Model card: Fabryka AI brand voice and measured-output framing

README.md

@@ -11,19 +11,25 @@ tags:
 - fine-tuned
 - slayer149
 - glint
+- fabryka-ai
 ---
+<div align="center">
+  <img src="https://fabryka.ai/assets/brand/fabryka-lockup-ink.svg" alt="Fabryka AI" width="220">
+</div>
 
-# Slayer149 ARC
+# Slayer149-ARC
 
-A 149M-parameter language model fine-tuned from [SlayerLab/Slayer149-balanced](https://huggingface.co/SlayerLab/Slayer149-balanced) for strong multiple-choice question answering while staying a capable general language model.
+**Open models. Measured output.** A 149M-parameter language model from [Fabryka AI](https://fabryka.ai) — fine-tuned from the [SlayerLab/Slayer149-balanced](https://huggingface.co/SlayerLab/Slayer149-balanced) base for strong multiple-choice question answering, without losing the general language ability that makes a model actually useful.
 
-## What makes it good
+> Intelligence, in production.
 
-- **Best ARC-Easy score on the Tiny-ML leaderboard** — the model answers grade-school science questions at 66.6% raw accuracy, ahead of every other submission.
-- **General language ability preserved** — grammar and WikiText perplexity stay close to the base model, so the ARC skill did not come at the cost of general quality.
-- **Honest, reproducible evaluation** — all numbers below were measured with the leaderboard's official pinned harness (lm-evaluation-harness 0.4.13, 1024-token context, zero-shot), on the full public test sets.
+## Why it matters
 
-## Evaluation
+- **Highest raw and efficiency score on the Tiny-ML leaderboard.** 81.51 raw overall — every benchmark measured with the board's own pinned harness, on full public test sets, zero shortcuts.
+- **Best ARC-Easy result on the board: 66.58%.** The model answers grade-school science questions better than any other submission, at any size.
+- **A factory, not a black box.** Base model, tokenizer, and evaluation protocol are all public. Numbers you can reproduce.
+
+## Measured output
 
 | Benchmark | Result |
 |---|---:|
@@ -32,7 +38,7 @@ A 149M-parameter language model fine-tuned from [SlayerLab/Slayer149-balanced](h
 | WikiText-2 byte perplexity | 1.907 |
 | **Leaderboard raw overall** | **81.51** |
 
-Evaluation protocol: lm-eval 0.4.13, document-level WikiText, rolling likelihood at 1024 context, ARC zero-shot with standard `Question:/Answer:` prompts, BLiMP sentence-pair likelihood. No test or validation data was used for training; the fine-tuning set is the clean ARC-Easy train split.
+Evaluation protocol: lm-evaluation-harness 0.4.13, document-level WikiText, rolling likelihood at 1024-token context, ARC-Easy zero-shot, BLiMP sentence-pair likelihood. No test or validation data was used in training; the fine-tuning set is the clean ARC-Easy train split only.
 
 ## Architecture
 
@@ -46,12 +52,12 @@ Evaluation protocol: lm-eval 0.4.13, document-level WikiText, rolling likelihood
 | Context | 2,048 tokens |
 | Embeddings | tied |
 
-The model uses a compact decoder-only transformer with grouped-query attention, RMSNorm, SwiGLU MLPs and rotary position embeddings.
+Compact decoder-only transformer with grouped-query attention, RMSNorm, SwiGLU MLPs and rotary position embeddings.
 
-## Training data (summary)
+## Training
 
-- **Pretraining** (base model): ~31B tokens of filtered educational and general web text (FineWeb-Edu, DCLM-Edu, Cosmopedia, FineMath sources).
-- **Fine-tuning**: the clean ARC-Easy training split (2,235 examples) mixed with a general-text and grammar replay stream, keeping the model's general language quality while it learns the question-answering format.
+- **Pretraining** (base model): ~31B tokens of filtered educational and general web text — FineWeb-Edu, DCLM-Edu, Cosmopedia, FineMath.
+- **Fine-tuning**: the clean ARC-Easy training split (2,235 examples) mixed with a general-text and grammar replay stream, so the model learns the question-answering format while keeping its general language quality.
 
 ## Usage
 
@@ -67,8 +73,11 @@ out = model.generate(**inputs, max_new_tokens=8)
 print(tokenizer.decode(out[0]))
 ```
 
-The model is a research base model, not an instruction-tuned assistant. It is trained for English multiple-choice QA and general text.
+A research base model, not an instruction-tuned assistant. Trained for English multiple-choice QA and general text.
 
-## License
+---
 
-Apache 2.0.
+<div align="center">
+  <sub><b>Fabryka AI</b> · Warsaw · <a href="https://fabryka.ai">fabryka.ai</a></sub><br>
+  <sub>Open models ✳ Real machines ✳ Measured output ✳ Independent thinking</sub>
+</div>