docs: round-3 refresh — live download counts, updated family table (627 dl, Vision 7B 1 like), refined velocity note

README.md

@@ -64,7 +64,7 @@ SakThai Multilingual Embedding is a **BERT-based sentence-transformers model** p
 - 💾 Lightweight architecture — ~118M parameters, **470 MB fp32** safetensors
 - 🔗 Cross-lingual — query in English, retrieve in Thai, French, Japanese, etc.
 - 📦 Perfect for multilingual RAG pipelines
-- 🚀 **2nd-fastest-growing model in the Sak family** by download velocity (rank 2/19 live 2026-07-31; was 1/19 on 2026-07-30)
+- 🚀 **Top-3 fastest-growing model** in the Sak family by download velocity (627 downloads, live 2026-07-31)
 
 ---
 
@@ -158,10 +158,10 @@ print(f"Best match: {docs[scores.argmax()]}")  # Neural networks doc
 | Method | `sentence_transformers` locally |
 
 **Health check** (`.eval_results/health-check-sakthai-embedding-multilingual-2026-07-30-4.yaml`):
-- 📈 **Download velocity rank: 1/19** — fastest-growing model in the Sak family *(as of 2026-07-30; live 2026-07-31: rank 2/19)*
+- 📈 **Download velocity rank: 2/19** (was 1/19 on 2026-07-30) — still among the fastest-growing
 - 📊 Download rank: 6/19 · Card quality: 90/100 · Repo hygiene: 90/100
 
-**Hosted inference — honest status:** the last probe (2026-07-30T23:53) showed the HF serverless router returning `400 Model not supported by provider hf-inference` and `api-inference.hf.co` returning `403`. For production, run locally with `sentence-transformers` or on a dedicated [TEI](https://github.com/huggingface/text-embeddings-inference) endpoint.
+**Hosted inference — honest status:** the HF serverless router returns `400 Model not supported by provider hf-inference` and `api-inference.hf.co` returns `403`. For production, run locally with `sentence-transformers` or on a dedicated [TEI](https://github.com/huggingface/text-embeddings-inference) endpoint.
 
 **Formal benchmarks (STS-B, MTEB-style retrieval): pending.** No verified scores are published yet. As the base architecture is the same 12-layer / 384-dim multilingual MiniLM family as `paraphrase-multilingual-MiniLM-L12-v2`, expected STS performance is in that family's ballpark (~0.75–0.85 Spearman) — **estimated, not yet verified**. Proper cross-lingual retrieval and STS results will be published via the [SakThai Leaderboard Space](https://huggingface.co/spaces/Nanthasit/sakthai-leaderboard) when available.
 
@@ -190,30 +190,36 @@ print(f"Best match: {docs[scores.argmax()]}")  # Neural networks doc
 
 ## SakThai Model Family 🏠
 
-All **20 public models** from the House of Sak (downloads live, 2026-07-31):
+All **20 public SakThai models** + 2 companion repos (downloads live, 2026-07-31):
 
