CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.olmo / Emo_1b14b_130B
From: allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.olmoSubject:

Emo_1b14b_130B

Date: 2026-11-15Commit: ca26e66Signed: 2DC28CC7B26A283B ✓

Text generation model with 13.6B parameters. Safetensors weights, 54.3 GB in all. Published by allenai under Apache-2.0.

13.6B params54.3GBEmo_1b14b_130Bsafetensorspermissive
FactsParams13.6BSize54.3 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get allenai/Emo_1b14b_130B
# manifest sha256 bf0dcf1a13c4… · 54.3 GB · 24 files
$ fw verify ./Emo_1b14b_130B allenai/Emo_1b14b_130B
From sourceHosted (signed)allenai/Emo_1b14b_130BLast check: 2026-11-15 03:52 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
54.3 GB
Weights
54.3 GB (safetensors)
Parameters
13.6B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
24, each with a sha256
Publisher
allenai
Added
2026-11-15
Section
alt.freeweights.olmo
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 03:52 UTCpassed

Model card

From the publisher at commit ca26e66. Shown as plain text with links; images open at the publisher.

Emo_1b14b_130B#

A smaller-scale ablation checkpoint of EMO from EMO: Pretraining Mixture of Experts for Emergent Modularity — referred to as EMO at the 130B-token scale in the paper (Table 1 / Figure 11). Not midtrained.

1B-active / 14B-total parameter Mixture-of-Experts model (128 experts: 127 routed + 1 shared, k=8 active per token) pretrained on 130B tokens of the OLMoE pretraining mix with the EMO document-level expert pool constraint. Used in the paper's memory-matched ablation suite.

Usage#

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "allenai/Emo_1b14b_130B"
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

inputs = tokenizer(["Language modeling is "], return_tensors="pt", return_token_type_ids=False)
out = model.generate(**inputs, max_new_tokens=100, do_sample=True, temperature=1.0, top_p=0.7)
print(tokenizer.batch_decode(out, skip_special_tokens=True)[0])

Citation#

@article{wang2026emo,
  title  = {EMO: Pretraining Mixture of Experts for Emergent Modularity},
  author = {Wang, Ryan and Bhagia, Akshita and Min, Sewon},
  year   = {2026},
  url    = {https://arxiv.org/abs/2605.06663}
}

License#

This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with Ai2's Responsible Use Guidelines

Files

24 files · 54.3 GBWeights 54.3 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 24 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md1.81 KBae95507ca2597f60be40d9a4f14b871fb0da30b8eb53e8e8d6cbf8e6a68407ae
chat_template.jinja196 B153280e3ff55d19da1398bdb3914ee2a51b80429bfaedde11d7d216c39db80f3
config.json983 Bd685e45834e783c2bed3b1c86d75eb7c84da529c3f5650758e9a6a511cd149b2
configuration_emo.py11.7 KBf1bd419d8dd926cf7d15131b8192938a0feda1b003586320fa56de20360e4bf2
generation_config.json69 B49b7b376c9a77281e37b1544e00f6b83ffe1d46bd47ff1c5ee04a7d642ecbe2b
merges.txt917 KBb6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502
model-00001-of-00011.safetensors4.99 GB68e0a585ca88ebdb52632dc4c1a2bb57eaa9037ec5ed1a86f0f607094a8e21e6
model-00002-of-00011.safetensors4.99 GBac128f7a54d8214699d4c88526a7bf2a996468ab71b6ed45525bfcdef67af0a4
model-00003-of-00011.safetensors4.99 GBa0119f6ab0b159b6abfb37f1d1360c35b5af86774e4861956cdef49e075832c8
model-00004-of-00011.safetensors4.99 GB0aebc6c1e5b92658d16684a3dda56f8eb732d3e5a3c891162bafc73b798a3bde
model-00005-of-00011.safetensors4.99 GBfb4643446571694226deb3fd061461629f7a071d8f97b6af57b6833000d6805b
model-00006-of-00011.safetensors4.99 GB3aa4f3f2473dc5ff535d8ffe772a4578a1427ae86d97848cadfe09efd092cd0d
model-00007-of-00011.safetensors4.99 GB587e0f4df9b73402497ed451fc0d5a86588b3cd3a411fcd656ea9a793fb00d90
model-00008-of-00011.safetensors4.99 GB7fd2ed6696918c81b08b2c9ea8fa8b0ec1b9da2dde636f7a79c801061838e67b
model-00009-of-00011.safetensors4.99 GBb6ef2ecac98762c7a3ef335f2d1fc4db1b435bed52f8e9555b3a4a79cc85e0e1
model-00010-of-00011.safetensors4.99 GB469da95a25f96f61df7f90080880ef77d4be2c90ebbb428dc7b3339b26af12ad
model-00011-of-00011.safetensors4.35 GBf9c1a2c4babb4817a4882f8243dc5f55ed91c308e78901188d8d899ce524e67d
model.safetensors.index.json562 KB934e6eb0b66c52b4f4a5d7ef7fde489f41d8fa697ea8ff52862c959377412339
modeling_emo.py55.2 KBe10fb25a662d581b25708c7b1d640ba22c7547824a1f4f00c1fc39f08801d32b
special_tokens_map.json207 B4cb2b52960bababa8ec27153831e405ef7811e3fad1226106e09c28e715cfb21
tokenizer.json7.14 MB73fd5254624f39a88e3faac6a8e11300fc3c735ed37880d4f4f08db898eaecca
tokenizer_config.json4.31 KB733b2ec0f743cf206dd20335eacbd4427c85487fd6f5216bb361f92a85314315
vocab.json1.61 MB9e14712c91b37c7aab74b1306baa46ac342d620637a4b44523cdc3aec7d24195
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
ca26e6680d pinned now2026-11-15 03:52 UTC24 files · 54.3 GB

