Bielik-v3 - Family
Collection
Bielik-v3 model family - models in all sizes and quantizations • 15 items • Updated • 30
Bielik-11B-v3.0-Instruct-MLX-8bit
This model was converted to MLX format from SpeakLeash's Bielik-11B-v3.0-Instruct.
DISCLAIMER: Be aware that quantised models show reduced response quality and possible hallucinations!
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("speakleash/Bielik-11B-v3.0-Instruct-MLX-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Model description:
- Developed by: SpeakLeash & ACK Cyfronet AGH
- Language: Multilingual (32 European languages, optimized for Polish)
- Model type: causal decoder-only
- Quant from: Bielik-11B-v3.0-Instruct
- Finetuned from: speakleash/Bielik-11B-v3-Base-20250730
- License: Apache 2.0
Responsible for model quantization
- Remigiusz KinasSpeakLeash - team leadership, conceptualizing, calibration data preparation, process creation and quantized model delivery.
Contact Us
If you have any questions or suggestions, please use the discussion tab. If you want to contact us directly, join our Discord SpeakLeash.
- Downloads last month
- 230
Model size
11B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
8-bit
Model tree for speakleash/Bielik-11B-v3.0-Instruct-MLX-8bit
Base model
speakleash/Bielik-11B-v3-Base-20250730 Finetuned
speakleash/Bielik-11B-v3.0-Instruct