CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / tt-x15-megatron-51-30B
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

tt-x15-megatron-51-30B

Date: 2026-11-15Commit: 09a6037Signed: 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-x15-megatron-51-30Bsafetensorspermissive
FactsParams30.5BSize61.1 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get laion/tt-x15-megatron-51-30B
# manifest sha256 ed96534c6aac… · 61.1 GB · 28 files
$ fw verify ./tt-x15-megatron-51-30B laion/tt-x15-megatron-51-30B
From sourceHosted (signed)laion/tt-x15-megatron-51-30BLast check: 2026-11-15 04:15 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

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

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 04:15 UTCpassed

Model card

From the publisher at commit 09a6037. Shown as plain text with links; images open at the publisher.

tt-x15-megatron — step 51 (X15 Megatron entropy rescue)#

GRPO checkpoint from the TaskTrove X15 experiment, trained on Iris / CoreWeave (cw-rno2a, 4x8 H100, Megatron runtime). Base model Qwen/Qwen3-Coder-30B-A3B-Instruct, trained on DCAgent/exp_rpt_multifile with SkyRL + Terminus-2. X15 tested whether lr 8e-6 + eps_clip_low 0.3 + temp 1.2 prevents the X14 Megatron late collapse; the answer is negative — the arm collapsed the same way.

Checkpoint selection#

global_step_51 — the owner-confirmed campaign selection (trailing-5 0.2199; step reward 0.2441; pass@8 0.4219; entropy 0.0194), the best pre-collapse saved checkpoint (near-tie with step 39 within smoothing flavor). Exported on-Iris from the sharded Megatron checkpoint bank (427.7 GB distcp, 30 objects) via the checkpoint-export job at the saved policy geometry (2x8 H100).

Run status — KILLED at 101/400 (COLLAPSED)#

Reward peaked ~0.2273 trailing-5, collapsed to ~0 at steps 84/86 and held ~8% of peak for 13+ steps while tokens shrank 9.2k -> 7.6k. Mechanism (first identified for this family): entropy collapse shortened per-turn output until agents exhausted max_turns: 30 unfinished (cap-hitters 23% -> 100%, tokens/turn 572 -> 281). Not infrastructure. Not an admissible horizon result; the arm is preserved as the collapse-family negative control. Confound: three hyperparameters moved at once.

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 v5dzu6fw.

Training Traces#

open-athena/tt-x15-megatron — 1/8 systematic subsample (every 8th trial of 53,411 = 6,677 selected, uniform coverage of steps 1-101). The full set (~256 GB) exceeded the sync host's free disk (47 Gi); 1/4 (~64 GB) also did not fit. Documented, owner-precedented deviation (same rule as tt-x10-fsdp2-fa2: smallest stride that fits).