Use it

$ fw get allenai/Emo_1b14b_130B
# manifest sha256 bf0dcf1a13c4… · 54.3 GB · 24 files
$ fw verify ./Emo_1b14b_130B allenai/Emo_1b14b_130B
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/allenai/Emo_1b14b_130B.json --dir ./Emo_1b14b_130B $ python3 fw.py verify ./Emo_1b14b_130B ./allenai__Emo_1b14b_130B.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download allenai/Emo_1b14b_130B --revision ca26e6680d4e4c3721efa19d83ea38cf05bebfa4 --local-dir ./Emo_1b14b_130B
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("allenai/Emo_1b14b_130B", revision="ca26e6680d4e4c3721efa19d83ea38cf05bebfa4") model = AutoModelForCausalLM.from_pretrained("allenai/Emo_1b14b_130B", revision="ca26e6680d4e4c3721efa19d83ea38cf05bebfa4", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve allenai/Emo_1b14b_130B --revision ca26e6680d4e4c3721efa19d83ea38cf05bebfa4
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
ae95507ca2597f60be40d9a4f14b871fb0da30b8eb53e8e8d6cbf8e6a68407ae
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: allenai <huggingface.co/allenai>Newsgroups: alt.freeweights.olmoSubject: Emo_1b14b_130BDate: 2026-11-15Commit: ca26e66Signed: 2DC28CC7B26A283B ✓
Upstream
allenai/Emo_1b14b_130B
Pinned commit
ca26e6680d4e4c3721efa19d83ea38cf05bebfa4
Manifest
Emo_1b14b_130B.json · .minisig
Manifest sha256
bf0dcf1a13c4f1ad7ea3857266d6d1c1c79864b81e2d55d9b14ce393beb32e39
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:52 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/allenai/Emo_1b14b_130B.json $ curl -O https://freeweights.allternit.com/manifests/allenai/Emo_1b14b_130B.json.minisig $ minisign -Vm Emo_1b14b_130B.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 allenai/Emo_1b14b_130B
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Emo_1b14b_130B.json. Provenance. Takedown history: none.
Source
huggingface.co/allenai/Emo_1b14b_130B

Related models

All of alt.freeweights.olmo →
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3-7B-Instruct-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3-7B-Think-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3.1-32B-Instruct-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3.1-32B-Think-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_olmOCR-2-7B-1025-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_olmOCR-7B-0225-preview-GGUF