CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / madlad400-8b-lm
From: google <huggingface.co/google>Newsgroups: alt.freeweights.textSubject:

madlad400-8b-lm

Date: 2026-11-15Commit: d1017b4Signed: 2DC28CC7B26A283B ✓

Text generation model with 8.6B parameters. Safetensors weights, 34.6 GB in all. Published by google under Apache-2.0.

8.6B params34.6GBmadlad400-8b-lmsafetensorspermissive
FactsParams8.6BSize34.6 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get google/madlad400-8b-lm
# manifest sha256 78e2769b7da3… · 34.6 GB · 19 files
$ fw verify ./madlad400-8b-lm google/madlad400-8b-lm
From sourceHosted (signed)google/madlad400-8b-lmLast check: 2026-11-15 03:49 UTC
Run at homeGet help

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

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
34.6 GB
Weights
34.5 GB (safetensors)
Parameters
8.6B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
19, each with a sha256
Publisher
google
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

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 03:49 UTCpassed

Model card

From the publisher at commit d1017b4. Shown as plain text with links; images open at the publisher.

This model has the safetensors weights for the Madlad-400 8B param language model.

The HF transformers code to run inference is not ready yet. The original implementation is in JAX/Flaxformer.

The model architecture is the same as Palm 8B.

It's a decoder-only T5 with 32 layers, 16 query heads, 1 KV head, and 4096 embedding size.

These are the main differences relative to the original T5 architecture:

  • SwiGLU Activation
  • Parallel Layers
  • Multi-Query Attention
  • RoPE Embeddings
  • Shared Input-Output Embeddings
  • No biases
  • Bidirectional attention
  • Layer Norm with center_scale_at_zero and final layer with use_scale=False

If you are looking for the language models models, here are the available versions:

Article: MADLAD-400: A Multilingual And Document-Level Large Audited Dataset

Abstract:

We introduce MADLAD-400, a manually audited, general domain 3T token monolingual dataset based on CommonCrawl, spanning 419 languages. We discuss the limitations revealed by self-auditing MADLAD-400, and the role data auditing had in the dataset creation process. We then train and release a 10.7B-parameter multilingual machine translation model on 250 billion tokens covering over 450 languages using publicly available data, and find that it is competitive with models that are significantly larger, and report the results on different domains. In addition, we train a 8B-parameter language model, and assess the results on few-shot translation. We make the baseline models available to the research community.

Files

19 files · 34.6 GBWeights 34.5 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 19 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md4.54 KBa5451837e4169bc77573882c1d858768462fe4ba82e7461cb2a66502876451a5
added_tokens.json4 Bd914176fd50bd7f565700006a31aa97b79d3ad17cee20c8e5ff2061d5cb74817
config.json1.12 KB638a7f9c006fb17ac7ef192a587a8a974e59f63062d8a771b5e9ea0a9b419338
decoderonlyt5_config.py459 B897baa5fb0aafa7f6918857cbbbd2a0605a22b663a95caf31eac91aa3e349251
decoderonlyt5_modeling.py34.3 KBb167a1373556dea6d6ea021b7bf782be4535f1babb3cb31bacbb77fcde3180bd
model-00000-of-00007.safetensors5.15 GBeee3b0c4eef668152f9f1106f18bf0a892bd04ba8b26017d7d5865f49dec5f3c
model-00001-of-00007.safetensors4.74 GB29b44a655d9261522e705d963d1fa7ca1717c3e6bcfb9402fa69cb8ee6156c6f
model-00002-of-00007.safetensors4.74 GB1dbd16405fa07722d953ba5c99aeb8ae05c1068cb4018a9622e5828336c1b9c8
model-00003-of-00007.safetensors4.74 GB7444d7670f145f12706970a191b260b609a82626c5e417f08f1039c05fbdda75
model-00004-of-00007.safetensors4.74 GB471e481023c3f4622d2ff0b1031a34c55469fb10fe1252f5c5c62e8f95418b4b
model-00005-of-00007.safetensors4.74 GBe934d8fcf5bc54649e82b29c1322b7ce3d13e8915d2cac205e65660e0a4cdbbb
model-00006-of-00007.safetensors4.74 GBf3f82de95453b49cb5a78ec517fac3219556f83edd9075a20a7ac95a577b5e93
model-00007-of-00007.safetensors948 MBf816e875186339eaf9afa8964d34952c80e697ade369154512f9900ea0a33553
model.safetensors.index.json24.5 KB219e2ceeacde5c3d59b52015e07a05dbd329d204667eae04e5ce840a1b10aa3d
special_tokens_map.json414 B7f79f1d5063d56c4b980eec0692f3c7429bdef335071d34e566bd00fd4b5e3e0
spiece.model4.43 MBef11ac9a22c7503492f56d48dce53be20e339b63605983e9f27d2cd0e0f3922c
tokenizer.json16.6 MBa2799ccc696b752ba00c34f58726bfe253a04921ceb6cfc620400f560474790b
tokenizer_config.json830 B641fc660745306dfb935f666a68f8bc10a44c39241cfb357be518fda8c09662d
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
d1017b424b pinned now2026-11-15 03:49 UTC19 files · 34.6 GB

Use it

$ fw get google/madlad400-8b-lm
# manifest sha256 78e2769b7da3… · 34.6 GB · 19 files
$ fw verify ./madlad400-8b-lm google/madlad400-8b-lm
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/google/madlad400-8b-lm.json --dir ./madlad400-8b-lm $ python3 fw.py verify ./madlad400-8b-lm ./google__madlad400-8b-lm.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download google/madlad400-8b-lm --revision d1017b424b97ad0fd1bbeca987ff208ef17367e0 --local-dir ./madlad400-8b-lm
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("google/madlad400-8b-lm", revision="d1017b424b97ad0fd1bbeca987ff208ef17367e0") model = AutoModelForCausalLM.from_pretrained("google/madlad400-8b-lm", revision="d1017b424b97ad0fd1bbeca987ff208ef17367e0", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve google/madlad400-8b-lm --revision d1017b424b97ad0fd1bbeca987ff208ef17367e0
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
a5451837e4169bc77573882c1d858768462fe4ba82e7461cb2a66502876451a5
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: google <huggingface.co/google>Newsgroups: alt.freeweights.textSubject: madlad400-8b-lmDate: 2026-11-15Commit: d1017b4Signed: 2DC28CC7B26A283B ✓
Upstream
google/madlad400-8b-lm
Pinned commit
d1017b424b97ad0fd1bbeca987ff208ef17367e0
Manifest
madlad400-8b-lm.json · .minisig
Manifest sha256
78e2769b7da3d90b636df6692430abb1da1ce029cd02c651a2db4c1499c07c9a
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:49 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/google/madlad400-8b-lm.json $ curl -O https://freeweights.allternit.com/manifests/google/madlad400-8b-lm.json.minisig $ minisign -Vm madlad400-8b-lm.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

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download google/madlad400-8b-lm
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. madlad400-8b-lm.json. Provenance. Takedown history: none.
Source
huggingface.co/google/madlad400-8b-lm

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