alt.freeweights.text / seqnorm-tis-shaped-40-8B

From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

seqnorm-tis-shaped-40-8B

Date: 2026-11-15Commit: 64661faSigned: 2DC28CC7B26A283B ✓

Model with 8.2B parameters. Safetensors weights, 16.6 GB in all. Published by laion under Apache-2.0.

8.2B params16.6GBseqnorm-tis-shaped-40-8Bsafetensorspermissive

FactsParams8.2BSize16.6 GBFormatssafetensorsTasknot taggedLicenseApache-2.0From sourcepermissive

$ fw get laion/seqnorm-tis-shaped-40-8B
# manifest sha256 bc3b64d18fb8… · 16.6 GB · 48 files
$ fw verify ./seqnorm-tis-shaped-40-8B laion/seqnorm-tis-shaped-40-8B

From sourceHosted (signed)laion/seqnorm-tis-shaped-40-8BLast check: 2026-11-15 04:24 UTC

Run at home Get 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.

Works with

Run8 Fine-tune7 Convert8 Scan2

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

Transformers LocalAI tinygrad Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Overview

Size: 16.6 GB
Weights: 16.4 GB (safetensors)
Parameters: 8.2B
Formats: safetensors
Task: not tagged
License: Apache-2.0 (permissive)
Files: 48, 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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 04:24 UTC	passed

Model card

From the publisher at commit 64661fa. Shown as plain text with links; images open at the publisher.

seqnorm-tis-shaped (step 40)#

RL checkpoint from the shaped-reward ablation (seqnorm + TIS objective) on the pymethods2test-large agentic coding dataset. This is the shaped-reward successor to the a3 RLOO-n series.

Base model (RL-from): laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink (Qwen3-8B SFT)
Training dataset: DCAgent/exp_rpt_pymethods2test-large
Objective: sequence-normalized RLOO-n + Truncated Importance Sampling (TIS), shaped reward (% tests passing)
Checkpoint: global_step 40 of 80 (selected by trailing 5-step EMA of reward/avg_raw_reward; EMA=0.4749)
Trainer: SkyRL (fully-async), Jupiter (56 GPU)

See rl_config.yaml for the full launch configuration and training_logs/ for parsed metrics, reward plots, and the raw SLURM logs.

Training Traces#

Training-time Daytona/Harbor rollouts for this run are uploaded as a companion dataset: open-athena/seqnorm-tis-shaped

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.

Files

48 files · 16.6 GBWeights 16.4 GB (safetensors). Sizes and sha256 from the signed manifest.

