alt.freeweights.text / tt-x16-entropy0p003-42-30B
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

tt-x16-entropy0p003-42-30B

Date: 2026-11-15Commit: 7858b3cSigned: 2DC28CC7B26A283B ✓

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

30.5B params61.1GBtt-x16-entropy0p003-42-30Bsafetensorspermissive
FactsParams30.5BSize61.1 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get laion/tt-x16-entropy0p003-42-30B
# manifest sha256 6f3a829e3fe0… · 61.1 GB · 28 files
$ fw verify ./tt-x16-entropy0p003-42-30B laion/tt-x16-entropy0p003-42-30B
From sourceHosted (signed)laion/tt-x16-entropy0p003-42-30BLast check: 2026-11-15 04:16 UTC

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

Overview

Size
61.1 GB
Weights
61.1 GB (safetensors)
Parameters
30.5B
Formats
safetensors
Task
text generation
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 04:16 UTCpassed

Model card

From the publisher at commit 7858b3c. Shown as plain text with links; images open at the publisher.

tt-x16-entropy0p003 — step 42 (X16 entropy bonus 0.003)#

GRPO checkpoint from the TaskTrove X16 exploration sweep (entropy-bonus lever on the X14 Megatron recipe), trained on Iris / CoreWeave (cw-rno2a, 4x8 H100, Megatron runtime 6a25520f). Base model Qwen/Qwen3-Coder-30B-A3B-Instruct, trained on DCAgent/exp_rpt_multifile with SkyRL + Terminus-2. This arm added entropy_loss_coef 0.003 to test whether an entropy bonus holds exploration on the collapsing Megatron schedule (relaunch r2 on the #404 entropy-loss fix).

Checkpoint selection#

global_step_42 — highest trailing-5 reward EMA (alpha=1/3) over the stitched two-generation W&B curve (steps 1-92, no gaps): EMA 0.2268; step reward 0.2520; pass@8 0.375; entropy 0.0237. This matches the owner's "best single reads 42-43" note. All 31 banked checkpoints (steps 3-90) were retained, so the true EMA-best was available (unlike the Jupiter KL arms). Exported on-Iris via the checkpoint-export job at the saved policy geometry (2x8 H100, Megatron profile).

Run status — killed at 92/400 after COLLAPSE (POLICY stop condition met)#

The arm cleared its early gate and improved to ~0.25 reward, then collapsed in epoch 2 from ~step 77: reward 0.02-0.05 for steps 77-88, entropy at 0.06x step 1, grad norm decaying — the POLICY stop condition. Verdict: an entropy bonus of 0.003 does NOT hold exploration on this schedule. Not an admissible horizon result; preserved as the entropy-lever negative control. Stopped by owner decision 2026-08-18 (job killed at logged step 92; banked 90).

See training_logs/ for metrics.csv (stitched per-step curve + trailing-5 EMA), report.md, reward_plot.png, and the launch rl_config.yaml. W&B: dogml/OpenThoughts-Agent runs zgyhu8oc + vne6jh9g (r2 generations).

Training Traces#

open-athena/tt-x16-entropy0p003 — 1/16 systematic subsample (every 16th trial of 51,701, uniform coverage of steps 1-92). The full set (~248 GB) and 1/8 (~31 GB) exceeded the sync host's free disk (28 Gi); smallest-stride-that-fits per the owner-precedented deviation rule (x10/x15 used 1/8 under more headroom).

