alt.freeweights.text / tt-x2_clip-hi0p05-10-30B

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

tt-x2_clip-hi0p05-10-30B

Date: 2026-11-15Commit: 4defbabSigned: 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-x2_clip-hi0p05-10-30Bsafetensorspermissive

FactsParams30.5BSize61.1 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get laion/tt-x2_clip-hi0p05-10-30B
# manifest sha256 f38e7887d9c9… · 61.1 GB · 16 files
$ fw verify ./tt-x2_clip-hi0p05-10-30B laion/tt-x2_clip-hi0p05-10-30B

From sourceHosted (signed)laion/tt-x2_clip-hi0p05-10-30BLast check: 2026-11-15 04:15 UTC

Run at home Get 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

Run24 Fine-tune29 Convert15 Evaluate13 Scan13 Apps58

Runs with

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

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers LMCache Xinference LMDeploy mistral.rs Mooncake FlashInfer

Show all 24

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad gpu-unlock Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX Core ML Tools ExecuTorch

Show all 15

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Show all 13

picklescan

Overview Model card Files Use it License Provenance Model 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: 16, 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

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

Model card

From the publisher at commit 4defbab. Shown as plain text with links; images open at the publisher.

tt-x2_clip-hi0p05 -- step 10 (PPO upper-clip = 0.05)#

GRPO checkpoint from the TaskTrove X2 (upper PPO clip) sweep. Base model Qwen/Qwen3-Coder-30B-A3B-Instruct, trained on DCAgent/exp_rpt_multifile with SkyRL + Terminus-2; campaign verifier is pass_ratio shaping.

Checkpoint selection#

global_step_10 was selected by the trailing-5 reward EMA (alpha = 1/3) over the full restart chain -- the highest-EMA aligned checkpoint (EMA 0.2094; step reward 0.2344; pass@8 0.4516; entropy 0.1184), per parse_skyrl_metrics.py --run_dir --save_every 5.

Run status -- terminated near-horizon (elevated entropy)#

Terminated by the owner at step 76/80. Reward peaked early (step 10) then declined as policy entropy climbed ~8x (0.11 -> 0.90) -- approaching the campaign entropy stop rule (10x). Step 10 is the best saved checkpoint. Not a horizon result.

See training_logs/ for metrics.csv, report.md, reward_plot.png, rl_config.json, and the gzipped .out chain.

Training Traces#

open-athena/tt-x2_clip-hi0p05 -- 1/4 systematic subsample (every 4th trial, uniform coverage; 24,125 rows from ~103k trials across 4 run roots). The full set was GPFS-read-bound on the Jupiter login node; subsample is a documented deviation for this terminated (76/80) arm.

Files

16 files · 61.1 GBWeights 61.1 GB (safetensors). Sizes and sha256 from the signed manifest.