Show all 48 files with their sha256

File	Size	sha256
.gitattributes	2.07 KB	a4dbdf0e736d5e6357e81631e4552aa532efef4785dce0e13dcdd4aa58752a78
README.md	1.56 KB	7e04098c8f4499546dc8440387965e4f5d37e78008faeab69fa6c628ecb2e0d2
added_tokens.json	707 B	c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja	4.17 KB	a55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
config.json	1.54 KB	ed36641e183b3d95dcefad8906aa22d183c445e4b582c8a0ca7d71a713c85f2d
generation_config.json	188 B	3b101cd89b140b757d0bca469e75570e75789a2423ada90a33ec17707dfacf08
merges.txt	1.67 MB	8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00004.safetensors	4.90 GB	4f63e75a3995feae5f916993dd1fb533a7c9191f2e92e73e020a325fe5a34fc1
model-00002-of-00004.safetensors	4.92 GB	eeaa1109dbae21d1f45b5f45ddf28ba410f9855fd67305b1a581d40d96167f1d
model-00003-of-00004.safetensors	4.98 GB	61c8645c644b9badeb1c75eac15f2680c8826b6d6f761814a42caf4f77c63c1b
model-00004-of-00004.safetensors	1.58 GB	04bfbe35ac7c51ee7802ee8e44de570cc3a0739e068c09da2f201df95d2502bd
model.safetensors.index.json	32.9 KB	e7e4bdc58d3302c97357f27979b270987dd620cf0cd9b1c130e3a51c9d64df95
rl_config.yaml	13.5 KB	e9c90ec2d5542e2995cb94f033a2028980f9a2ea3f08de7695eab29fa9451219
special_tokens_map.json	613 B	76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json	11.4 MB	aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json	5.43 KB	3e27b302e9844c5b9648a8dbc1958fbbf3bda640e07302f53c17ac7a3192def5
training_logs/20260613_155933_metrics_seqnorm-tis-shaped_850358.csv	16.8 KB	878c3ac7ec5c358ea3b9c1b408a36f9e35863a8c9bcab7b29f703433c4abc254
training_logs/20260613_155933_metrics_seqnorm-tis-shaped_850359.csv	17.6 KB	ddf75bf8663af37f5c5a7b9ae987961c6f0e0349afff9ad4515d38e7698f076d
training_logs/20260613_155933_metrics_seqnorm-tis-shaped_850360.csv	15.6 KB	86233f23a54092b5a655cfe3c5cfd7b5e7da342d36c7b4163e2e61be6220571d
training_logs/20260613_155933_metrics_seqnorm-tis-shaped_850361.csv	5.92 KB	dfd7b70c2473e855869b0818ce25d186e2255423582cea87cffdbaa8a4816b2b
training_logs/20260613_155933_metrics_table.csv	50.8 KB	f9f9773074b4ddbaa619957e8d605613614bd7b1df2d73653a57598e1d45c37f
training_logs/20260613_155933_vllm_metrics_seqnorm-tis-shaped_850358.csv	689 KB	9ce7ea3b4fa0a07678a668615930a4633d026fa8f8e4b605fa3aa3cb6eb08e8c
training_logs/20260613_155933_vllm_metrics_seqnorm-tis-shaped_850359.csv	693 KB	081579abe0f71a8b32a1cbc0e1fc309a0a4a5db262daf39a1f85e277e2d24652
training_logs/20260613_155933_vllm_metrics_seqnorm-tis-shaped_850360.csv	684 KB	8deab2032f60d5dc38b0887db269afd232682dbb7ac57f95bc8ed92eda240467
training_logs/20260613_155933_vllm_metrics_seqnorm-tis-shaped_850361.csv	236 KB	901af2b95de6380682ce9e98753d8be9f8f2237a680a1b4d880a46c8ffcfa549
training_logs/20260613_155933_vllm_metrics_seqnorm-tis-shaped_850362.csv	664 B	56781561076a397425866f8dbf88b1e774812caaf997869e19cf3a77edb28c07
training_logs/20260613_155933_vllm_metrics_table.csv	3.05 MB	8a0ef974776d07d8d13ed78c1e247d88f926f06a7f571c929c569c07138d4632
training_logs/20260613_191904_metrics_report.md	24.1 KB	7f1638f97e712f614898c3b6a101f3ae09f10c8f5184c39225ee5587ac3a1921
training_logs/20260613_191904_metrics_seqnorm-tis-shaped_850358.csv	16.8 KB	878c3ac7ec5c358ea3b9c1b408a36f9e35863a8c9bcab7b29f703433c4abc254
training_logs/20260613_191904_metrics_seqnorm-tis-shaped_850359.csv	17.6 KB	ddf75bf8663af37f5c5a7b9ae987961c6f0e0349afff9ad4515d38e7698f076d
training_logs/20260613_191904_metrics_seqnorm-tis-shaped_850360.csv	15.6 KB	86233f23a54092b5a655cfe3c5cfd7b5e7da342d36c7b4163e2e61be6220571d
training_logs/20260613_191904_metrics_seqnorm-tis-shaped_850361.csv	5.92 KB	dfd7b70c2473e855869b0818ce25d186e2255423582cea87cffdbaa8a4816b2b
training_logs/20260613_191904_metrics_table.csv	50.8 KB	f9f9773074b4ddbaa619957e8d605613614bd7b1df2d73653a57598e1d45c37f
training_logs/20260613_191904_reward_vs_steps.png	293 KB	394e62a4889d4f9fec70bc9da8f84af94d4ffb19492b48b4c20b379f61173db6
training_logs/20260613_191904_trial_results.csv	3.95 MB	048cf73008dcefa88c66d2f9c531e0b3552775015bccbe5fe75861297468d82f
training_logs/20260613_191904_turn_count_distribution.png	118 KB	6444f663522c57c804f0d8026c70715b8ff309bbed0db7d0642d563031f0409e
training_logs/20260613_191904_vllm_metrics_seqnorm-tis-shaped_850358.csv	689 KB	9ce7ea3b4fa0a07678a668615930a4633d026fa8f8e4b605fa3aa3cb6eb08e8c
training_logs/20260613_191904_vllm_metrics_seqnorm-tis-shaped_850359.csv	693 KB	081579abe0f71a8b32a1cbc0e1fc309a0a4a5db262daf39a1f85e277e2d24652
training_logs/20260613_191904_vllm_metrics_seqnorm-tis-shaped_850360.csv	684 KB	8deab2032f60d5dc38b0887db269afd232682dbb7ac57f95bc8ed92eda240467
training_logs/20260613_191904_vllm_metrics_seqnorm-tis-shaped_850361.csv	236 KB	901af2b95de6380682ce9e98753d8be9f8f2237a680a1b4d880a46c8ffcfa549
training_logs/20260613_191904_vllm_metrics_seqnorm-tis-shaped_850362.csv	664 B	56781561076a397425866f8dbf88b1e774812caaf997869e19cf3a77edb28c07
training_logs/20260613_191904_vllm_metrics_table.csv	3.05 MB	8a0ef974776d07d8d13ed78c1e247d88f926f06a7f571c929c569c07138d4632
training_logs/seqnorm-tis-shaped_850358.out	57.2 MB	cbf921bc9c6fafd387eef2d5bf1fc3551d6a7f24fe795f74c3e539cc60576b3a
training_logs/seqnorm-tis-shaped_850359.out	59.2 MB	893f955ac0d970db549b627d767b11295f1193efc50928730dc3943408681885
training_logs/seqnorm-tis-shaped_850360.out	54.6 MB	d61a2ec3f3a9c2153af284c98a945798690a33a90347d276a1e56b489c151ad8
training_logs/seqnorm-tis-shaped_850361.out	20.4 MB	7b0d8f25626fb08e6421fcbabb6498493b26e7084c390aa10b9ef02cd5f841b3
training_logs/seqnorm-tis-shaped_850362.out	831 KB	f6596e43e50a001efbd6894e920f8ec504647bf2ee238ed881ef1ba2166cd364
vocab.json	2.78 MB	ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
64661facfd pinned now	2026-11-15 04:24 UTC	48 files · 16.6 GB

