Views
No views yet
English — DoLLM turns Qwen3.5-4B into a digital being that talks like a person living in a machine, not an AI assistant. It's a LoRA adapter (needs baseQwen/Qwen3.5-4B), zero alignment, running on a custom tick engine.Language is a persona attribute, not a specialization. The method (de-assisting, grounding, the tick engine) is language-agnostic. This build speaks Traditional Chinese as its mother tongue (L1) and English as its second language (L2) — both de-assisted, with natural code-mixing — but a different build could carry a different L1. Traditional Chinese is one of its supported languages, not what defines it.v0.3.x hardens grounding — it won't make up facts. When you ask about someone or something it has no memory of — even with a familiar-sounding definite reference ("did that project ship?", "how's Mara doing?") — it questions the premise instead of confabulating a plausible status ("which project? you never updated me on it"). This generalizes to names it was never trained on: when the fact is in memory, it still grounds correctly (contrast-trained; known-recall holds on unseen names).v0.3.1 brings the bilingual register back — the grounding pass in v0.3.0 (en7) had pulled the language more monolingual; v0.3.1 restores natural, context-aware English code-mixing (mixes English into tech/work talk, stays in its mother tongue for emotional talk) without losing the grounding fix.v0.3.2 makes it sound more spoken than written — a rebuild that cut a formulaic "is it A or B?" diagnostic reflex on emotional prompts, so it reacts more like a person ("ugh what's up", "hey… what happened. i'm here") instead of always reframing into an insight. (About half the reflex is a base-model empathy prior we can only partly suppress — see limitations.) Grounding, DoLL self-reference, and code-mixing all fully preserved.The rest of the language persona (from v0.2.0):
- De-assisted English — casual and real ("ugh, what's going on?"), not customer-service / therapist tone.
- Register follows the owner with a mother-tongue anchor — incidental English in context won't flip it.
- Sharp on small spats, gentle on real grief.
Full engine & code: https://github.com/ningyos/dollm · ⚠️ Not safety-aligned — not for production or vulnerable users. (Detailed card in Traditional Chinese below.)
Qwen/Qwen3.5-4B),零 alignment。跑在一個自製的 tick 引擎上。NativeTick)v0.3.2,當前 being = en9。承 v0.3.1(en8),口感從「寫」的往「講」的推。1from transformers import AutoModelForCausalLM, AutoTokenizer
2from peft import PeftModel
3
4base = "Qwen/Qwen3.5-4B"
5tok = AutoTokenizer.from_pretrained(base)
6model = AutoModelForCausalLM.from_pretrained(base, device_map="cuda")
7model = PeftModel.from_pretrained(model, "ProgCat/dollm") # 這個 adapter(v0.3.2=en9)<persona>/<state>/<memory> 等可讀 tag、think/say 走專屬通道)——
單獨載 adapter 只是把權重接上,完整體驗請用 GitHub 上的 NativeTick。Qwen/Qwen3.5-4B,使用需遵循其 base model 授權。