docs: improve model card — verified notes, serving table, reproducibility, family table

docs: improve model card with usage, benchmark table, limitations, citation

chore: enrich model-index with SakThai Bench v2 verified results

Improve model card: add model-size badge, refresh family-table downloads, update coverage wording to 26 public models.

Fix family coverage wording: 22 -> 26 public models; add model-size badge.

Improve model card: model-size badge, refreshed family table row download counts, expanded coverage wording.

docs: unify usage section, add Limitations, improve tool-calling snippet

docs: verify internal benchmark + add prompt template to coder-1.5b card

docs: remove duplicated Internal SakThai Coding Suite heading/table

docs: fix duplicated Benchmarks section after live eval insert

docs: add live local eval snapshot to Benchmarks

docs: add How to Use, Limitations, Citation; repair front-matter sections

docs: add usage snippet, clarify benchmarks, tighten evaluation section

docs: add Tool-calling example section to README

docs: promote benchmark eval to model card

docs: repair TTS badge link and verify Model Description section

docs: add Model Description, fix badge link, improve metadata

Upload README.md with huggingface_hub

chore: add dataset cross-link sakthai-combined-v10

fix: clean model-index metric names for HF validator compatibility

docs: improve model card — tool-calling XML example, expanded limitations, honest benchmark caveats

Upload README.md with huggingface_hub

docs: improve model card — Model Description, Usage, Benchmarks, Limitations, Citation; honest base-model refs + internal suite; widget YAML normalized

fix: include sakthai-bench-v2 and irrelevance-supplement in datasets YAML; update Training section

Update family count: 20 public models -> 22 public models

docs: GGUF-only metadata (library_name gguf), honest inference section, ecosystem status refresh, housekeeping cleanup-done; .gitattributes junk entries removed

Audit fix: family collection count 20 public models / 15 datasets / 4 Spaces (39 items, bench-v3 joined)

Update collection footer: 13 datasets -> 14 (sakthai-combined-v11 joined the family collection)

fix(crosslinks): correct stale Coder Browser GGUF size 6.6->7.1 GB (actual 7,111,560,032 B); remove phantom private/internal dataset claim (combined-v8 & cycle-bench 404)

docs: refresh collection/family counts to live state (19 public models, 13 datasets, 4 Spaces)

docs: enrich coder-1.5b card — 19-model family table with live downloads + verified sizes, fix stale embedding size (80MB->470MB), architecture table, llama-cpp-python example, honest single-trial verified:false, ecosystem status + repo hygiene note

Fix cross-link: replace dead sakthai-vision-demo Space (404) with sakthai-web-agent

Update model card: fix model-index format, add source metadata, refresh dataset counts

Update model card: add downloads badge, benchmarks, code examples, YAML tags

Update model card: refresh download counts, add coding benchmarks and usage examples

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Fix model count: 11→12 public (v2 added)

docs: add origin story + CTA section for narrative consistency across House of Sak cards

Fix coder-1.5b card: remove dead Rising Stars links, add 0.5b-tools cross-link, fix ecosystem count

Upload README.md with huggingface_hub

fix: model count 12→11 (actual from HF API)

fix: update model family count from 13 to 12

fix: correct model count 14→13, remove deprecated English embedding reference

fix: align family count to 14 models + add signature tagline

docs: align card to lean standard — live downloads badge, single canonical family table, drop funnel sections and stale counts

docs: align card to lean standard — live downloads badge, single canonical family table, drop funnel sections and stale counts

fix: replace broken shields.io/endpoint badge with working static badge (70 dl)

Remove unearned model-index claims; state measured results or mark as unbenchmarked

Overhaul coder-1.5b card: add growing ecosystem section, expand family table, fix counts 12→13 models, 5→6 datasets