Downloads · 30 days
228
28% of all-time downloads
dikiyplayerpig/dpp-gpt-V2.1-base-90m
dpp-gpt-V2.1-base-90m 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
228
28% of all-time downloads
All-time downloads
806
Public
Repo size
2.1 GB
Likes
1
Public
Click a slice to open those files.
.gguf749 MB · 57%
From the Hugging Face model README
(🇺🇸 English / 🇷🇺 Русский)
⚠️ Note: This is a base foundation model. It has only undergone pre-training and has not been fine-tuned for general chat. For the instruction-following / chat version, please download dpp-gpt-V2.1-Flash-90m.
This is a microscopic foundation language model with 93M parameters, trained entirely from scratch. Despite its tiny size, it possesses native mathematical and translation capabilities embedded directly into its pre-training weights.
As a raw base model, it is highly sensitive to syntax. Mathematical and textual formatting was baked into the pre-training weights. Use strictly the following structures to get accurate results:
⚠️ Tip: This model is highly sensitive to the user's prompt formatting. To get a stable and correct translation, you must start your prompt with a capital letter and experiment with punctuation (sometimes adding or removing a period at the end changes the output).
<|im_start|>user
Переведи на английский: Я тебя люблю.<|im_end|>
<|im_start|>assistant
I love you.
To activate step-by-step math solving, use the [THINK] token:
<|im_start|>user
[THINK] 1523 - 659 + 234<|im_end|>
<|im_start|>assistant
(The model will continue by breaking down the calculation into Thousands, Hundreds, Tens, and Units).
⚠️ Внимание: Это базовая (foundation) модель. Она прошла только этап pre-training и не обучалась свободному ведению диалога. Если вам нужна готовая чат-версия, скачайте dpp-gpt-V2.1-Flash-90m.
Это базовая компактная языковая модель на 93М параметров, обученная полностью с нуля. Даже в сыром виде без файнтюнинга модель демонстрирует базовые навыки пошагового счета и перевода, зашитые напрямую в веса предобучения.
Так как это сырая базовая модель, она крайне чувствительна к синтаксису запроса. Если формат нарушен — логика генерации сломается. Разметка зашивалась в претрейн через формат ChatML, поэтому используйте строго следующие конструкции:
⚠️ Совет: Модель крайне чувствительна к формату вашего запроса. Чтобы получить стабильный и правильный перевод, пользователю необходимо начинать фразу с заглавной буквы, а также иногда экспериментировать с пунктуацией (наличие или отсутствие точки в конце запроса может поменять результат).
<|im_start|>user
Translate to russian: I love you.<|im_end|>
<|im_start|>assistant
Я люблю тебя.
Для активации пошагового решения используйте тег [THINK]:
<|im_start|>user
[THINK] 1523 - 659 + 234<|im_end|>
<|im_start|>assistant
(Модель сама продолжит текст, расписав вычитание и сложение по разрядам).
<!-- 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.