fumetodev/Hy-MT2-1.8B-JP-Manga-Finetune-v2-GGUF

Hy-MT2-1.8B-JP-Manga-Finetune-v2

This repo contains a version of the Hy-MT2-1.8B model that's been finetuned further for more accurate and natural sounding English translations of conversational/manga-style Japanese than the v1 finetune. Note this improvement likely came at the cost of translation quality for other language pairs that aren't Japanese to English.

Scope: this is a manga finetune

The training data is Japanese manga dialogue, and the model is built for translating manga — short, self-contained lines, translated one line at a time.

It will still translate other Japanese, but the finetune's biases follow its training domain, and they are worth knowing before deploying it on something else:

• —Fragmentary input gets completed rather than translated. Manga lines are short and elliptical while the training targets are complete, natural sentences, so the model learned to produce a whole utterance from a partial one. Give it truncated input — ASR output, a cut-off caption, a mid-sentence chunk — and it will confidently finish the thought instead of translating only what it was given. Outside the intended domain this is the most common failure.
• —Real-world proper nouns are weaker than in the base model. The names in the training data are fictional character names. For public figures, places and brands, stock Hy-MT2-1.8B is often more reliable.
• —Technical, business and other specialist terminology is not covered. Nothing in the training data teaches it.
• —Register leans conversational. Formal or expository source text comes out more casual than the source warrants.

If your input is continuous speech or long-form prose rather than discrete lines of dialogue, A/B it against stock Hy-MT2-1.8B before committing — this finetune does not dominate the base model everywhere.

Prompting

The finetune was trained with a short terminology block in the prompt: a few reference translations, written in the target language, placed ahead of the Japanese text to translate. It does attend to that block — ablating it measurably lowered quality (about 1 chrF++, with some conspicuous individual failures). This is a real difference from stock Hy-MT2-1.8B, which largely ignores terminology injected into the prompt. If you have a glossary, putting it in the prompt is worthwhile here.

The instruction frame around that block was English during training; only the terminology block itself is written in the target language.

Sampling

Recommended: temperature 0.15, top_k 20, top_p 0.6, repeat_penalty 1.05, min_p 0, with the sampler chain ordered penalties → topk → topp → temperature.

Higher temperatures measured worse. The cost is mostly variance rather than average quality, and that variance shows up as occasional invented content — so if you are seeing hallucination, lower the temperature before anything else. Note that llama.cpp and llama-server default min_p to 0.05; set it to 0 to match the conditions this model was evaluated under.