smolgpt-fables

neonforestmist/smolgpt-fables

smolgpt-fables is a text generation model from neonforestmist. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

<p align="center" <a href="https://github.com/neonforestmist/SmolGPT-Fables-iOS" <img src="https://raw.githubusercontent.com/neonforestmist/SmolGPT-Fables-iOS/main/docs/smolgpt-fables-banner.png" alt="SmolGPT-Fables w…

Downloads · 30 days

125

3% of all-time downloads

All-time downloads

4.2K

Public

Parameters

1.7B

5.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors3.4 GB · 76%

At a glance

Task: Text Generation
Library: transformers
License: apache-2.0
Model type: llama
Access: Public
Created: Jul 11, 2026
Updated: Aug 29, 2026
SHA: d29900c9

Try a prompt

Base models

HuggingFaceTB/SmolLM2-1.7B-Instruct

Datasets

neonforestmist/smolgpt-markdown-stories

Spaces

neonforestmist/SmolGPT-Fable-Studio

Model card

From the Hugging Face model README

SmolGPT-Fables v1

SmolGPT-Fables turns a simple idea into a short story with one to six scenes. Tell it who the characters are, where the story happens, and how you want it to end. It handles the story structure for you.

What it does

Writes short English stories and fables with 1–6 numbered scenes.
Accepts separate Name and About them fields for each main character.
Tries to preserve requested names, setting details, important objects, and endings.
Runs with Transformers or llama.cpp-compatible apps. A separate Core ML companion is available for native Apple apps.

See it in action

Open SmolGPT-Fables Studio, choose the model and number of scenes, then describe each character in their own card. The Studio returns a clean story preview and a Markdown download.

Try a story

The easiest way to use the model is SmolGPT-Fables Studio. You do not need to write Markdown or learn a prompt format.

Story idea: Two rival mapmakers must share one observatory during the season when stars change their names.
Genre: Romance
Scenes: 3

Name: Mara
About them: A careful mapmaker who wants credit for her work.

Name: Ilyan
About them: A wandering artist looking for a home.

Setting: A cliffside observatory above a winter port.
Important moments: The star charts begin changing; Mara and Ilyan discover a shared error; they publish the corrected map together.
Details: Include a brass compass and snow on the observatory glass. Avoid a tragic ending.
Ending: Hopeful, with their work and trust made public.

Examples from the hosted Studio

These three representative cards show complete, captured outputs from SmolGPT-Fables v1 generations in the Studio's Examples tab. They are stacked for easy reading: two three-scene stories and one six-scene story. The hosted Studio contains six complete examples in total.

<details open> <summary>The Names of Stars · Romance · 3 scenes · Mara Vale, Ilyan Rook</summary>

### Scene 01:
The cliffside observatory above the winter port held a brass compass, its needle trembling in the cold air. Mara Vale, a rival mapmaker, stood beside the window, her eyes fixed on the stars streaming across the sky. Ilyan Rook, her counterpart, stood at the edge of the room, his gaze fixed on the map spread out before him. The air was thick with tension, as the two mapmakers knew that the season when stars changed their names would soon arrive, and with it, the chance to claim the greatest prize in the world of cartography.

### Scene 02:
As the night wore on, Mara and Ilyan found themselves drawn to the same corner of the room, where a single, unmarked map lay spread out before them. The map was old, its ink faded to a deep brown, but it was clear that it had been drawn by a master hand. Mara and Ilyan both knew that the map was the key to unlocking the greatest prize in the world of cartography, and they both knew that they had to have it.

### Scene 03:
As the night wore on, Mara and Ilyan found themselves engaged in a heated debate over the map. Mara argued that the map was too old to be of any use, while Ilyan argued that the map was too valuable to be shared. The debate raged on, with neither side willing to back down. But just as it seemed that the debate would never end, a sudden movement caught everyone's eye.

</details> <details open> <summary>The Last Crossing · Folklore · 3 scenes · Orra and the fox</summary>

# The Last Crossing

### Scene 01:
The braided river where crossings are paid for with useful stories swirled in mist as Orra stepped aboard her ferry. Frost creaked beneath the lantern, and she counted the last passenger before river freeze - a fox carrying a village's missing shadow. Its fur shimmered like moonlight, and its eyes gleamed with ancient wisdom.

### Scene 02:
Orra learned the shadow belonged to the village. It had been lost in the chaos of harvest, when laughter and tears mingled in the wind. The fox sat beside her, its paws brushing the edge of the bell that hummed softly, echoing the village's heartbeat. She realized the crossing was not just a journey but a gift.