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.md2.21 KBed700cb7aedce804b9f32edee07773098603c94a5de3923496da38ca47201202
chat_template.jinja6.21 KB5a38bfa05833266240066aedc497decc9b00cc0d3e3b8cceea98cf530196ab06
config.json1.02 KB3580b33db4d9c872e3d297884e3a07509a136f5399e878f53259cddb2c4f0eb6
generation_config.json216 Bf2a80a84a116bc7a296bbddfea4e48cf69a12f46e1925fe912b59c21a3651a90
model-00001-of-00016.safetensors4.00 GB438f60d73a34c87b4fe8f72f36a92c635644cc1cfecef3e0e2d465c85093c6f7
model-00002-of-00016.safetensors4.00 GB93645c8661039652e5ae403d369864b275a5be3c10383d80118a1dd62e012be6
model-00003-of-00016.safetensors4.00 GB7bf3be4ed160e796c51c57ebdb58ae7594ad84d2a449dbbd6a286bae100f689d
model-00004-of-00016.safetensors4.00 GB6e55866a03589b7d3b38734450f32668e9fedce856821d28cbfff66dfd9bd037
model-00005-of-00016.safetensors4.00 GBe428b148d88b34cf8e0f46507b0fafa3cb7996ff6d02facbbb0e5f8ea4ecb304
model-00006-of-00016.safetensors4.00 GBae0c2f550251e06ce35c7ddfa6339c815fa8411144caadaa104fb07b1e1b3cd3
model-00007-of-00016.safetensors4.00 GB05fa40c918022cc53255105f93234e762de265fadbd578bdae5433967c908c62
model-00008-of-00016.safetensors4.00 GBa3e9829cfd765c685e833d7db3d59b0efa03b644828295d0e0e446334d784838
model-00009-of-00016.safetensors4.00 GBbeb40847e7954de9e3e9807def82e877640d98b7fdd26fe40d1d6ea6526be156
model-00010-of-00016.safetensors4.00 GBc84cc661ab2611c5b1f468337e9ba51e4612f9e5bd350a8a87e0c594eab45d23
model-00011-of-00016.safetensors4.00 GBa0e25d848efd6b130c0e0eb46c1ffbb303d6656dfe0c8e65cbf760243b08e705
model-00012-of-00016.safetensors3.99 GB3487d6fa169aa6e72799600ed104b579a782e22fd1ed1fca49d2823f56563053
model-00013-of-00016.safetensors4.00 GB72800c28848bb6b4aff4499ba6bc6449231f67d0c6532ead463b9b67f7bd0890
model-00014-of-00016.safetensors4.00 GB9e075c9a53e3c880b16abcca0e7fdacc2f4afa7d80fd31fe815d906eced42804
model-00015-of-00016.safetensors4.00 GBd79876bddc4ba4be99d47b1b483be87bcf55c41ce7e8d102038058edacf43d11
model-00016-of-00016.safetensors1.09 GB68cc607c51fbc0baa846e43db5db1bf4be9f86d732c35f5b976c84496af686dc
model.safetensors.index.json1.78 MBcd5a55f53eba14836473ba18c4d169b8570744a40147ac72190fe8a1e66592a5
tokenizer.json11.4 MBbe75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
tokenizer_config.json695 Bf6f4c67578d26ccdf6535fa0bc88683b9a0e7acb6797aca1f4759ad3330c22e9
training_logs/metrics.csv11.0 KB19eee0bc60b7731e6abf08c9f225451229f57e4d71e2923e3972b44c600d0eef
training_logs/report.md2.52 KBca67f344ea3b77a3e89a397f1f4bdc37833e4b363288ebe56b893dab13b303cc
training_logs/reward_plot.png94.1 KB364eff0d1001963c8aa8e20e490ccbe62acd50e64001a58c8ad231fba65d8ffd
training_logs/rl_config.yaml12.6 KBf94cd2654435ff2f7c90de4e05f5076db3439c24ee77583204f3ef63db5cdbb4
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
09a6037c4f pinned now2026-11-15 04:15 UTC28 files · 61.1 GB

Use it

$ fw get laion/tt-x15-megatron-51-30B
# manifest sha256 ed96534c6aac… · 61.1 GB · 28 files
$ fw verify ./tt-x15-megatron-51-30B laion/tt-x15-megatron-51-30B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/tt-x15-megatron-51-30B.json --dir ./tt-x15-megatron-51-30B $ python3 fw.py verify ./tt-x15-megatron-51-30B ./laion__tt-x15-megatron-51-30B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/tt-x15-megatron-51-30B --revision 09a6037c4f44b3e3255597606cf9e85e847eebe5 --local-dir ./tt-x15-megatron-51-30B
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-x15-megatron-51-30B", revision="09a6037c4f44b3e3255597606cf9e85e847eebe5") model = AutoModelForCausalLM.from_pretrained("laion/tt-x15-megatron-51-30B", revision="09a6037c4f44b3e3255597606cf9e85e847eebe5", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve laion/tt-x15-megatron-51-30B --revision 09a6037c4f44b3e3255597606cf9e85e847eebe5
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
ed700cb7aedce804b9f32edee07773098603c94a5de3923496da38ca47201202
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-x15-megatron-51-30BDate: 2026-11-15Commit: 09a6037Signed: 2DC28CC7B26A283B ✓
Upstream
laion/tt-x15-megatron-51-30B
Pinned commit
09a6037c4f44b3e3255597606cf9e85e847eebe5
Manifest
tt-x15-megatron-51-30B.json · .minisig
Manifest sha256
ed96534c6aac0a3e3d3b6f926b686f1d763ef8cff681ceff2db94d116e583f02
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:15 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/tt-x15-megatron-51-30B.json $ curl -O https://freeweights.allternit.com/manifests/laion/tt-x15-megatron-51-30B.json.minisig $ minisign -Vm tt-x15-megatron-51-30B.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-x15-megatron-51-30B
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. tt-x15-megatron-51-30B.json. Provenance. Takedown history: none.
Source
huggingface.co/laion/tt-x15-megatron-51-30B

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