Fix pipeline_tag; add accuracy chart, GitHub link, PDF report

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+accuracy_by_category.png filter=lfs diff=lfs merge=lfs -text
+nano-dates-report.pdf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -9,7 +9,7 @@ tags:
   - structured-output
   - byte-level
   - from-scratch
-pipeline_tag: text2text-generation
+pipeline_tag: text-generation
 library_name: safetensors
 ---
 
@@ -31,6 +31,11 @@ The model is given a **reference date** (`today`) at the start of the prompt, so
 relative phrases ("tomorrow", "in 3 weeks") are computable from the input alone —
 it never needs a wall clock.
 
+**Code, training, and reproduction:** https://github.com/vukrosic/nano-dates
+(self-contained `train.py` / `eval.py` / data generator / tests + a PDF report).
+
+![accuracy by category](accuracy_by_category.png)
+
 ## Why this exists
 
 A 1M-parameter model can't be a general assistant, but it *can* completely nail a

nano-dates-report.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68cee35c5950926f249cdb4728ca4c7a3a85d212be275d54d3e93c666ff71c58
+size 162814