Hide all 16 files with their sha256

File	Size	sha256
.gitattributes	1.70 KB	f597e39f2e5b0e820e810496e36aee321dc80575680c89fa6a706b3302228b0f
README.md	1.54 KB	57dafed559b0976fbba1e8a338cfd68d9779aa791d1a482bbc2a2f6c4a1beed6
chat_template.jinja	6.21 KB	5a38bfa05833266240066aedc497decc9b00cc0d3e3b8cceea98cf530196ab06
config.json	1.02 KB	e8b91d3d30aae0cc141cb2412d434445f8b19dae5a77d01bb332d744d4d72005
generation_config.json	217 B	2cb42f3bbca69b7dbf925354f69a3a8c5ef2184f33f8c2cd744d24aaa8e6ca69
model-00001-of-00002.safetensors	50.0 GB	0af7b5bb833255dc7074689446b7f38512e0f8e6db4de700ca532442055140d7
model-00002-of-00002.safetensors	11.1 GB	d3a3d1eb99d10d0fcd232b3a5993fb3890fb4a2f806c327490526a22a1707f30
model.safetensors.index.json	1.70 MB	8056f5e61a77bcc39322368320783ace12dfd0877cf642821620e33341d5d25e
tokenizer.json	11.4 MB	be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
tokenizer_config.json	693 B	45d3581eb7a1eba4265c25dab7825032d4945f8829fec21deeee33cb1f359881
training_logs/metrics.csv	122 KB	6c6a3f8179143e1c23547f4d93385288270b501687ebd06f9443264d2a0875c6
training_logs/report.md	33.9 KB	1e15e308f4a7036514eebc041119869a9e3aed97f9fee0a68578cb7b87cd72bc
training_logs/reward_plot.png	574 KB	f7f72d87088b4be84af65497add0943129e524ef935ababa07523bb7f4181bf6
training_logs/rl_config.json	9.23 KB	97cb8015d3b28181f8322c96f3eb2e90784671e36397ad8713e3fd0431cc5cef
training_logs/tt-x2_clip-hi0p05_out_logs.tar.gz	5.48 MB	268b6ad48d6f1573fef0ff59a078969098ce5081741a9b3acb79ec3fe7752df8
training_logs/vllm_metrics.csv	10.7 MB	7b078aaebd435927b425930ef3b1d3363ece555162fc40e4be6e91b843a768fa

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

Upstream commit	Date	Contents
4defbab8ac pinned now	2026-11-15 04:15 UTC	16 files · 61.1 GB

Use it

$ fw get laion/tt-x2_clip-hi0p05-10-30B
# manifest sha256 f38e7887d9c9… · 61.1 GB · 16 files
$ fw verify ./tt-x2_clip-hi0p05-10-30B laion/tt-x2_clip-hi0p05-10-30B

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

$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/tt-x2_clip-hi0p05-10-30B.json --dir ./tt-x2_clip-hi0p05-10-30B
$ python3 fw.py verify ./tt-x2_clip-hi0p05-10-30B ./laion__tt-x2_clip-hi0p05-10-30B.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/tt-x2_clip-hi0p05-10-30B --revision 4defbab8ac4d2a273168f17555d12835eea21e54 --local-dir ./tt-x2_clip-hi0p05-10-30B

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-x2_clip-hi0p05-10-30B", revision="4defbab8ac4d2a273168f17555d12835eea21e54")
model = AutoModelForCausalLM.from_pretrained("laion/tt-x2_clip-hi0p05-10-30B", revision="4defbab8ac4d2a273168f17555d12835eea21e54", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve laion/tt-x2_clip-hi0p05-10-30B --revision 4defbab8ac4d2a273168f17555d12835eea21e54

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: 57dafed559b0976fbba1e8a338cfd68d9779aa791d1a482bbc2a2f6c4a1beed6
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-x2_clip-hi0p05-10-30BDate: 2026-11-15Commit: 4defbabSigned: 2DC28CC7B26A283B ✓

Upstream: laion/tt-x2_clip-hi0p05-10-30B
Pinned commit: 4defbab8ac4d2a273168f17555d12835eea21e54
Manifest: tt-x2_clip-hi0p05-10-30B.json · .minisig
Manifest sha256: f38e7887d9c9bd25c60d135e9b6465c27f3ad7ac15f1ce354343568e5eb33c8b
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-x2_clip-hi0p05-10-30B.json
$ curl -O https://freeweights.allternit.com/manifests/laion/tt-x2_clip-hi0p05-10-30B.json.minisig
$ minisign -Vm tt-x2_clip-hi0p05-10-30B.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-x2_clip-hi0p05-10-30B

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. tt-x2_clip-hi0p05-10-30B.json. Provenance. Takedown history: none.

Source

huggingface.co/laion/tt-x2_clip-hi0p05-10-30B

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

tt-x2_clip-hi0p05-10-30B

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

tt-x2_clip-hi0p05 -- step 10 (PPO upper-clip = 0.05)#

Checkpoint selection#

Run status -- terminated near-horizon (elevated entropy)#

Training Traces#

Files

Use it

License

Provenance

How to verify

Model tree

Related models