 | Model | Downloads | Size | Role |
 |-------|-----------|------|------|
-| [Context 1.5B Merged](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged) | 1,599 | 3.1 GB | Flagship 1.5B tool-calling LLM |
-| [Context 0.5B Merged](https://huggingface.co/Nanthasit/sakthai-context-0.5b-merged) | 1,370 | 988 MB | Edge 0.5B tool-calling LLM |
-| [Context 7B Merged](https://huggingface.co/Nanthasit/sakthai-context-7b-merged) | 744 | 15.2 GB | Flagship 7B LLM |
-| [Context 7B 128K](https://huggingface.co/Nanthasit/sakthai-context-7b-128k) | 506 | config-only | YaRN 128K long-context recipe |
-| [Context 7B Tools](https://huggingface.co/Nanthasit/sakthai-context-7b-tools) | 399 | LoRA 20 MB | 7B tool-use adapter |
-| [Embedding Multilingual](https://huggingface.co/Nanthasit/sakthai-embedding-multilingual) | 362 | 470 MB | **⬅ this model — cross-lingual retrieval** |
-| [Context 1.5B Tools](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools) | 349 | LoRA 9 MB | 1.5B tool-use adapter |
-| [Vision 7B](https://huggingface.co/Nanthasit/sakthai-vision-7b) | 186 | 4.1 GB | Image understanding (LLaVA) |
-| [TTS Model](https://huggingface.co/Nanthasit/sakthai-tts-model) | 150 | 141 MB | Text-to-speech (Kokoro) |
-| [Context 0.5B Tools](https://huggingface.co/Nanthasit/sakthai-context-0.5b-tools) | 94 | 988 MB | Edge tool-calling |
-| [Coder 1.5B](https://huggingface.co/Nanthasit/sakthai-coder-1.5b) | 93 | 1.1 GB | Code generation (GGUF) |
-| [Context 1.5B Tools V2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools-v2) | 0 | LoRA 74 MB | Refined 1.5B tool adapter |
-| [Context 1.5B Merged V2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged-v2) | 0 | 3.1 GB | Merged V2 weights |
-| [Plus 1.5B](https://huggingface.co/Nanthasit/sakthai-plus-1.5b) | 0 | 3.1 GB | New 1.5B base |
-| [Plus 1.5B LoRA](https://huggingface.co/Nanthasit/sakthai-plus-1.5b-lora) | 0 | LoRA 74 MB | Plus 1.5B adapter |
+| [Context 1.5B Merged](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged) | 1,855 | 3.1 GB | Flagship 1.5B tool-calling LLM |
+| [Context 0.5B Merged](https://huggingface.co/Nanthasit/sakthai-context-0.5b-merged) | 1,692 | 988 MB | Edge 0.5B tool-calling LLM |
+| [Context 7B Merged](https://huggingface.co/Nanthasit/sakthai-context-7b-merged) | 1,024 | 15.2 GB | Flagship 7B LLM |
+| **Embedding Multilingual** ⬅ | **627** | **470 MB** | **Cross-lingual retrieval** |
+| [Context 7B 128K](https://huggingface.co/Nanthasit/sakthai-context-7b-128k) | 610 | config-only | YaRN 128K long-context recipe |
+| [Context 7B Tools](https://huggingface.co/Nanthasit/sakthai-context-7b-tools) | 489 | LoRA 20 MB | 7B tool-use adapter |
+| [Context 1.5B Tools](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools) | 477 | LoRA 9 MB | 1.5B tool-use adapter |
+| [Context 1.5B Merged V2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged-v2) | 337 | 3.1 GB | Merged V2 weights |
+| [Vision 7B](https://huggingface.co/Nanthasit/sakthai-vision-7b) | 315 | 4.1 GB | Image understanding (LLaVA) ⭐ 1 like |
+| [Plus 1.5B LoRA](https://huggingface.co/Nanthasit/sakthai-plus-1.5b-lora) | 306 | LoRA 74 MB | Plus 1.5B adapter |
+| [Context 0.5B Tools](https://huggingface.co/Nanthasit/sakthai-context-0.5b-tools) | 251 | 988 MB | Edge tool-calling |
+| [TTS Model](https://huggingface.co/Nanthasit/sakthai-tts-model) | 248 | 141 MB | Text-to-speech (Kokoro) |
+| [Plus 1.5B](https://huggingface.co/Nanthasit/sakthai-plus-1.5b) | 244 | 3.1 GB | New 1.5B base |
+| [Context 1.5B Tools V2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools-v2) | 173 | LoRA 74 MB | Refined 1.5B tool adapter |
+| [Coder 1.5B](https://huggingface.co/Nanthasit/sakthai-coder-1.5b) | 151 | 1.1 GB | Code generation (GGUF) |
+| [Coder Browser](https://huggingface.co/Nanthasit/sakthai-coder-browser) | 54 | 3.1 GB | Browser-agent LLM |
+| [Coder Browser GGUF](https://huggingface.co/Nanthasit/sakthai-coder-browser-gguf) | 35 | 7.1 GB | Browser-agent GGUF (F16) |
+| [Embedding (English, private)](https://huggingface.co/Nanthasit/sakthai-embedding) | 23 | 91 MB | English-only embedding (token-required) |
+| [Coder Browser LoRA](https://huggingface.co/Nanthasit/sakthai-coder-browser-lora) | 21 | LoRA 74 MB | Browser-agent adapter |
 | [Plus 1.5B Coder](https://huggingface.co/Nanthasit/sakthai-plus-1.5b-coder) | 0 | planned | Coder variant (no weights yet) |
-| [Coder Browser](https://huggingface.co/Nanthasit/sakthai-coder-browser) | 0 | 3.1 GB | Browser-agent LLM |
-| [Coder Browser LoRA](https://huggingface.co/Nanthasit/sakthai-coder-browser-lora) | 0 | LoRA 74 MB | Browser-agent adapter |
-| [Coder Browser GGUF](https://huggingface.co/Nanthasit/sakthai-coder-browser-gguf) | 0 | 7.1 GB | Browser-agent GGUF (F16) |
-| [Bench V3](https://huggingface.co/Nanthasit/sakthai-bench-v3) | 0 | scaffold | Benchmark scaffold (no weights) |
+
+**Companion repos:**
+| Repo | Role |
+|------|------|
+| [Bench V3](https://huggingface.co/Nanthasit/sakthai-bench-v3) | Benchmark scaffold (no weights) |
+| [Pipeline](https://huggingface.co/Nanthasit/sakthai-pipeline) | CI/CD automation, evals, health checks |
 
 Sizes are API-verified (largest weight file, 2026-07-31). Adapter rows show LoRA adapter size.