alt.freeweights.text / rl_mixed-struct-step37_terminus-structured
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

rl_mixed-struct-step37_terminus-structured

Date: 2026-11-15Commit: cd61074Signed: 2DC28CC7B26A283B ✓

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

8.2B params16.4GBrl_mixed-struct-step37_terminus-structuredsafetensorspermissive
FactsParams8.2BSize16.4 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get laion/rl_mixed-struct-step37_terminus-structured
# manifest sha256 dc69a1d1da04… · 16.4 GB · 16 files
$ fw verify ./rl_mixed-struct-step37_terminus-structured laion/rl_mixed-struct-step37_terminus-structured
From sourceHosted (signed)laion/rl_mixed-struct-step37_terminus-structuredLast check: 2026-11-15 04:25 UTC

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

Fine-tune of r2egym-nl2bash-stack-bugsseq-fixthink-again.

Works with

Overview

Size
16.4 GB
Weights
16.4 GB (safetensors)
Parameters
8.2B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
16, each with a sha256
Publisher
laion
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: laion/r2egym-nl2bash-stack-bugsseq-fixthink-again

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 cd61074. Shown as plain text with links; images open at the publisher.

rl_mixed-struct-step37_terminus-structured#

RL-trained Qwen3-8B with structured tool calls on mixed dataset (200 nl2bash + 500 r2egym + 500 swesmith).

37 RL steps with terminus-structured agent. SWEBench-100: 42% pass@3.

Training Details#

  • Base model: laion/r2egym-nl2bash-stack-bugsseq-fixthink-again
  • Training method: rloo-n with terminus-structured agent (structured tool calls: bash, view, edit, create, search)
  • Framework: BenSkyRL + Harbor
  • Context: 32k (24k input + 8k output)
  • Learning rate: 1e-5

SWEBench-Verified Results (100 tasks, pass@3)#

ModelSWEBench pass@3
Base SFT (terminus-2)37%
This model (terminus-structured)See eval results

Usage#

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("laion/rl_mixed-struct-step37_terminus-structured")
tokenizer = AutoTokenizer.from_pretrained("laion/rl_mixed-struct-step37_terminus-structured")

Files

16 files · 16.4 GBWeights 16.4 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.35 KBf33efa9cbbcb8ed4dee049cc55ab9cdd61921f7680abf6a633d788e0c3a40a50
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja4.17 KBa55ee1b1660128b7098723e0abcd92caa0788061051c62d51cbe87d9cf1974d8
config.json1.54 KBba0034e547c55d23e895919cd5ae10d05eefdda9562463b2c4a4c0fbeb32d698
generation_config.json188 Bd62d5449628acccf95dca468b1ff99002b3d0d428dfcdbe132f1be35a815a97b
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00004.safetensors5.29 GBde653b68542ad46d593011b7d8f5450051705bb52c70f20f097e9c027bd7780d
model-00002-of-00004.safetensors5.30 GB49d6513d285f655f720103510401627aa6fa1cf57cb805fd0a9e69aefd14866a
model-00003-of-00004.safetensors5.36 GBaee8f9df14b34a32cea9d8a996f58d177246b947d96b96c0a7f632adb579caf4
model-00004-of-00004.safetensors428 MB0eb565927691fd490ecb44d4fc111c6e6b23ac8b8b5375096a4abcb367882743
model.safetensors.index.json32.9 KBd25b6d9f406fc3e6d0472554555295ab62e1788f1db4ee1e87f597cd481fb73b
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.43 KB3e27b302e9844c5b9648a8dbc1958fbbf3bda640e07302f53c17ac7a3192def5
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
cd61074356 pinned now2026-11-15 04:25 UTC16 files · 16.4 GB

Use it

$ fw get laion/rl_mixed-struct-step37_terminus-structured
# manifest sha256 dc69a1d1da04… · 16.4 GB · 16 files
$ fw verify ./rl_mixed-struct-step37_terminus-structured laion/rl_mixed-struct-step37_terminus-structured
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/rl_mixed-struct-step37_terminus-structured.json --dir ./rl_mixed-struct-step37_terminus-structured $ python3 fw.py verify ./rl_mixed-struct-step37_terminus-structured ./laion__rl_mixed-struct-step37_terminus-structured.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/rl_mixed-struct-step37_terminus-structured --revision cd61074356e2e32402869193b995777e6817afda --local-dir ./rl_mixed-struct-step37_terminus-structured
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/rl_mixed-struct-step37_terminus-structured", revision="cd61074356e2e32402869193b995777e6817afda") model = AutoModelForCausalLM.from_pretrained("laion/rl_mixed-struct-step37_terminus-structured", revision="cd61074356e2e32402869193b995777e6817afda", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve laion/rl_mixed-struct-step37_terminus-structured --revision cd61074356e2e32402869193b995777e6817afda

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
f33efa9cbbcb8ed4dee049cc55ab9cdd61921f7680abf6a633d788e0c3a40a50
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: rl_mixed-struct-step37_terminus-structuredDate: 2026-11-15Commit: cd61074Signed: 2DC28CC7B26A283B ✓
Upstream
laion/rl_mixed-struct-step37_terminus-structured
Pinned commit
cd61074356e2e32402869193b995777e6817afda
Manifest
rl_mixed-struct-step37_terminus-structured.json · .minisig
Manifest sha256
dc69a1d1da04fb3d4cbb74a0922285b15f8669769710bb35c7b87d6da5ce7253
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/rl_mixed-struct-step37_terminus-structured.json $ curl -O https://freeweights.allternit.com/manifests/laion/rl_mixed-struct-step37_terminus-structured.json.minisig $ minisign -Vm rl_mixed-struct-step37_terminus-structured.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/r2egym-nl2bash-stack-bugsseq-fixthink-again · 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/rl_mixed-struct-step37_terminus-structured
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. rl_mixed-struct-step37_terminus-structured.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