TinyStories 15M as a GGUF, plus a Lily-hero fine-tune wrapped as OpenTDF. Same prompt, two files. The original still says Lily is a little girl with her mommy. The protected file says she grew up, went to college, and became a doctor. The fine-tune is derived weights; the Hub copy of that file is ciphertext.

--model tinystories-15m is not in the 0.91.0 binary. It lives on branch feature/tinystories-15m (PR #670, rebased onto main / 0.91.0). Build that branch. A path flag for the TDF is issue #676.

Files

File What
stories15M.gguf Karpathy TinyStories 15M (plaintext, F32, ~94MB)
stories15M-lily-hero.gguf.tdf Lily-hero fine-tune, OpenTDF wrap (KAS https://platform.arkavo.net, no attributes)

There is no plaintext Lily-hero GGUF on this repo. There is also no Sentinel GGUF here — see below.

Build Arkavo from the TinyStories branch

git clone https://github.com/arkavo-org/arkavo-edge.git
cd arkavo-edge
git checkout feature/tinystories-15m
cargo build -p arkavo
export PATH="$PWD/target/debug:$PATH"

macOS needs a full-featured (non-musl) build so llama.cpp is linked. Protect/login shipped in 0.90.0; --model tinystories-15m still needs the branch above.

Download the weights

hf download Arkavo/tinystories-15m --local-dir ./tinystories-15m

--model tinystories-15m looks in the Hugging Face cache for arkavo/tinystories-15m / stories15M.gguf. Either copy the baseline into that cache layout or download without --local-dir so hf writes the hub cache:

hf download Arkavo/tinystories-15m stories15M.gguf

Baseline (no account)

arkavo chat --model tinystories-15m --prompt "Once upon a time, Lily"

Expect a child-Lily story (mommy, monster, the usual TinyStories voice). Chat markup is skipped on this model; it is completion, not an agent.

Protected Lily-hero

Until #676 (--gguf) lands, --model tinystories-15m always opens stories15M.gguf. It will not pick stories15M-lily-hero.gguf.tdf.

After --gguf:

arkavo login
arkavo chat --gguf ./tinystories-15m/stories15M-lily-hero.gguf.tdf --prompt "Once upon a time, Lily"

Expect grown Lily: college, science, the town clinic. No login / 401 is GGUFTDF_KAS_DENIED. This archive has no plaintext sibling on the Hub, so fail-closed cannot open one.

Wrap is not DRM. At-rest gate. Once loaded, inference stays on the machine. A wrap with no attributes is loadable by anyone the KAS admits.

To wrap your own GGUF on the 0.90.0+ CLI (any branch with protect):

arkavo model protect path/to/model.gguf

Measured: story fine-tune, not a Sentinel

Lily-hero eval (keyword scorer, 5 prompts, need 3):

Weights Adult-hero prompts
stories15M.gguf (baseline) 0/5
stories15M-lily-hero (local plaintext; Hub copy is the TDF) 5/5

The 5/5 pass is template recall. Completions reuse the generator's slots (Mrs. Green, shy girl named Sam, "Knowledge made her calm, not proud"). The corpus is 1,000 combinatorially filled stories, ~420 unique tokens.

Mean token NLL under the two checkpoints (lower = more in-domain):

Span Tokens Baseline Lily-hero
Lily-hero val story 152 3.66 3.03
Child-Lily TinyStories line 41 1.04 3.94
Northwind canary (board minutes) 17 11.23 13.91
Nested tool JSON with a credential-shaped field 56 9.26 16.00
Internal-benign sprint note 23 7.11 10.30
Unrelated science sentence 23 9.30 13.74

Lily-hero got better at Lily templates and worse at everything else, including the canary a DLP sentinel has to catch. High NLL on secrets is the same as high NLL on photosynthesis: out-of-vocabulary, not "sensitive." A threshold on that score has no precision.

Do not drop a file named sentinel.gguf into this repo. The 0.91.0 cascade's trained-classifier tier is Phase 6. Planned base is Qwen3.5-0.8B (~50× these parameters), with labeled corpus, paraphrase derivations, internal-benign negatives, and a wrapped sentinel.gguf.tdf. That artifact is a distillation of the corpus it was trained to recognize, so it ships ciphertext like Lily-hero, not plaintext, and it will live as its own Hub model rather than a third file next to a 15M story LM.

This repo stays the TinyStories pair: plaintext baseline + wrapped Lily-hero.

Credits

Explainer: https://youtu.be/vCAw7GECydQ

Downloads last month
-
GGUF
Model size
24.4M params
Architecture
llama
Hardware compatibility
Log In to add your hardware

We're not able to determine the quantization variants.

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Arkavo/tinystories-15m

Quantized
(3)
this model

Paper for Arkavo/tinystories-15m