### Scene 03:
As the river froze, Orra set the fox ashore, the shadow unfolding from its mouth like a wing. The fox vanished into the ice, leaving behind the bell and the memory of the village's joy. Orra watched as the river reshaped itself around them, and the story returned home.

</details> <details open> <summary>The Teapot at Number Nine · Cozy fantasy · 6 scenes · Mina Bell, Pip</summary>

### Scene 01:
The tiny row house where the teapot remembered every neighbor's favorite song held its breath as Mina Bell entered. She had returned the borrowed teapot, but the house's annual porch supper was already in full swing. The teapot, its china glinting in the soft light, seemed to be watching Mina with a quiet curiosity.

### Scene 02:
As Mina approached the porch, the teapot began to sing. Its voice was low and melodious, filling the air with the scent of old china and fresh tea. The neighbors, who had been chatting and laughing, paused in their conversation, their faces filled with wonder.

### Scene 03:
Mina stood frozen, her eyes fixed on the teapot as it sang. She had never seen anything like it before. The teapot, sensing her wonder, continued to sing, its voice growing louder and more vibrant with each passing moment.

### Scene 04:
As the teapot sang, the porch supper began to take shape. The neighbors, who had been watching Mina with curiosity, began to gather around the teapot, their faces filled with wonder. The teapot, sensing their excitement, continued to sing, its voice growing louder and more vibrant with each passing moment.

### Scene 05:
As the teapot sang, the neighbors began to share stories and laughter. The teapot, sensing their joy, continued to sing, its voice growing louder and more vibrant with each passing moment. Mina, who had been watching the scene unfold, felt a sense of wonder and connection that she had never felt before.

### Scene 06:
As the teapot sang, the neighbors began to disperse, each carrying a small piece of the teapot's magic. Mina, who had been watching the scene unfold, felt a sense of wonder and connection that she had never felt before. She knew that she would carry the teapot's magic with her always, and that she would never forget the sense of wonder and connection that it had brought into her life.

</details>

These are observed generations from the published v1 revision, not promises that every prompt will use the same words.

Use it with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "neonforestmist/smolgpt-fables"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)

messages = [
    {
        "role": "user",
        "content": (
            "Write a two-scene cozy fable about Mina Vale, a careful mapmaker, "
            "and Orin Reed, a retired courier. Set it in a canal city at "
            "midnight and end with Mina restoring a vanished neighborhood."
        ),
    }
]
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, do_sample=False, max_new_tokens=700)
new_tokens = outputs[0, inputs["input_ids"].shape[1]:]
print(tokenizer.decode(new_tokens, skip_special_tokens=True))

SmolGPT-Fables model

These are the files for the standard language model. Pick the format that fits your runtime:

Format	File	Size	Best for
Standard	`model.safetensors`	3.42 GB	Transformers and full model precision
Compact	`SmolGPT-Fables-v1-Q4_K_M.gguf`	1.06 GB	Runtimes that support `Q4_K_M` GGUF models

The standard and GGUF files are the model variants in this repository. The evaluation results below apply to the standard Transformers model; the GGUF variant has not been evaluated separately.

Core ML companion

The Core ML version now lives in its own repository so it is easy to distinguish from the standard SmolGPT-Fables model. It is intended for native Apple apps and is not required for Transformers or GGUF use.

Format	Companion repository	Size	Best for
Core ML INT4	`neonforestmist/smolgpt-fables-coreml`	0.96 GB	Native Apple apps on iOS 18 or macOS 15 and later

The companion card reports the Core ML conversion and numerical smoke-test results separately, including cosine similarity and top-token agreement.

Variant snapshot

Variant	Size	Format	Published evidence
SmolGPT-Fables v1	3.42 GB	BF16 `safetensors`	1.71B parameters; story evaluation below
SmolGPT-Fables v1 Compact	1.06 GB	`Q4_K_M` GGUF	218 tensors; quantization manifest published
SmolGPT-Fables v1 Apple	0.96 GB	Core ML INT4	0.9529 FP16/INT4 cosine similarity; matching top token; 4/5 top-5 overlap

The Apple variant is distributed from the separate Core ML companion repository.

Story behavior evaluation

This is a focused 60-prompt development evaluation for the Studio behavior—not a claim of broad language-model benchmark performance. The full manifests and SHA-256 evidence are published with the model files.