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.md2.40 KB02eebd61f2fde60e4a1a7ec82c04359fc3cf86c7f28a36abef7043f72171ae0c
chat_template.jinja6.21 KB5a38bfa05833266240066aedc497decc9b00cc0d3e3b8cceea98cf530196ab06
config.json1.02 KB3580b33db4d9c872e3d297884e3a07509a136f5399e878f53259cddb2c4f0eb6
generation_config.json216 Bf2a80a84a116bc7a296bbddfea4e48cf69a12f46e1925fe912b59c21a3651a90
model-00001-of-00016.safetensors4.00 GB01e38bd7d9c98ef03ddf9f3b68987eafedd88280858417d8194506097a2d3f14
model-00002-of-00016.safetensors4.00 GB45d6b0ed2aa2ddfce3bc0f6f9b9f5e7fd8f0d8c63a413a55452a8c7a807b2d5b
model-00003-of-00016.safetensors4.00 GB94ccb3f4d4ed426f365390d9ffb6f8666ca7994d265736427ce1c5d16121a581
model-00004-of-00016.safetensors4.00 GBd924fd0bcb528efa34e6ac42419a69ae2f6404e1a44a26645343daea74c1c0aa
model-00005-of-00016.safetensors4.00 GBc9c5428c7f3172590cb3ec2f6e13bbce7d56d93b80a37e571eb0f4873cef91de
model-00006-of-00016.safetensors4.00 GBf1aa73571b05409bd9be3be17b902b4d69e36b725e84f8795c867623c4658fdd
model-00007-of-00016.safetensors4.00 GBdadcc07881f31e52d43b8478d12a01bc858e08f01cd164bed16bf86607f6092a
model-00008-of-00016.safetensors4.00 GB1d250e72f18c0deb65afd53b6cc63d36e9293a6c11240da79b183939b40aea14
model-00009-of-00016.safetensors4.00 GB0d718e2a347847d5b56b3cb62dc57533f29bb269fac0a8f0c654b99ee25d4bfe
model-00010-of-00016.safetensors4.00 GB109e901d0c1d1f9f402c8b4e980e86a54e16310e9f9fdf2658ca66594ac21829
model-00011-of-00016.safetensors4.00 GBc86f0350b340aff5747d6ba8f4a5b383d533863ba9aadbccef0543f1ef80c489
model-00012-of-00016.safetensors3.99 GBec3d3c57a10333864bd512357154d49a256d505fdec601084667e1d30ff00d91
model-00013-of-00016.safetensors4.00 GBa90718ece0cc8b1f01c83660a4912ecac261fcd1b7081444e797839cff53ab49
model-00014-of-00016.safetensors4.00 GB837423d966c1670ec7ac1ad480bdce29df624e69d4620baaa47f12dce2585001
model-00015-of-00016.safetensors4.00 GBe08e094ec943aebeef4024da57eecabaefd5ce2e041baa6925d1c5b62198d279
model-00016-of-00016.safetensors1.09 GBb5b9b3d328d287da3f10ec45c7aecfcad443cfefeaa5a719f2ed40858e217caf
model.safetensors.index.json1.78 MBcc0e94ac29ed2239538b78a98ed7a9ebf6894f51beeaa70a586d5023d979804e
tokenizer.json11.4 MBbe75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
tokenizer_config.json695 Bf6f4c67578d26ccdf6535fa0bc88683b9a0e7acb6797aca1f4759ad3330c22e9
training_logs/metrics.csv4.78 KBa3e1e22a2223a317d04a2d0b2d1c6e63de00f5807f64b316a164b656e2237219
training_logs/report.md2.14 KB26d71069047633db3e816fe047167cd802b5b702c4a81457040f20617ff5bcc8
training_logs/reward_plot.png99.5 KBe481597825bcc8d0e023e1af2406de4a66726ce1a10069508e17bbf24fc669e3
training_logs/rl_config.yaml8.55 KB2a0679182a3ae3d3bf452d414f75fc29d7f997f9451f176473fc453f21d6a36b
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
7858b3cf85 pinned now2026-11-15 04:16 UTC28 files · 61.1 GB

Use it

$ fw get laion/tt-x16-entropy0p003-42-30B
# manifest sha256 6f3a829e3fe0… · 61.1 GB · 28 files
$ fw verify ./tt-x16-entropy0p003-42-30B laion/tt-x16-entropy0p003-42-30B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/tt-x16-entropy0p003-42-30B.json --dir ./tt-x16-entropy0p003-42-30B $ python3 fw.py verify ./tt-x16-entropy0p003-42-30B ./laion__tt-x16-entropy0p003-42-30B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/tt-x16-entropy0p003-42-30B --revision 7858b3cf85b3298d6ddea84fce0d7baa7d569c9d --local-dir ./tt-x16-entropy0p003-42-30B
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("laion/tt-x16-entropy0p003-42-30B", revision="7858b3cf85b3298d6ddea84fce0d7baa7d569c9d") model = AutoModelForCausalLM.from_pretrained("laion/tt-x16-entropy0p003-42-30B", revision="7858b3cf85b3298d6ddea84fce0d7baa7d569c9d", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve laion/tt-x16-entropy0p003-42-30B --revision 7858b3cf85b3298d6ddea84fce0d7baa7d569c9d

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
02eebd61f2fde60e4a1a7ec82c04359fc3cf86c7f28a36abef7043f72171ae0c
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: tt-x16-entropy0p003-42-30BDate: 2026-11-15Commit: 7858b3cSigned: 2DC28CC7B26A283B ✓
Upstream
laion/tt-x16-entropy0p003-42-30B
Pinned commit
7858b3cf85b3298d6ddea84fce0d7baa7d569c9d
Manifest
tt-x16-entropy0p003-42-30B.json · .minisig
Manifest sha256
6f3a829e3fe0e32262e9f5f1ae8334bfbdf8460172bcd55514d3e7de7bbf5e3b
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:16 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/tt-x16-entropy0p003-42-30B.json $ curl -O https://freeweights.allternit.com/manifests/laion/tt-x16-entropy0p003-42-30B.json.minisig $ minisign -Vm tt-x16-entropy0p003-42-30B.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/tt-x16-entropy0p003-42-30B
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. tt-x16-entropy0p003-42-30B.json. Provenance. Takedown history: none.
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