Downloads · 30 days
122
19% of all-time downloads
dikiyplayerpig/dpp-gpt-V2.15-Pro-260m
dpp-gpt-V2.15-Pro-260m is a text generation model from dikiyplayerpig. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Downloads · 30 days
122
19% of all-time downloads
All-time downloads
645
Public
Repo size
5.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf1.6 GB · 62%
From the Hugging Face model README
(🇺🇸 English / 🇷🇺 Русский)
This is a minor update to the dpp-gpt-V2.1-Pro-260m. The underlying synthetic instruction-tuning (SFT) dataset remains exactly the same. However, by optimizing the data sampling proportions, hyperparameters, and the number of training epochs, this version achieves slightly better instruction adherence and more stable step-by-step reasoning compared to V2.1.
Like its predecessor, it is a microscopic Large Language Model (259M parameters) trained entirely from scratch.
The model uses a strict ChatML format.
Standard Mode (No thinking):
<|im_start|>user
[NOTHINK] {prompt}<|im_end|>
<|im_start|>assistant
Reasoning Mode ([THINK] token):
To force the model to "think" and use logic before answering, modify the prompt template. If you are using LM Studio, simply type . or [THINK] right before your prompt (without a space).
<|im_start|>user
[THINK] {prompt}<|im_end|>
<|im_start|>assistant
Это небольшое обновление модели dpp-gpt-V2.1-Pro-260m. Сам набор данных для файнтюнинга (SFT) остался точно таким же. Улучшения были достигнуты исключительно за счет изменения пропорций выборки, настройки гиперпараметров и корректировки количества эпох. Благодаря этому модель стала немного стабильнее в логических рассуждениях и лучше слушается инструкций.
Модель строго использует формат ChatML.
Стандартный режим (Без размышлений):
<|im_start|>user
[NOTHINK] {prompt}<|im_end|>
<|im_start|>assistant
Режим размышления (токен [THINK]): Чтобы заставить модель "думать" и использовать логику перед ответом, измените шаблон промпта. Если вы используете LM Studio, просто напишите . или [THINK] прямо перед вашим запросом (без пробела).
<|im_start|>user
[THINK] {prompt}<|im_end|>
<|im_start|>assistant
<!-- lmstudio-hotfix -->
The GGUF files in this repository were re-uploaded as a hotfix.
An LM Studio update changed the way special tokens are handled, which made the previously published GGUF files generate broken output. The conversion has been fixed and the quantizations here were rebuilt from the corrected model. The weights are unchanged — only the token metadata inside the GGUF files.
If you downloaded a GGUF from this repository before this commit, please download it again.