Audio-Text-to-Text
Transformers
Safetensors
Russian
English
borealis
feature-extraction
audio
speech
multimodal
whisper
qwen
custom_code
Instructions to use Vikhrmodels/Borealis-5b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Vikhrmodels/Borealis-5b-it with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Vikhrmodels/Borealis-5b-it", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ library_name: transformers
|
|
| 15 |
|
| 16 |
# Borealis-5B-IT
|
| 17 |
|
|
|
|
|
|
|
| 18 |
Borealis is an audio-language model that combines Whisper encoder with Qwen3-4B LLM for speech understanding and instruction-following tasks.
|
| 19 |
|
| 20 |
## Model Description
|
|
|
|
| 15 |
|
| 16 |
# Borealis-5B-IT
|
| 17 |
|
| 18 |
+
[📓 **Demo Notebook**](https://huggingface.co/Vikhrmodels/Borealis-5b-it/blob/main/Borealis_Demo.ipynb) — download and open in Colab/Jupyter
|
| 19 |
+
|
| 20 |
Borealis is an audio-language model that combines Whisper encoder with Qwen3-4B LLM for speech understanding and instruction-following tasks.
|
| 21 |
|
| 22 |
## Model Description
|