Skip to main content
ToolPotion
AI Advisor
Submit a Tool (Free)

BgGPT-Gemma-2-27B-IT-v1.0

No ratings yet
AI ModelsAI Models & LLMsOpen source · Web

BgGPT-Gemma-2-27B-IT-v1.0 is a Bulgarian language model developed by INSAIT, based on Google's Gemma 2 27B. It excels in Bulgarian cultural and linguistic tasks while retaining English capabilities.

View Model
Share
View Model
Share

Description

BgGPT-Gemma-2-27B-IT-v1.0 is a state-of-the-art Bulgarian language model created by INSAIT, part of Sofia University St. Kliment Ohridski. Built on Google's Gemma 2 27B models, it was pre-trained on approximately 100 billion tokens, with 85 billion in Bulgarian. This extensive pre-training, using the Branch-and-Merge strategy, enhances its cultural and linguistic capabilities in Bulgarian while maintaining English performance.

Read More

The model was instruction-fine-tuned using a Bulgarian instruction dataset derived from real-world conversations. It has been evaluated on various benchmarks, including Winogrande, Hellaswag, ARC Easy/Challenge, TriviaQA, GSM-8k, and MON exams, demonstrating superior performance in logical reasoning, mathematics, and language understanding.

BgGPT-Gemma-2-27B-IT-v1.0 outperforms larger models like Alibaba's Qwen 2.5 72B and Meta's Llama3.1 70B in Bulgarian tasks. It also excels in chat performance, surpassing smaller variants of commercial models such as Anthropic's Claude Haiku and OpenAI's GPT-4o-mini, and matches the best commercial models in Bulgarian chat performance.

The model is available for use with the 🤗 Transformers library and supports integration with vLLM and GGML/llama.cpp formats. It is distributed under the Gemma Terms of Use and welcomes community feedback to optimize its performance further.

  • CategoryAI Models & LLMs
  • Pricing ModelOpen source
  • DeploymentCloud
  • PlatformsWeb

BgGPT-Gemma-2-27B-IT-v1.0 Highlights

  • State-of-the-art Bulgarian language model

  • Based on Google's Gemma 2 27B

  • Pre-trained on 100 billion tokens

  • Instruction-fine-tuned with real-world conversations

  • Superior performance in Bulgarian tasks

  • Outperforms larger models

  • Supports integration with 🤗 Transformers

  • Distributed under Gemma Terms of Use

Getting Started with BgGPT-Gemma-2-27B-IT-v1.0

  1. Access page: Visit Hugging Face model page

  2. Load model: Use 🤗 Transformers library

  3. Configure environment: Set recommended parameters

  4. Integrate: Use with vLLM or GGML/llama.cpp

  5. Fine-tune: Apply instruction format

BgGPT-Gemma-2-27B-IT-v1.0's Use Cases

  • Language translation
  • Cultural analysis
  • Chat applications
  • Educational tools
  • Content creation

FAQ from BgGPT-Gemma-2-27B-IT-v1.0

BgGPT-Gemma-2-27B-IT-v1.0 Reviews

BgGPT-Gemma-2-27B-IT-v1.0 Reviews

Loading...

Popular AI Tools Like BgGPT-Gemma-2-27B-IT-v1.0

Gemma 3-27B IT Model

AI Models

Gemma 3-27B IT is a state-of-the-art multimodal AI model from Google, capable of handling text and image inputs to generate text outputs. It supports over 140 languages and is…

AI Models & LLMs
View Tool

Gemma 3-27B IT Model

AI Models

State-of-the-art multimodal AI model from Google, capable of handling text and image inputs to generate text outputs. It supports over 140 languages and is…Gemma 3-27B IT is a state-of-the-art multimodal AI model from Google, capable of handling text and image inputs to generate text outputs. It supports over 140 languages and is…

AI Models & LLMs
See the Top 5 AI Models

Google Gemma 2 9B Instruct

AI Models

Google Gemma 2 9B Instruct is a lightweight, state-of-the-art open model designed for text generation tasks. It is part of the Gemma family, offering capabilities in question…

