A small chill-friend chatbot. This is the casual-conversation version of TinyBrainBot-360M-A75M-v5.1-Instruct: same 383M-parameter mixture-of-experts model (24 experts per layer, 4 active, so 75M parameters work per token), trained a bit more to talk like a laid-back friend instead of an assistant. Short replies, goes along with how you talk, asks back, says bye when you do, and knows it’s an AI called TinyBrainBot, made by nkthebass. It loads as a standard MixtralForCausalLM. 33 unedited conversations, mistakes included, are in conversationsamples.md`. The Chat version gives up a little formal instruction following (IFEval) for casual conversation; knowledge benchmarks stay the same. Chat arithmetic (2- to 4-digit, 25 problems per kind) is 100% on every kind. GGUF (llama.cpp, LM Studio, Jan, Ollama): Q80 (409 MB), Q4K_M (239 MB) or F16 (768 MB). The chat template is embedded, chats tokenize exactly like transformers, and greedy F16 output matches transformers token for token. Recommended sampling: temperature 0.4, top-p 0.9, repetition penalty 1.15. The —logit-bias flags block the byte tokens that start every emoji (the tokenizer has no emoji pieces). If a reply starts with a …
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: nkthebass
Теги: gguf, mixtral, tinybrainbot, mixture-of-experts, moe, small-language-model, from-scratch, chat
Лайков: 3 | Загрузок: 619
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
