Add training recipe/script (README.md, SHA256SUMS)

README.md

@@ -14,7 +14,9 @@ pipeline_tag: text-generation
 # TokenizerTest-32m-B (Polish research base model, tokenizer comparison — arm B)
 
 A small Polish **base** language model trained as arm **B** of a controlled tokenizer experiment. It is a research
-checkpoint for comparing tokenizers, not a model for use.
+checkpoint for comparing tokenizers, not a model for use. It is a Fabryka AI project (formerly SlayerLab).
+
+**Author:** Arkadiusz Słota (Fabryka AI), who designed and ran the experiment. Tokenizer of this arm: stubbornGuy.
 
 ## Companion model (tokenizer A/B experiment)
 
@@ -112,6 +114,8 @@ corresponding training checkpoint exactly (checked with `torch.equal` for every
 ## License
 
 **Weights: CC BY-SA 4.0** (the training text includes CC BY-SA parts of `SlayerLab/slayer-pl-8x3b`). Attribution:
-TokenizerTest-32m-B, Fabryka AI (SlayerLab), link to this repository; derivative weights under the same licence.
+TokenizerTest-32m-B, Arkadiusz Słota / Fabryka AI, link to this repository; derivative weights under the same licence.
 The tokenizer (`tokenizer.json`) was created by stubbornGuy and is released here under CC BY-SA 4.0 with his consent.
 Training data keep their upstream licences; see the dataset card of `SlayerLab/slayer-pl-8x3b`.
+
+*TokenizerTest — Fabryka AI. **Author: Arkadiusz Słota.** Tokenizer of arm B: stubbornGuy.*

SHA256SUMS

@@ -1,4 +1,4 @@
-a0e944099340c90223f7e02b166d317e87f699b7cf811a279c9e6bbb9d39f475  README.md
+8433989094d7c66227bdbca2887cf8e18aa94ad7537ba0bd3d79c5843114f268  README.md
 5a52c0867ea28be8ef8506f830d803ce98fcdea59fb654c8f4fe6ffa75c95e90  bpb_curve.json
 525c8d131963e6dc92f798bc602e4367e5a26fc274016ddb08b8a87b54f7fa51  config.json
 1a2fd327fc4069fe739e4152810acbfb66d23cf873e674d55dc85c839149d354  model.safetensors