Use it

$ fw get laion/seqnorm-tis-shaped-40-8B
# manifest sha256 bc3b64d18fb8… · 16.6 GB · 48 files
$ fw verify ./seqnorm-tis-shaped-40-8B laion/seqnorm-tis-shaped-40-8B

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/seqnorm-tis-shaped-40-8B.json --dir ./seqnorm-tis-shaped-40-8B
$ python3 fw.py verify ./seqnorm-tis-shaped-40-8B ./laion__seqnorm-tis-shaped-40-8B.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/seqnorm-tis-shaped-40-8B --revision 64661facfd1c42f0c076c8b26bd0b8e8ff403a01 --local-dir ./seqnorm-tis-shaped-40-8B

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: 7e04098c8f4499546dc8440387965e4f5d37e78008faeab69fa6c628ecb2e0d2
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: seqnorm-tis-shaped-40-8BDate: 2026-11-15Commit: 64661faSigned: 2DC28CC7B26A283B ✓

Upstream: laion/seqnorm-tis-shaped-40-8B
Pinned commit: 64661facfd1c42f0c076c8b26bd0b8e8ff403a01
Manifest: seqnorm-tis-shaped-40-8B.json · .minisig
Manifest sha256: bc3b64d18fb8c0f1f1518d5b3dec4f1405b23e6d900416cb0d3f92930d742139
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 04:24 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/seqnorm-tis-shaped-40-8B.json
$ curl -O https://freeweights.allternit.com/manifests/laion/seqnorm-tis-shaped-40-8B.json.minisig
$ minisign -Vm seqnorm-tis-shaped-40-8B.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/seqnorm-tis-shaped-40-8B

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. seqnorm-tis-shaped-40-8B.json. Provenance. Takedown history: none.

Source

huggingface.co/laion/seqnorm-tis-shaped-40-8B

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