alt.freeweights.text / stories15M_MOE

From:

ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.textSubject:

stories15M_MOE

Date: 2026-11-15Commit: b6dd737Signed: 2DC28CC7B26A283B ✓

Text generation model with 36M parameters. Gguf and safetensors weights, 466 MB in all. Published by ggml-org under MIT.

36M params

466MBstories15M_MOEgguf safetensorspermissive

FactsParams36MSize466 MBFormatsgguf, safetensorsTasktext generationLicenseMITFrom sourcepermissive

$ fw get ggml-org/stories15M_MOE
# manifest sha256 a6bf01709efb… · 466 MB · 33 files
$ fw verify ./stories15M_MOE ggml-org/stories15M_MOE

From sourceHosted (signed)ggml-org/stories15M_MOELast check: 2026-11-15 02:33 UTC

Run at home Get help

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

Works with

Run34 Fine-tune29 Convert16 Evaluate13 Scan13 Apps58

Runs with

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

vLLM exo Text Generation WebUI

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

Show all 34

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX

ggml Core ML Tools ExecuTorch

Show all 16

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: 466 MB
Weights: 16.4 MB (smallest of 3 GGUF variants)
Parameters: 36M
Formats: gguf, safetensors
Task: text generation
License: MIT (permissive)
Files: 33, each with a sha256
Publisher: ggml-org
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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 02:33 UTC	passed

Model card

From the publisher at commit b6dd737. Shown as plain text with links; images open at the publisher.

stories15M_MOE#

This model is ModelCloud/tinyllama-15M-stories repeated 4 times to make 4 experts.

The model is used for testing, not intended to be used in production (unless your product is some kind of bedtime story teller)

Weight of router is initialized randomly

shakespeare LoRA adapter#

A LoRA adapter trained on first 100 paragraphs of shakespeare can be found inside moe_shakespeare15M

With input: Look in thy glass

Original model generates: Look in thy glass was a little girl. She was only three years old and she was three years old. She was
LoRA adapter generates: Look in thy glass in love of the eye: That's when when the eye see thy on the sun'

Files

33 files · 466 MBWeights 16.4 MB (smallest of 3 GGUF variants). Sizes and sha256 from the signed manifest.

Show all 33 files with their sha256

File	Size	sha256
.gitattributes	1.56 KB	e08cf896faa882fdfbf869edf3ac5e9cfaa850c0ff3b79cf4a29e394bbe2572a
.gitignore	26 B	5952c950c58173f4decbeab3d4baa8bca8a2e416e411e8714a4fd92e47b0ec83
README.md	763 B	99bd592e0326eedb94b444ecd00d175a7ccf25fad35cc695a07f24b8c166afec
config.json	711 B	e901e012953d1df93574b2cc3d7db5ed4758d52f8bd4a7dd4b647936e32261be
data.txt	66.9 KB	8aba9f75ac88b48a9576935995a26b806f3d2cd75f6ca9267fe0fba79cd3f64f
finetune.ipynb	5.87 KB	9340e2469b4cabf6ff40ae3e3c57cd7526065b3548dc9321d3a9f6c77673e1eb
generate_moe.ipynb	16.5 KB	de1b029dceaf02dba5263f3db60de5b14924363a234f19ba55d3751a93d073a5
generation_config.json	115 B	295aa491adda22ab9fbdecdda9e8121e8348fd0eea0529d8802993426ab0892c
model.safetensors	72.7 MB	dbfa0289f68a8dd721d10eb12d8bd82e098455682027f6f9986ba548913f9082
model.safetensors.index.json	8.89 KB	cd4af1df494f42e9099c1bdf9ea8487c06166c8ca60f6264a617497a8151fd31
moe_shakespeare15M.gguf	16.4 MB	d1e0617d7e10de960639d18a4620ec8c6bb56343f45692830d3634a1a3e1fe1a
moe_shakespeare15M/checkpoint-400/README.md	5.10 KB	9a5ff9e6e119283168af9ab99634853d19133e3e31ec154b34596fbd674ee5c9
moe_shakespeare15M/checkpoint-400/adapter_config.json	723 B	bc7a694ce0155d5ca6f7601f00fd61017b2f67615a5338745b5b5c97c43e89bb
moe_shakespeare15M/checkpoint-400/adapter_model.safetensors	68.2 MB	82cc79a24e640c3554d1465ef673df301cecb46eda10176e7fc90a8855c6c7cf
moe_shakespeare15M/checkpoint-400/optimizer.pt	62.7 MB	ae5736675ac820b1e25b6a3e298df4d49f8d571faecf7ed121a9a9027a0a02f4
moe_shakespeare15M/checkpoint-400/rng_state.pth	14.2 KB	32cbbc805815844964f4e4c4d6a59d08af005aa6a8c007556b995159e3413fc5
moe_shakespeare15M/checkpoint-400/scheduler.pt	1.06 KB	b98c509be49173a16c0268de5029f75de52b88c3d925c26c88bf4cafd360eb93
moe_shakespeare15M/checkpoint-400/trainer_state.json	3.69 KB	91d96f6b1afb85e0f28ca7da468409d8585a0dc4384cbf84d5560a0b8ee1e122
moe_shakespeare15M/checkpoint-400/training_args.bin	5.11 KB	a2b73b2f545cb4aeeed59e19bc6a72d15f8bfdd68be832143d3c7096a9982a57
moe_shakespeare15M/checkpoint-500/README.md	5.10 KB	9a5ff9e6e119283168af9ab99634853d19133e3e31ec154b34596fbd674ee5c9
moe_shakespeare15M/checkpoint-500/adapter_config.json	723 B	bc7a694ce0155d5ca6f7601f00fd61017b2f67615a5338745b5b5c97c43e89bb
moe_shakespeare15M/checkpoint-500/adapter_model.safetensors	68.2 MB	f18954c98a8efbf979d86e3af1f9a8e8fdf624a0bcf3aa239e59dd6d820f31cc
moe_shakespeare15M/checkpoint-500/optimizer.pt	62.7 MB	c02c354dd7b15801a89b4d60e6da5846270b8f81c4c8cb28e679907f5e76459b
moe_shakespeare15M/checkpoint-500/rng_state.pth	14.2 KB	2a9285bd087c798eb4268ef909268e501cbd456d1aaa56bfd2778031e469f9cd
moe_shakespeare15M/checkpoint-500/scheduler.pt	1.06 KB	cc4ab5f608c113ef9b81b5921bd661a21962184c52075538ed871611015781ce
moe_shakespeare15M/checkpoint-500/trainer_state.json	4.42 KB	f612e4f0b86fa83474b917d064ae4997750d28487d3e7edd1697ecd26ac85ddc
moe_shakespeare15M/checkpoint-500/training_args.bin	5.11 KB	a2b73b2f545cb4aeeed59e19bc6a72d15f8bfdd68be832143d3c7096a9982a57
run_finetuned.ipynb	3.69 KB	e8193577f5d571671e9804f2acfc856fa52394e8166193b9509db862c78ecae8
special_tokens_map.json	411 B	ff3b4a612c4e447acb02d40071bddd989fe0da87eb5b7fe0dbadfc4f74de7531
stories15M_MOE-F16.gguf	73.5 MB	1240dfc1957df9f3550dd6c1d9e64b466fc2f452d8bc34bd4e45e1a1e2ca6055
stories15M_MOE-Q8_0.gguf	39.4 MB	c7aa6863f9a4b3cdf19716e2c95622dcbd3bd06989324bf1ac8e60486ef8e881
tokenizer.json	1.84 MB	8eea70c4866c4f1320ba096fc986ac82038a8374dbe135212ba7628835b4a6f1
tokenizer_config.json	686 B	33d29c87e41f7dd1efb0434d852730320c82970f292be452d820539bce417052

