UnimeType Transliteration 2.0 0.8B — v2.6 (12-Language Offline IME Engine · GGUF Q4_K_M & Q8_0)

Current Release: v2.6 (dataset_v5.1 · 12 Languages / 13 Modes + Blind-Typing Typo Recovery) · Protocol: unimetype-convert-short-v3 (0 system-prompt tokens, 100% drop-in compatible with all Transliteration-2.0 clients)

UnimeType gives you one keyboard for all your languages — no switching keyboards across apps or mid-sentence. Keep a clean ASCII layout for single-key shortcuts in Figma or Blender, LaTeX commands in Overleaf, WASD controls in games, Terminal/IDE workflows, and switching between Slack, Mail, WhatsApp, WeChat, or LINE, then convert romanized text in-place only when you want native script.

UnimeType Transliteration 2.0 0.8B (v2.6) is a deterministic on-device input-method transliteration engine fine-tuned from unquantized BF16 Qwen/Qwen3.5-0.8B. It converts romanized or ASCII-typed input across 12 languages (13 output modes) — Chinese Pinyin, Japanese Romaji (natural & kana), Hindi Hinglish, Arabic Arabizi, Russian, Greek, Vietnamese, Spanish, French, Portuguese, German, and Italian — while keeping inline English terms, @handles, URLs, code spans, file paths, numbers, and line breaks untouched.

• 🚀 Launch Interactive Playground Space → (Inspect multi-clause presets or run live in-browser WebAssembly inference)
• ⌨️ Download the UnimeType Keyboard App → (One keyboard across macOS, Windows, Linux, iOS, Android & ChromeOS — zero keyboard switching across apps or mid-sentence)
• 📖 Evaluation Methodology & Local LM Studio Setup Guide →

---

Official v2.6 Model Family (0.8B · 4B · 9B)

Included GGUF Quantizations

---

What's New in v2.6

1. 12 Languages / 13 Output Modes with Zero System Prompt: Expands from 4 languages (zh, ja, hi, ar) to 12 languages (chinese, japanese natural & kana, hindi, arabic, russian, greek, vietnamese, spanish, french, portuguese, german, italian) using a single-line compact JSON user message and an empty system prompt (0 prompt-prefix overhead).
2. New 9B Flagship Offline Tier Surpasses Cloud on Core Benchmarks: Transliteration-2.0-9B reaches 92.09% strict accuracy on the 708-case v4-aligned suite (+1.27 pp ahead of DeepSeek V4.1 Flash with a ~2,800-token production system prompt) and 90.94% on Core-5 (+0.64 pp ahead of cloud), while matching cloud accuracy on Dogfood-30 (76.7%) and OOD-Unseen-20 probe repair (90.0%, 18/20).
3. Blind-Typing Adjacent-Key Typo Repair & Glossary Precision: Recovers realistic fast-typing transpositions (e.g., shujuuk → 数据库, yanchanghiu → 演唱会, yanuhuo → 验货), honors dynamic lexicon contact/brand entries without false-positive homophone hijacking, and cleanly emits UNIMETYPE_NO_ALTERNATIVE when closed-set reconvert alternatives are exhausted.
4. Unconditional Non-Thinking Chat Template: Ships with <|im_start|>assistant\n<think>\n\n</think>\n\n baked into chat_template.jinja across MLX, Safetensors, and GGUF so LM Studio, mlx-lm, and llama.cpp emit converted text on the very first token with zero reasoning-token latency.

---

Quickstart: unimetype-convert-short-v3 Compact JSON Protocol

Usage Note: This checkpoint is a specialized IME conversion engine, not an open-ended chatbot. Send a compact JSON object as the user message with empty System Prompt and temperature: 0, or pair LM Studio / Ollama directly with the UnimeType Keyboard App for system-wide Caps Lock / Convert key replacement in any app.

curl http://127.0.0.1:1234/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "UnimeType/Transliteration-2.0-0.8B-GGUF",
    "temperature": 0,
    "max_tokens": 256,
    "messages": [
      {
        "role": "user",
        "content": "{\"operation\":\"convert\",\"input\":\"mingtian 3pm he @alex review auth-service de PR #412, ranhou deploy dao staging\",\"enabled_languages\":[\"chinese\",\"english\"],\"primary_language\":\"chinese\"}"
      }
    ]
  }'

---

Evaluation Benchmarks (v2.6)

1. Six-Suite Head-to-Head Benchmark: Offline v2.6 (0.8B / 4B / 9B) vs. Cloud DeepSeek V4.1 Flash

All offline v2.6 models run with 0 system-prompt tokens (system_prompt = "", compact JSON input, temperature = 0), compared head-to-head against UnimeType's production cloud baseline (deepseek-v4.1-flash paired with the full ~2,800-token v30 production system prompt and boundary guards). Zero sentence or OOD probe overlap (0.00%) exists between training data and any of the 6 evaluation suites (1,975 held-out prompts total).

Boundary Safety: Across all 520 noisy mixed-script inputs in MST-Bench-520, all three v2.6 offline models (0.8B, 4B, 9B) recorded 0 protected-span corruptions (URL, @handle, #issue, code, file paths, and version tags preserved verbatim) and 100% pass on closed-set reconvert exhaustion (UNIMETYPE_NO_ALTERNATIVE).

2. Per-Language Strict Accuracy Across All 12 Languages / 13 Modes (1,573 Held-Out Cases)

---

Version History & Reproducible Revisions

This repository tracks the latest 2.x release on main while preserving immutable Git tags for every milestone:

• v2.6 (default / main): 12-language / 13-mode offline transliteration upgrade (dataset_v5.1), blind-typing typo recovery, dynamic lexicon distractor resistance, and closed-set UNIMETYPE_NO_ALTERNATIVE stopping.

  huggingface-cli download UnimeType/Transliteration-2.0-0.8B-GGUF --revision v2.6
  

• v2.1: 4-language multi-clause long-sentence upgrade (2.0-v4, max_seq_len=1024).

  huggingface-cli download UnimeType/Transliteration-2.0-0.8B-GGUF --revision v2.1
  

• v2.0: Initial 4-language short-protocol release (2.0-v3, max_seq_len=640).

  huggingface-cli download UnimeType/Transliteration-2.0-0.8B-GGUF --revision v2.0