metadata
license: apache-2.0
base_model: speakleash/Bielik-11B-v2.2-Instruct
language:
- pl
library_name: transformers
tags:
- finetuned
- TensorBlock
- GGUF
inference:
parameters:
temperature: 0.2
widget:
- messages:
- role: user
content: Co przedstawia polskie godło?
extra_gated_description: >-
If you want to learn more about how you can use the model, please refer to our
<a href="https://bielik.ai/terms/">Terms of Use</a>.
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
speakleash/Bielik-11B-v2.2-Instruct - GGUF
This repo contains GGUF format model files for speakleash/Bielik-11B-v2.2-Instruct.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<s><|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Bielik-11B-v2.2-Instruct-Q2_K.gguf | Q2_K | 3.878 GB | smallest, significant quality loss - not recommended for most purposes |
| Bielik-11B-v2.2-Instruct-Q3_K_S.gguf | Q3_K_S | 4.519 GB | very small, high quality loss |
| Bielik-11B-v2.2-Instruct-Q3_K_M.gguf | Q3_K_M | 5.034 GB | very small, high quality loss |
| Bielik-11B-v2.2-Instruct-Q3_K_L.gguf | Q3_K_L | 5.476 GB | small, substantial quality loss |
| Bielik-11B-v2.2-Instruct-Q4_0.gguf | Q4_0 | 5.885 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Bielik-11B-v2.2-Instruct-Q4_K_S.gguf | Q4_K_S | 5.928 GB | small, greater quality loss |
| Bielik-11B-v2.2-Instruct-Q4_K_M.gguf | Q4_K_M | 6.262 GB | medium, balanced quality - recommended |
| Bielik-11B-v2.2-Instruct-Q5_0.gguf | Q5_0 | 7.169 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Bielik-11B-v2.2-Instruct-Q5_K_S.gguf | Q5_K_S | 7.169 GB | large, low quality loss - recommended |
| Bielik-11B-v2.2-Instruct-Q5_K_M.gguf | Q5_K_M | 7.364 GB | large, very low quality loss - recommended |
| Bielik-11B-v2.2-Instruct-Q6_K.gguf | Q6_K | 8.535 GB | very large, extremely low quality loss |
| Bielik-11B-v2.2-Instruct-Q8_0.gguf | Q8_0 | 11.054 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/Bielik-11B-v2.2-Instruct-GGUF --include "Bielik-11B-v2.2-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/Bielik-11B-v2.2-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'