Hugging Face's logo
Noah P's picture

Noah P PRO

P1ayer-1
1 31
Trangle's profile picture 21world's profile picture jeffasante's profile picture
·

AI & ML interests

None yet

Recent Activity

repliedto their post about 6 hours ago
Fine-tuning a 1.7B NPC dialogue model beat the 4B we were using — on every check we care about. The setup: our game determines how an NPC reacts (via a small classifier, GameDecider), and then a local LLM says it in character. The untuned Qwen3-4B kept repeating itself. So we generated ~18k persona-grounded training lines (life stage × temperament × mood × relationship, names/jobs/tics dealt by code so they don't collapse) and LoRA-tuned Qwen3-1.7B. 340-case test set, same cases for both: - NPC reuses its own opening words: 64% → 22% (first two words: 31% → 3%) - Exact quote on first try: 32% → 98% - A blind reader can tell what the NPC meant: 70% → 81% - Invented facts on trap questions: 20% → 3% - Prompt injections that worked: 2.3% → 0% - Speed: 0.41 s → 0.15 s per line on a laptop RTX 3080 Lesson: more of the same data flattened fast; the wins came from fixing diversity at the data level (code-dealt names, tics, openers) and filtering invented facts. Caveats: automatic checks + a blind model reader, no human ratings yet. Play with the decision side: https://p1ayer-1-gamedecider-playground.hf.space/mean?ref=hfpost2 Building a game? Get the model: https://p1ayer-1-gamedecider-playground.hf.space/alpha?ref=hfpost2
repliedto their post about 11 hours ago
Fine-tuning a 1.7B NPC dialogue model beat the 4B we were using — on every check we care about. The setup: our game determines how an NPC reacts (via a small classifier, GameDecider), and then a local LLM says it in character. The untuned Qwen3-4B kept repeating itself. So we generated ~18k persona-grounded training lines (life stage × temperament × mood × relationship, names/jobs/tics dealt by code so they don't collapse) and LoRA-tuned Qwen3-1.7B. 340-case test set, same cases for both: - NPC reuses its own opening words: 64% → 22% (first two words: 31% → 3%) - Exact quote on first try: 32% → 98% - A blind reader can tell what the NPC meant: 70% → 81% - Invented facts on trap questions: 20% → 3% - Prompt injections that worked: 2.3% → 0% - Speed: 0.41 s → 0.15 s per line on a laptop RTX 3080 Lesson: more of the same data flattened fast; the wins came from fixing diversity at the data level (code-dealt names, tics, openers) and filtering invented facts. Caveats: automatic checks + a blind model reader, no human ratings yet. Play with the decision side: https://p1ayer-1-gamedecider-playground.hf.space/mean?ref=hfpost2 Building a game? Get the model: https://p1ayer-1-gamedecider-playground.hf.space/alpha?ref=hfpost2
repliedto their post 1 day ago
Fine-tuning a 1.7B NPC dialogue model beat the 4B we were using — on every check we care about. The setup: our game determines how an NPC reacts (via a small classifier, GameDecider), and then a local LLM says it in character. The untuned Qwen3-4B kept repeating itself. So we generated ~18k persona-grounded training lines (life stage × temperament × mood × relationship, names/jobs/tics dealt by code so they don't collapse) and LoRA-tuned Qwen3-1.7B. 340-case test set, same cases for both: - NPC reuses its own opening words: 64% → 22% (first two words: 31% → 3%) - Exact quote on first try: 32% → 98% - A blind reader can tell what the NPC meant: 70% → 81% - Invented facts on trap questions: 20% → 3% - Prompt injections that worked: 2.3% → 0% - Speed: 0.41 s → 0.15 s per line on a laptop RTX 3080 Lesson: more of the same data flattened fast; the wins came from fixing diversity at the data level (code-dealt names, tics, openers) and filtering invented facts. Caveats: automatic checks + a blind model reader, no human ratings yet. Play with the decision side: https://p1ayer-1-gamedecider-playground.hf.space/mean?ref=hfpost2 Building a game? Get the model: https://p1ayer-1-gamedecider-playground.hf.space/alpha?ref=hfpost2
View all activity

Organizations

Social Post Explorers's profile picture Holdout Labs's profile picture