Instructions to use burgasdotpro/bgGPT-llama-3.1-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use burgasdotpro/bgGPT-llama-3.1-8B-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("burgasdotpro/bgGPT-llama-3.1-8B-GGUF", dtype="auto")

llama-cpp-python

How to use burgasdotpro/bgGPT-llama-3.1-8B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="burgasdotpro/bgGPT-llama-3.1-8B-GGUF",
	filename="bgGPT-llama-3.1-8B-GGUF.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use burgasdotpro/bgGPT-llama-3.1-8B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf burgasdotpro/bgGPT-llama-3.1-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf burgasdotpro/bgGPT-llama-3.1-8B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf burgasdotpro/bgGPT-llama-3.1-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf burgasdotpro/bgGPT-llama-3.1-8B-GGUF: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 burgasdotpro/bgGPT-llama-3.1-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf burgasdotpro/bgGPT-llama-3.1-8B-GGUF: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 burgasdotpro/bgGPT-llama-3.1-8B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf burgasdotpro/bgGPT-llama-3.1-8B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/burgasdotpro/bgGPT-llama-3.1-8B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use burgasdotpro/bgGPT-llama-3.1-8B-GGUF with Ollama:
```
ollama run hf.co/burgasdotpro/bgGPT-llama-3.1-8B-GGUF:Q4_K_M
```

Unsloth Studio

How to use burgasdotpro/bgGPT-llama-3.1-8B-GGUF 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 burgasdotpro/bgGPT-llama-3.1-8B-GGUF 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 burgasdotpro/bgGPT-llama-3.1-8B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for burgasdotpro/bgGPT-llama-3.1-8B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use burgasdotpro/bgGPT-llama-3.1-8B-GGUF with Docker Model Runner:
```
docker model run hf.co/burgasdotpro/bgGPT-llama-3.1-8B-GGUF:Q4_K_M
```

Lemonade

How to use burgasdotpro/bgGPT-llama-3.1-8B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull burgasdotpro/bgGPT-llama-3.1-8B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.bgGPT-llama-3.1-8B-GGUF-Q4_K_M

List all available models

lemonade list

Актуализиран 19.01.2025

Changed training params
Continued pretraining
Уикипедиа 20%

Актуализиран 18.01.2025

Changed training params
Updated wiki dataset
Updated synthetic dataset
Continued pretraining
Уикипедиа 5%

Актуализиран 15.01.2025

Changed training params
Updated dataset
Continued pretraining
Уикипедиа 10%

Актуализиран 10.01.2025

Changed training params
Continued pretraining
Уикипедиа 10%

Актуализиран 06.01.2025

Changed training params
Continued pretraining
Уикипедиа 10%

Актуализиран 03.01.2025

Continued pretraining
Уикипедиа 20%

Актуализиран 01.01.2025

Continued pretraining
Уикипедиа 10%

Актуализиран 30.12.2024

по-дълги отговори
по-подробна информация
по-дълбоко обучение
~2500 реда синтетични данни

~~Първите резултати, които не са лоши...~~ ~~Засега е тренирана върху моят малък датасет с 2000 реда синтетични данни (формат: въпрос-отговор)~~

Пример на работа

Въпрос:

Как компания Burgas Professionals е свързана с ПГМЕЕ?

Отговор:

Компания "Burgas Professionals" поддържа тесни връзки с Професионалната гимназия по мехатроника и електроенергетика (ПГМЕЕ) в Бургас. Тези връзки включват партньорства, лекции и обучителни програми, които помагат на учениците да развият умения в областта на информационните технологии и IT управление. Основната цел е да се осигури на младото поколение достъп до актуална информация и практически опит, който ще ги направи готови за бъдещата работна среда. Чрез тези партньорства ПГМЕЕ и Burgas Professionals работят заедно за развитие на технологиите в региона и за подготовка на нови поколения IT специалисти.

Тази llama модела тренирана 2 пъти по-бързо с помоща на Unsloth и TRL библиотеката на Huggingface.

Uploaded model

Developed by: burgasdotpro
License: apache-2.0
Finetuned from model : unsloth/meta-llama-3.1-8b-bnb-4bit

Downloads last month: 101

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

burgasdotpro
/

bgGPT-llama-3.1-8B-GGUF

Пример на работа

Въпрос:

Отговор:

Uploaded model

Dataset used to train burgasdotpro/bgGPT-llama-3.1-8B-GGUF

Collection including burgasdotpro/bgGPT-llama-3.1-8B-GGUF

GGUF