How well it works

The Studio-focused check is strong on the behavior this interface needs:

Check	Result
Stories containing every requested full name	60 / 60 (100%)
First name combined with the wrong surname	0 / 60
Studio behavior gates	All passed
Strict writing suite	32 / 60 (53.3%)
Minimum distinct-trigram rate	0.8394 (target 0.8500)

The strict suite's most common misses were incomplete causal resolution and scene length. These measurements are useful signals, not guarantees for every story.

Story-focused comparison

This is the comparison that matters for the Fables Studio. All three models received the same ten story briefs: a mix of three- and six-scene requests, different genres, named characters, settings, and required story details. Decoding was deterministic. Bold marks the best direction in each row.

Story check (10 shared briefs)	SmolGPT-Fables v1	SmolLM2 1.7B Instruct	Qwen2.5 1.5B Instruct
Requested names retained	6 / 10 (60%)	8 / 10 (80%)	9 / 10 (90%)
Story detail anchors retained	12 / 20 (60%)	14 / 20 (70%)	14 / 20 (70%)
Exact requested scene count	9 / 10 (90%)	5 / 10 (50%)	0 / 10 (0%)
Story contract pass (names + scene count)	5 / 10 (50%)	4 / 10 (40%)	0 / 10 (0%)

The complete prompt suite, pinned revisions, raw SmolGPT-Fables example captures, and per-prompt results are in the benchmarks/smolgpt_fables_story_comparison_v1.json report. This is a focused product measurement, not a broad language-model leaderboard.

Known limits

Names and requested scene counts are learned behavior, not hard guarantees.
Longer stories can lose continuity or end weakly.
The model can repeat phrases or flatten cultural nuance.
It is English-focused and intended for short stories rather than factual advice.
Review and edit generated writing before sharing it.

Training data

SmolGPT-Fables v1 was adapted from HuggingFaceTB/SmolLM2-1.7B-Instruct using the published neonforestmist/smolgpt-markdown-stories dataset. The synthetic and curated stories cover varied genres, settings, character descriptions, required details, and endings.

<details> <summary>Technical checks and exact artifact hashes</summary>

The published BF16 artifact contains 1,711,376,384 parameters across 218 tensors. It uses micro update 8 over adapter update 68 and the smolgpt-fables-smollm3-chat-v5 prompt contract.

Artifact	SHA-256
`model.safetensors`	`00d2c2b4b01ce0a13fbec5ba79f4fb843a751af2780e939ab431a092f1789207`
`training_manifest.json`	`22b90db42797c891bb69ac526ff237ef973be05827722ae83d2e3fdb794702ea`
`SmolGPT-Fables-v1-Q4_K_M.gguf`	`6d4d38e9075bcae3cfe59ed37c0acc3425ad31296de7530611e63628424a7c35`
GGUF quantization manifest	`87da452fd6df5658b8e9f07844a84993f656ae1b3f580e560eba018a37cc5a2f`
GGUF checksums file	`9ca968f9719327c941d2e1766cca7d0520a3732eefb9a92efc47cfb240bba761`
Core ML package tree	`ea250d4ed2a05d5dc0ad9a6f4b4fbbddf39fd3184963b784cea8f46e4f0d3ab3`
Core ML INT4 weights	`2d9e564d652618ee3ea7309b01998bdcfe775c0cc35adeb6fe9fb5d8c22a5fa3`

The GGUF file contains 218 tensors and is 1,055,609,376 bytes. It was converted with llama.cpp commit aff6eb6e7503538fec1532dec2f584bc7a4a4e4d.

Strict-suite diagnostic occurrences:

Diagnostic	Count
Incomplete causal resolution	17
Scene length	16
Character-role retention	1
Required detail	2
Scene heading	2
Unresolved ending	1

Character-name audit report SHA-256: 38a1ba15d6ae8545ae71a9953077d0626aba5c85ccf7f3844514bba04188f3a6.

</details>

Citation

If SmolGPT-Fables v1 is useful in your work, please cite the model release:

@misc{lozada2026smolgptfables,
  author = {Lukas Lozada Perez},
  title = {SmolGPT-Fables v1},
  year = {2026},
  howpublished = {Hugging Face model card},
  url = {https://huggingface.co/neonforestmist/smolgpt-fables}
}

For work that uses the underlying model or training data, also cite SmolLM2 and the smolgpt-markdown-stories dataset.

License

Apache-2.0. Review the SmolLM2-1.7B-Instruct model card alongside this one when assessing intended use and limitations.

Task: Text Generation
Library: transformers
Type: llama
License: apache-2.0
Languages: en
Created: Jul 11, 2026
Updated: Aug 29, 2026