Ikhou Dict S (MLC) is a WebGPU-ready, quantized build of ikhou/dict-s for in-browser inference with MLC-LLM / WebLLM. The source model is a Qwen/Qwen3-1.7B fine-tune for bilingual dictionary glossing.

Model Summary

Task: single-line dictionary gloss generation
Format: chat-based (system + user + assistant)
Quantization: q4f16_1 (4-bit weights, fp16 activations)
Target runtime: WebLLM (WebGPU)

Training Data (Source Model)

The source model ikhou/dict-s was trained on synthetic bilingual dictionary examples generated from multilingual web corpora (FineWeb-2 with optional FineWeb). The pipeline:

Extract sentences from multilingual corpora.
Select a word or short phrase from each sentence.
Sample a target language (cross-lingual by default).
Use a teacher LLM to generate a short gloss under a strict rubric.
Filter, de-duplicate, and write SFT JSONL with a system prompt, user prompt, and <final>...</final> assistant response.

See ikhou/dict-s for full training details.

Prompt Format

System prompt used during training:

text

You are a bilingual dictionary assistant.

Your job: given a word/phrase in context, output a SHORT dictionary-style gloss line.

Hard rules:
- Output EXACTLY ONE LINE and nothing else.
- No quotes, no bullets, no labels (no "Definition:", "Meaning:", etc).
- Do NOT repeat the original word/phrase in the output.
- Keep it short (ideally <= 120 characters).

Gloss rules:
- Output 1-4 translations/synonyms in the definition language, separated by ", ".
- Each gloss should be short (1-3 words). Prefer common, user-friendly glosses.
- Do NOT write full sentences. No trailing period.

French grammar hints (only if confident):
IMPORTANT: The French-only formatting hints below apply ONLY when the definition language is French (fr/fra).
If the definition language is NOT French, do NOT use nm./nf./adj./adv., do NOT add French tense notes, and do NOT add (pp).
- Noun: prefix with "nm." (masc) or "nf." (fem), then a space, then glosses.
  Example: nm. face
- Adjective: prefix with "adj.", then a space, then glosses.
  Example: adj. fragile, delicate
- Adverb: prefix with "adv.", then a space, then glosses.
  Example: adv. extremely, exceedingly
- Conjugated verb form: glosses, then add "(tense, subject)" in French.
  Example: came back, used to come back (imparfait, il)
- Past participle: glosses, then add "(pp)".
  Example: watched over, supervised (pp)

User prompt template:

text

Expression: "<selection>"
Context: <sentence>
Source language: <iso639-3> (<name>)
Definition language: <iso639-3> (<name>)

Return the single-line gloss now.

WebLLM Usage

javascript

import { MLCEngine } from "@mlc-ai/web-llm";

const engine = new MLCEngine();
await engine.reload("ikhou/dict-s-mlc-q4f16_1");

const messages = [
  { role: "system", content: "<system prompt above>" },
  {
    role: "user",
    content:
      "Expression: \"online\"\n" +
      "Context: He paid for the course online and started immediately.\n" +
      "Source language: eng (English)\n" +
      "Definition language: spa (Spanish)\n\n" +
      "Return the single-line gloss now.",
  },
];

const reply = await engine.chat.completions.create({
  messages,
  temperature: 0.0,
  max_tokens: 64,
});

console.log(reply.choices[0].message.content);

MLC Build Notes

This repository is produced from ikhou/dict-s using MLC-LLM:

bash

mlc_llm convert_weight /path/to/ikhou/dict-s \
  --quantization q4f16_1 \
  -o ./dict-s-mlc-q4f16_1

mlc_llm gen_config /path/to/ikhou/dict-s \
  --quantization q4f16_1 \
  --conv-template qwen2 \
  -o ./dict-s-mlc-q4f16_1

mlc_llm compile ./dict-s-mlc-q4f16_1/mlc-chat-config.json \
  --device webgpu \
  -o ./dict-s-mlc-q4f16_1/dict-s-q4f16_1-webgpu.wasm

If your MLC version uses a different conversation template name for Qwen3, replace qwen2 with the appropriate template.

Limitations

Outputs can be inaccurate or inconsistent with the rubric.
The model inherits biases from source corpora and the teacher model.
Specialized domains and low-resource languages may be weaker.

Acknowledgements

Base model: Qwen/Qwen3-1.7B. MLC runtime: MLC-LLM / WebLLM.