Instructions to use dikiyplayerpig/dpp-gpt-V2.1-base-260m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use dikiyplayerpig/dpp-gpt-V2.1-base-260m with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="dikiyplayerpig/dpp-gpt-V2.1-base-260m", filename="dpp-gpt-V2.1-260m-base-f16.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use dikiyplayerpig/dpp-gpt-V2.1-base-260m with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M # Run inference directly in the terminal: llama-cli -hf dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M # Run inference directly in the terminal: llama-cli -hf dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M
Use Docker
docker model run hf.co/dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use dikiyplayerpig/dpp-gpt-V2.1-base-260m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dikiyplayerpig/dpp-gpt-V2.1-base-260m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dikiyplayerpig/dpp-gpt-V2.1-base-260m", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M
- Ollama
How to use dikiyplayerpig/dpp-gpt-V2.1-base-260m with Ollama:
ollama run hf.co/dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M
- Unsloth Studio
How to use dikiyplayerpig/dpp-gpt-V2.1-base-260m with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for dikiyplayerpig/dpp-gpt-V2.1-base-260m to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for dikiyplayerpig/dpp-gpt-V2.1-base-260m to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for dikiyplayerpig/dpp-gpt-V2.1-base-260m to start chatting
- Atomic Chat new
- Docker Model Runner
How to use dikiyplayerpig/dpp-gpt-V2.1-base-260m with Docker Model Runner:
docker model run hf.co/dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M
- Lemonade
How to use dikiyplayerpig/dpp-gpt-V2.1-base-260m with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull dikiyplayerpig/dpp-gpt-V2.1-base-260m:Q4_K_M
Run and chat with the model
lemonade run user.dpp-gpt-V2.1-base-260m-Q4_K_M
List all available models
lemonade list
🧠 dpp-gpt v2.1 Base (260M)
(🇺🇸 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 version, please download dpp-gpt-v2.1-pro-260m.
This is a compact foundation language model with 259M parameters, trained entirely from scratch. Despite being a raw base model, it possesses strong native mathematical, tokenization, and translation capabilities embedded directly into its pre-training weights.
⚙️ Model Details
- Parameters: 259M
- Layers / Hidden Size / Heads: 20 / 1024 / 16
- Context Length: 4096 tokens
- Vocabulary Size: 16,384
- Type: Base (Pre-trained foundation model)
- Format: GGUF / PyTorch (.pth)
- License: Apache 2.0
📊 Pre-training Data
- Dataset Size: 11.8 Billion tokens (~45.5 tokens/parameter, batch size 512k).
- Languages: Balanced multi-lingual corpus consisting of Russian, English, and French data.
💡 Prompt Guide & Real Examples
As a raw base model, it is highly sensitive to syntax. Mathematical and textual formatting was baked into the pre-training using ChatML syntax. Use strictly the following structures to get accurate results:
🌍 Basic Translation
⚠️ 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). Also, cross-lingual prompts (e.g., asking in Russian to translate an English text into French) might yield less natural results.
<|im_start|>user
Переведи на английский: Я тебя люблю.<|im_end|>
<|im_start|>assistant
I love you.
🧮 Math Calculation (Chain-of-Thought)
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).
🔢 Counting Total Letters in a Word
<|im_start|>user
How many letters in "apple"?<|im_end|>
<|im_start|>assistant
Breaking down the word "apple" into letters:
a-p-p-l-e
a - 1
p - 2
p - 3
l - 4
e - 5
The word apple has 5 letters.
🎯 Counting Specific Letters
<|im_start|>user
How many letters "r" in "strawberry"?<|im_end|>
<|im_start|>assistant
Breaking down the word "strawberry" into letters:
s-t-r-a-w-b-e-r-r-y
s - 0
t - 0
r - 1
a - 1
w - 1
b - 1
e - 1
r - 2
r - 3
y - 3
Answer: 3
🔤 Spelling a Word Letter-by-Letter
⚠️ Important: When asking the model to simply spell a word, you MUST put a period . at the end of your prompt, otherwise the logic will break.
<|im_start|>user
Spell the word apple.<|im_end|>
<|im_start|>assistant
a-p-p-l-e
🇷🇺 Описание на русском
⚠️ 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-pro-260m.
Это базовая компактная языковая модель на 259М параметров, обученная полностью с нуля. Примечательно, что на этапе предобучения модель продемонстрировала мощные навыки счета, работы с текстом и базового перевода (в этой версии базовый математический аппарат работает даже точнее и стабильнее, чем в последующих SFT-модификациях).
⚙️ Детали модели
- Параметры: 259M
- Слои / Размерность / Головы: 20 / 1024 / 16
- Контекст: 4096 токенов
- Словарь: 16,384 токена
- Формат: GGUF / PyTorch (.pth)
- Лицензия: Apache 2.0
💡 Важное руководство по промптам (Prompt Guide)
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:
🌍 Базовый перевод
⚠️ 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 полностью поменять результат). Также ей тяжелее даются кросс-языковые задачи (например, просьба на русском перевести английский текст на французский).
<|im_start|>user
Translate to russian: I love you.<|im_end|>
<|im_start|>assistant
Я люблю тебя.
🧮 Математический расчет (Chain-of-Thought)
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: Milliers, Centaines, Dizaines, Unités).
🔢 Подсчет всех букв в слове
<|im_start|>user
Сколько букв в слове яблоко?<|im_end|>
<|im_start|>assistant
Разбивка слова "яблоко" на буквы:
я-б-л-о-к-о
я - 1
б - 2
л - 3
о - 4
к - 5
о - 6
В слове яблоко 6 букв.
🎯 Подсчет конкретной буквы
<|im_start|>user
Сколько букв "а" в слове абстракция?<|im_end|>
<|im_start|>assistant
Разбивка слова "абстракция" на буквы:
а-б-с-т-р-а-к-ц-и-я
а - 1
б - 1
с - 1
т - 1
р - 1
а - 2
к - 2
ц - 2
и - 2
я - 2
Ответ: 2
🔤 Побуквенный разбор слов
⚠️ Важно: При запросе на обычную разбивку по буквам, в конце промпта обязательно должна стоять точка .. Без неё модель может выдать некорректный результат.
<|im_start|>user
напиши слово яблоко по буквам.<|im_end|>
<|im_start|>assistant
я-б-л-о-к-о
- Downloads last month
- 74
2-bit
4-bit
6-bit
8-bit
16-bit