Nanthasit/sakthai-context-7b-128k

Add cron metadata eval result for 7b-128k

docs: improve verified eval reference and bench metadata

docs: fix cross-link in README.md

fix: restore model card from corrupted state

cron: add eval snapshot cron-eval-sakthai-sakthai-context-7b-128k-20260801T021537Z.yaml

Upload .eval_results/health-sakthai-context-7b-128k-2026-08-01.yaml with huggingface_hub

audit: remove private embedding link + restore omitted family rows

cron: refresh 128k card — repo contents, ecosystem status, live family table (2026-08-01)

eval-updater: add metadata eval 2026-07-31T19:18:14Z

eval-updater: add metadata eval 2026-07-31T19:10:26Z

chore(card): add model-index, benchmarks, how-to-use, limitations, citation, inference widget

cron: add eval result #32 for context-7b-128k (metadata_cron)

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

Improve model card: update live download counts, add datasets frontmatter (emozilla/pg19), add Citation section, add Model Card Benchmarks table, add Quick Example with 128K usage snippet, add arXiv badge, refresh family table with live stats

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

health-check: sakthai-context-7b-128k 2026-07-31 (score 96, no fixes needed)

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

Upload README.md with huggingface_hub

cron: add eval result #1 for sakthai-context-7b-128k (metadata_cron, YaRN 128K config)

Upload README.md with huggingface_hub

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

Fix model count: 11→12 (v2 added)

cron: add sibling datasets table + Rising Stars cross-promotion (0-dl assets)

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

docs: add origin story and CTA to 7b-128k model card

fix: update model family count from 13 to 12

docs: add House of Sak narrative to 7b-128k model card

fix: correct model count 14→13 (deprecated English embedding no longer public)

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: Remove dead links to 8 deleted v2/experimental repos, correct model count 18->12

Overhaul card: add full ecosystem cross-promotion (18 models, 8 datasets, 3 Spaces)

Remove GSM8K claim for a repo that has never contained weights

State clearly that this is a config-only repo with no weights; show how to apply YaRN

Upload .eval_results/quality.yaml with huggingface_hub

Delete .eval_results/text-quality.yaml with huggingface_hub

Upload .eval_results/quality.yaml with huggingface_hub

Upload .eval_results/text-quality.yaml with huggingface_hub

Lean rewrite: dynamic download badge, single family table, honest evals, story→profile

Fix card: remove dead paper link, drop unverified model-index claims, dedupe tables, fix stray markdown

cron: enrich 7B-128K card - fix stale counts, add Low-Download Gems, add irrelevance-supplement

fix: refresh all download counts, add missing models to family table

Enrich model card: dynamic badge + Pipeline Integration + updated counts

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Add House of Sak branding header + family badges

Add family cross-link table + conversational tag

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub