Downloads · 30 days
56
9% of all-time downloads
dikiyplayerpig/dpp-gpt-v2.0-flash-135m
dpp-gpt-v2.0-flash-135m 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
56
9% of all-time downloads
All-time downloads
614
Public
Repo size
1.4 GB
Likes
0
Public
Click a slice to open those files.
.gguf682 MB · 100%
From the Hugging Face model README
(🇺🇸 English / 🇷🇺 Русский)
This is a compact language model trained from scratch on the Llama 3 architecture. The model is part of the dpp-gpt small language models (SLM) family.
The model was pre-trained on a corpus of ~6.93 Billion tokens. The dataset is a carefully balanced mix of languages, code, and reasoning data:
The model is optimized for low-end devices and smartphones. It can be easily run using:
LM Studio
llama.cpp
KoboldCPP
recommended temperature: 0.3
recommended top-k: 10
Standard Prompt Format (ChatML):
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Reasoning Mode Prompt:
<|im_start|>user
[THINK] {prompt}<|im_end|>
<|im_start|>assistant
Это компактная языковая модель, обученная с нуля (from scratch) на архитектуре Llama 3. Модель является частью семейства малых языковых моделей (SLM) проекта dpp-gpt.
Модель обучалась на корпусе объемом ~6.93 млрд токенов. Состав датасета был сбалансирован для получения базовых навыков языка, логики и программирования:
Модель оптимизирована для работы на слабых устройствах и телефонах. Она легко запускается через:
LM Studio
llama.cpp
KoboldCPP
рекомендованная temperature: 0.3
рекомендованный top-k: 10
Стандартный формат промпта:
<|im_start|>user
{промпт}<|im_end|>
<|im_start|>assistant
Режим размышления:
<|im_start|>user
[THINK] {промпт}<|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.