AI Models & LLMs
View Tool

Google Gemma 2 9B Instruct

AI Models

Lightweight, state-of-the-art open model designed for text generation tasks. It is part of the Gemma family, offering capabilities in question…Google Gemma 2 9B Instruct is a lightweight, state-of-the-art open model designed for text generation tasks. It is part of the Gemma family, offering capabilities in question…

AI Models & LLMs
See the Top 5 AI Models

Gemma 3-4B Model

AI Models

Gemma 3-4B is a state-of-the-art multimodal AI model from Google, capable of handling text and image inputs to generate text outputs. It supports over 140 languages and is…

AI Models & LLMs
View Tool

Gemma 3-4B Model

AI Models

State-of-the-art multimodal AI model from Google, capable of handling text and image inputs to generate text outputs. It supports over 140 languages and is…Gemma 3-4B is a state-of-the-art multimodal AI model from Google, capable of handling text and image inputs to generate text outputs. It supports over 140 languages and is…

AI Models & LLMs
See the Top 5 AI Models

SmolLM3 Language Model

LLMs

SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports dual mode reasoning, six languages, and long context processing, offering…

AI Models & LLMs

Ranked #45 in LLMs

View Tool

SmolLM3 Language Model

LLMs

3B parameter language model designed to push the boundaries of small models. It supports dual mode reasoning, six languages, and long context processing, offering…SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports dual mode reasoning, six languages, and long context processing, offering…

AI Models & LLMs
Ranked #45 in LLMs

Phi-2 Language Model

AI Models

Phi-2 is a 2.7 billion-parameter language model from Microsoft Research. It demonstrates outstanding reasoning and language understanding, achieving state-of-the-art performance…

AI Models & LLMs
View Tool

Phi-2 Language Model

AI Models

2.7 billion-parameter language model from Microsoft Research. It demonstrates outstanding reasoning and language understanding, achieving state-of-the-art performance…Phi-2 is a 2.7 billion-parameter language model from Microsoft Research. It demonstrates outstanding reasoning and language understanding, achieving state-of-the-art performance…

AI Models & LLMs
See the Top 5 AI Models

Kimi-K2-Instruct Model

LLMs

Kimi-K2-Instruct is a state-of-the-art mixture-of-experts language model designed for advanced AI tasks. It excels in reasoning, coding, and tool use, offering robust performance…

AI Models & LLMs

Ranked #44 in LLMs

View Tool

Kimi-K2-Instruct Model

LLMs

State-of-the-art mixture-of-experts language model designed for advanced AI tasks. It excels in reasoning, coding, and tool use, offering robust performance…Kimi-K2-Instruct is a state-of-the-art mixture-of-experts language model designed for advanced AI tasks. It excels in reasoning, coding, and tool use, offering robust performance…

AI Models & LLMs
Ranked #44 in LLMs

Command A+ Model | Cohere

AI Models

Command A+ is a Mixture of Experts model with 25B active and 218B total parameters, designed for complex reasoning, vision, and multilingual tasks across 48 languages, providing…

AI Models & LLMs
View Tool

Command A+ Model | Cohere

AI Models

Mixture of Experts model with 25B active and 218B total parameters, designed for complex reasoning, vision, and multilingual tasks across 48 languages, providing…Command A+ is a Mixture of Experts model with 25B active and 218B total parameters, designed for complex reasoning, vision, and multilingual tasks across 48 languages, providing…

FeaturedAI Models & LLMs
See the Top 5 AI Models

Mistral-Large-Instruct-2411

AI Models

Mistral-Large-Instruct-2411 is a dense Large Language Model with 123B parameters, offering advanced reasoning, coding, and multilingual capabilities. It supports long contexts,…

AI Models & LLMs
View Tool

Mistral-Large-Instruct-2411

AI Models

Dense Large Language Model with 123B parameters, offering advanced reasoning, coding, and multilingual capabilities. It supports long contexts,…Mistral-Large-Instruct-2411 is a dense Large Language Model with 123B parameters, offering advanced reasoning, coding, and multilingual capabilities. It supports long contexts,…

AI Models & LLMs
See the Top 5 AI Models
1 of 8