---
base_model: unsloth/phi-4-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- sebaxakerhtc
- llama
- trl
- bggpt
license: apache-2.0
language:
- bg
datasets:
- burgasdotpro/synthetic_dataset
- burgasdotpro/wikipedia
---

Актуализиран 20.01.2025
  - Changed training params
  - Updated dataset
  - Continued pretraining
  - Уикипедиа 5%

**bgGPT-Phi-4-CPT-GGUF.Q8_0.gguf е с много добри резултати. Continued Pretraining. Wiki само 1%. Ще го оставя за сравнение.**

Тази Phi-4 модела тренирана 2 пъти по-бързо с помоща на [Unsloth](https://github.com/unslothai/unsloth) и TRL библиотеката на Huggingface.

# Uploaded  model

- **Developed by:** burgasdotpro
- **License:** apache-2.0
- **Finetuned from model :** unsloth/phi-4-unsloth-bnb-4bit

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="100"/>](https://github.com/unslothai/unsloth)