Update README.md
Browse files
README.md
CHANGED
|
@@ -42,7 +42,7 @@ It is a compact character-level bigram model — no transformer weights,
|
|
| 42 |
just transition probabilities. Runs entirely in the browser or on any machine with Python 3.8+.
|
| 43 |
|
| 44 |
This model was produced with **Micro Distillery v2.5** — a single-file HTML PWA that fetches open corpora, trains a toy bigram, applies optional NLP fan-out polish, and exports a HuggingFace-ready `.zip` bundle. Includes the **Jev Code Nous** deterministic API layer for coding-focused token prediction (harness only).
|
| 45 |
-
|
| 46 |
## CHANGE LOG — Updated 2026-10-25
|
| 47 |
|
| 48 |
Maintenance + feature release for the browser trainer. Bundle format remains `mD-v2` / `2.5.0`. No breaking changes to the exported artifact schema.
|
|
|
|
| 42 |
just transition probabilities. Runs entirely in the browser or on any machine with Python 3.8+.
|
| 43 |
|
| 44 |
This model was produced with **Micro Distillery v2.5** — a single-file HTML PWA that fetches open corpora, trains a toy bigram, applies optional NLP fan-out polish, and exports a HuggingFace-ready `.zip` bundle. Includes the **Jev Code Nous** deterministic API layer for coding-focused token prediction (harness only).
|
| 45 |
+
Available for download in the repo folder.
|
| 46 |
## CHANGE LOG — Updated 2026-10-25
|
| 47 |
|
| 48 |
Maintenance + feature release for the browser trainer. Bundle format remains `mD-v2` / `2.5.0`. No breaking changes to the exported artifact schema.
|