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

Upstream commit	Date	Contents
b6dd737497 pinned now	2026-11-15 02:33 UTC	33 files · 466 MB

Use it

$ fw get ggml-org/stories15M_MOE
# manifest sha256 a6bf01709efb… · 466 MB · 33 files
$ fw verify ./stories15M_MOE ggml-org/stories15M_MOE

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

$ python3 fw.py get https://freeweights.allternit.com/manifests/ggml-org/stories15M_MOE.json --dir ./stories15M_MOE
$ python3 fw.py verify ./stories15M_MOE ./ggml-org__stories15M_MOE.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/stories15M_MOE --revision b6dd737497465570b5f5e962dbc9d9454ed1e0eb --local-dir ./stories15M_MOE

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("ggml-org/stories15M_MOE", revision="b6dd737497465570b5f5e962dbc9d9454ed1e0eb")
model = AutoModelForCausalLM.from_pretrained("ggml-org/stories15M_MOE", revision="b6dd737497465570b5f5e962dbc9d9454ed1e0eb", device_map="auto")

llama.cppDownload one GGUF variant (moe_shakespeare15M, 16.4 MB), then serve it.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/stories15M_MOE --include "moe_shakespeare15M*" --local-dir ./stories15M_MOE
$ llama-server -m ./stories15M_MOE/moe_shakespeare15M.gguf

OllamaMake an Ollama model from the downloaded file.

$ printf 'FROM ./stories15M_MOE/moe_shakespeare15M.gguf\n' > Modelfile
$ ollama create stories15m-moe -f Modelfile

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve ggml-org/stories15M_MOE --revision b6dd737497465570b5f5e962dbc9d9454ed1e0eb

Run at home

License

Name: MIT License
Id: MIT
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: 99bd592e0326eedb94b444ecd00d175a7ccf25fad35cc695a07f24b8c166afec
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:

ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.textSubject: stories15M_MOEDate: 2026-11-15Commit: b6dd737Signed: 2DC28CC7B26A283B ✓

Upstream: ggml-org/stories15M_MOE
Pinned commit: b6dd737497465570b5f5e962dbc9d9454ed1e0eb
Manifest: stories15M_MOE.json · .minisig
Manifest sha256: a6bf01709efbab2f4252537149e40defa9bc478caa987b6874388d5bdca1d46d
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 02:33 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/stories15M_MOE.json
$ curl -O https://freeweights.allternit.com/manifests/ggml-org/stories15M_MOE.json.minisig
$ minisign -Vm stories15M_MOE.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 ggml-org/stories15M_MOE

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. stories15M_MOE.json. Provenance. Takedown history: none.

Source

huggingface.co/ggml-org/stories15M_MOE

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

stories15M_MOE

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

stories15M_MOE#

shakespeare LoRA adapter#

Files

Use it

License

Provenance

How to verify

Model tree

Related models