mist-tg-0.3b generates short chat titles from a user's first message.
Fine-tuned from google/byt5-small (~300M, byte-level seq2seq) on
SupraLabs/chat-titles-filtered-115K.
Production-ready for English — trained end-to-end on real English chat
messages and titles, no language tag or special formatting needed.
Also usable on Latin-script languages as a side effect of byte-level,
same-alphabet transfer — not trained on non-English targets, but Latin
script's byte-level overlap with English lets same-language title
extraction work reasonably well in practice for many Latin-alphabet
languages (see Benchmarks and Known Limitations).
Not reliable for non-Latin scripts (CJK, Hangul, Devanagari, Ethiopic,
etc.) — see Known Limitations for why, and what would need to change to fix
it.
1from transformers import AutoTokenizer, T5ForConditionalGeneration
23tok = AutoTokenizer.from_pretrained("olaverse/mist-tg-0.3b")4model = T5ForConditionalGeneration.from_pretrained("olaverse/mist-tg-0.3b")56message ="My laptop keeps freezing every time I open more than five browser tabs, any idea why?"7inputs = tok(message, return_tensors="pt", truncation=True, max_length=256)8output_ids = model.generate(**inputs, max_new_tokens=32)9print(tok.decode(output_ids[0], skip_special_tokens=True))10# Laptop Freezing Impact
No prompt template or language tag required — pass the raw message directly.
📊 Benchmarks
Cross-language qualitative check (25 languages, hand-written chat-style
messages on the same topic, no ground truth — informal check, not a scored
benchmark): same-language title extraction worked for roughly 17-19 of 25
languages tested, concentrated almost entirely among Latin-script languages
(English, French, German, Dutch, Vietnamese, Indonesian, Yoruba, Igbo, Hausa,
Swahili, Zulu, Xhosa, Shona, Somali, Afrikaans). All four non-Latin-script
languages tested (Japanese, Korean, Hindi, Amharic) failed to produce
same-language output, instead generating unrelated English text.
