todorov/ bggpt:Gemma-3-4B-IT-Q5_K_M

2,366 Downloads Updated 2 weeks ago

BgGPT is a Bulgarian language model built on top of Google’s Gemma 3.

ollama run todorov/bggpt:Gemma-3-4B-IT-Q5_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "todorov/bggpt:Gemma-3-4B-IT-Q5_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='todorov/bggpt:Gemma-3-4B-IT-Q5_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'todorov/bggpt:Gemma-3-4B-IT-Q5_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 weeks ago

2 weeks ago

11f72ada94f0 · 2.8GB ·

model

archgemma3

·

parameters3.88B

·

quantizationQ5_K_M

2.8GB

license

Gemma Terms of Use Last modified: April 1, 2024 By using, reproducing, modifying, distributing, perf

8.4kB

params

{ "num_ctx": 8192, "num_predict": 2048, "repeat_penalty": 1, "stop": [ "<sta

154B

template

<start_of_turn>user {{ if .System }}{{ .System }} {{ end }}{{ .Prompt }}<end_of_turn> <start_of_turn

136B

Readme

BgGPT

Meet BgGPT, a Bulgarian language model built on top of Google’s Gemma 3. BgGPT is distributed under Gemma Terms of Use.

Versions 0.1 and 0.2 of the model were built on top of Mistral 0.1 and 0.2.

This model was created by INSAIT Institute, part of Sofia University, in Sofia, Bulgaria.

Model description

BgGPT 3.0 is a series of Bulgarian-adapted LLMs based on Gemma 3, developed by INSAIT. Available in 4B, 12B and 27B sizes.

Blog post: BgGPT-3 Release

Key improvements over BgGPT 2.0

Vision-language understanding — The models understand both text and images within the same context.
Instruction-following — Trained on a broader range of tasks, multi-turn conversations, complex instructions, and system prompts.
Longer context — Effective context of 131k tokens for longer conversations and complex instructions.
Updated knowledge cut-off — Pretraining data up to May 2025, instruction fine-tuning up to October 2025.

Usage

CLI

ollama run todorov/bggpt

API

Example:

curl -X POST http://localhost:11434/api/generate -d '{
  "model": "todorov/bggpt",
  "prompt":"Кога е основан Софийският университет?"
 }'

References

BgGPT
BgGPT-Gemma-3-4B-IT on Hugging Face
BgGPT-Gemma-3-12B-IT on Hugging Face
BgGPT-Gemma-3-27B-IT on Hugging Face

<p><img src="https://bggpt.ai/_app/immutable/assets/logo-plain-bright.DudhvT1g.svg" alt="BgGPT logo"/></p>

<h1>BgGPT</h1>

<p>Meet BgGPT, a Bulgarian language model built on top of Google’s Gemma 3. BgGPT is distributed under <a href="https://ai.google.dev/gemma/terms" rel="nofollow">Gemma Terms of Use</a>.</p>
<p>Versions 0.1 and 0.2 of the model were built on top of Mistral 0.1 and 0.2.</p>

<p>This model was created by <a href="https://insait.ai/" rel="nofollow">INSAIT Institute</a>, part of <a href="https://www.uni-sofia.bg/index.php/eng" rel="nofollow">Sofia University</a>, in Sofia, Bulgaria.</p>

<h2>Model description</h2>

<p>BgGPT 3.0 is a series of Bulgarian-adapted LLMs based on Gemma 3, developed by <a href="https://insait.ai" rel="nofollow">INSAIT</a>. Available in 4B, 12B and 27B sizes.</p>
<p><strong>Blog post</strong>: <a href="https://models.bggpt.ai/blog/bggpt-3-release-en" rel="nofollow">BgGPT-3 Release</a></p>
<h3 class="relative group flex items-baseline">
	<a id="key-improvements-over-bggpt-20" class="block pr-1.5 text-lg md:absolute md:p-1.5 md:opacity-0 md:group-hover:opacity-100 md:right-full" href="#key-improvements-over-bggpt-20" rel="nofollow">
		<span class="header-link"><svg class="text-gray-500 hover:text-black dark:hover:text-gray-200 w-4" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span>
	</a>
	<span>
		Key improvements over BgGPT 2.0
	</span>
</h3>
<ol>
<li><strong>Vision-language understanding</strong> — The models understand both text and images within the same context.</li>
<li><strong>Instruction-following</strong> — Trained on a broader range of tasks, multi-turn conversations, complex instructions, and system prompts.</li>
<li><strong>Longer context</strong> — Effective context of 131k tokens for longer conversations and complex instructions.</li>
<li><strong>Updated knowledge cut-off</strong> — Pretraining data up to May 2025, instruction fine-tuning up to October 2025.</li>
</ol>

<h2>Usage</h2>

<h3>CLI</h3>

<pre><code>ollama run todorov/bggpt
</code></pre>

<h3>API</h3>

<p>Example:</p>

<pre><code>curl -X POST http://localhost:11434/api/generate -d &#39;{
  &#34;model&#34;: &#34;todorov/bggpt&#34;,
  &#34;prompt&#34;:&#34;Кога е основан Софийският университет?&#34;
 }&#39;
</code></pre>

<h2>References</h2>

<p><a href="https://bggpt.ai/" rel="nofollow">BgGPT</a><br>
<a href="https://huggingface.co/INSAIT-Institute/BgGPT-Gemma-3-4B-IT" rel="nofollow">BgGPT-Gemma-3-4B-IT on Hugging Face</a><br>
<a href="https://huggingface.co/INSAIT-Institute/BgGPT-Gemma-3-12B-IT" rel="nofollow">BgGPT-Gemma-3-12B-IT on Hugging Face</a><br>
<a href="https://huggingface.co/INSAIT-Institute/BgGPT-Gemma-3-27B-IT" rel="nofollow">BgGPT-Gemma-3-27B-IT on Hugging Face</a></p>

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)