14 training steps; lead SLURM job 515469, exit 0).

  • Base model: laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink (Qwen3-8B architecture)
  • Dataset: DCAgent/exp_rpt_e2egit-v2
  • Algorithm: RLOO_n, no KL loss, eps_clip 0.2/0.05, lr 8e-6, train_batch_size 64
  • Selection: EMA (alpha=1/3, 5-period) of reward/avg_raw_reward, step 10 EMA=0.6787

Training Traces#

Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset:

Files

29 files · 16.4 GBWeights 16.4 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 29 files with their sha256
FileSizesha256
.gitattributes1.84 KB32d978b9397c9b99d81c71c6022b6a77a428b142b841cee19883cc1510f5988d
README.md1.12 KB88fbe0f3cbad11aa834e7ad1e6fbc8bd99fb2630501f7dae2a301083dab07aec
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 GBebf62e12fd657e4f6470b2f60c1282859b0c6ac2516757c1800169e38e9e76bf
model-00002-of-00004.safetensors4.92 GB06728de00b39a7e42dc14d6ea24461ffdd6a651df74d6fe0bc4726c0b7ace8c0
model-00003-of-00004.safetensors4.98 GBec8625c23f7c09f0592635bcea5e3647aab876640af4a88d21d62c8db16d16d1
model-00004-of-00004.safetensors1.58 GB0379f09d8d2548b6b1243e2b9e50a4a8fc05fff563413ac51dad93420166b286
model.safetensors.index.json32.9 KBe7e4bdc58d3302c97357f27979b270987dd620cf0cd9b1c130e3a51c9d64df95
rl_config.yaml8.14 KB6cb9e855303de0dd4b1a9945e2b9d72bc99f5f0cda1f68daf65d2876ffaf6b31
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.43 KB3e27b302e9844c5b9648a8dbc1958fbbf3bda640e07302f53c17ac7a3192def5
trace_upload.log16.5 KB8c9343209622fa275ecdc9eaf00b33d7adab804027e7416ec3d5fad2bbefb306
training_logs/20260526_211859_metrics_job_515469.csv7.25 KBe92ef260c8a0f0ff6055d8b92d1a04332e290b271e937b5fb16d8af6f7e6f06d
training_logs/20260526_211859_metrics_report.md13.1 KBa659648d751d51f46077ca2a85c9df1e9c23e59184dcb4a942f4da37311c10dc
training_logs/20260526_211859_metrics_table.csv7.46 KB4a81e8af8f37dc275e112e8c37a8ee7ca5184c461623cd0233ecb9da5f6d1a1c
training_logs/20260526_211859_reward_vs_steps.png165 KBfc13210e812bfeedfdf29b78ee0ba606ecbcb084f98271d4d6f834c9eb7d2f84
training_logs/20260526_211859_trial_results.csv451 KBeba8aa92163a4adac0476dfbbff305c85cd7a5578dd6e82e184bd4ae40208ed6
training_logs/20260526_211859_turn_count_distribution.png109 KBde751b642e1e7cdc0695d7f6c69ca7e87689a9fccc9e09902b8ad11302a6704e
training_logs/20260526_211859_vllm_metrics_job_515469.csv260 KB5fe5a9e26d0c538c3e1e9b200675f4d723b414986e23ccdf2246b16980d982f0
training_logs/20260526_211859_vllm_metrics_table.csv299 KB0839875bf629b2cefe09f3f0af2ada8486700b72c209047efa4855105586c9e7
training_logs/a3-rl-DCAgent_exp_rpt_e2egit-v2_515469.out10.7 MB9a494b088b7b91503e42443d23ca977ba019429bdee4e7a229fdc563eb4398bc
upload.log27.9 KB0327b512f2906f44ed7cf281d3ca7b83e250871575837cc89e95e745e3f1f589
upload2.log29.2 KB12fe4d7b14722408bc4ab0e66781e6f58b95922d85e4b066eaa1c356346334b3
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
1274e3cd4a pinned now2026-11-15 04:19 UTC29 files · 16.4 GB

Use it

$ fw get laion/a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
# manifest sha256 26511246ee50… · 16.4 GB · 29 files
$ fw verify ./a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B laion/a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
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_exp_rpt_e2egit-v2-10-8B.json --dir ./a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B $ python3 fw.py verify ./a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B ./laion__a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B --revision 1274e3cd4a1cb6c767bcee59e3228bc21e00e7a1 --local-dir ./a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
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
88fbe0f3cbad11aa834e7ad1e6fbc8bd99fb2630501f7dae2a301083dab07aec
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_exp_rpt_e2egit-v2-10-8BDate: 2026-11-15Commit: 1274e3cSigned: 2DC28CC7B26A283B ✓
Upstream
laion/a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
Pinned commit
1274e3cd4a1cb6c767bcee59e3228bc21e00e7a1
Manifest
a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B.json · .minisig
Manifest sha256
26511246ee50f39a6de9b33f56a923b0bb3bdf4823e4bb21f058e7fe0035f13c
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/a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B.json $ curl -O https://freeweights.allternit.com/manifests/laion/a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B.json.minisig $ minisign -Vm a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B.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_exp_rpt_e2egit-v2-10-8B
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_exp_rpt_e2egit-v2-10-8B.json. Provenance. Takedown history: none.
Source
huggingface.co/laion/a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B

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_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
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h4_binary_easy-50-8B