MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/README.md

Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


lucky52-bloom-7b1-no-5 - GGUF
- Model creator: https://huggingface.co/MaLA-LM/
- Original model: https://huggingface.co/MaLA-LM/lucky52-bloom-7b1-no-5/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [lucky52-bloom-7b1-no-5.Q2_K.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q2_K.gguf) | Q2_K | 3.2GB |
| [lucky52-bloom-7b1-no-5.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.IQ3_XS.gguf) | IQ3_XS | 3.56GB |
| [lucky52-bloom-7b1-no-5.IQ3_S.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.IQ3_S.gguf) | IQ3_S | 3.63GB |
| [lucky52-bloom-7b1-no-5.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q3_K_S.gguf) | Q3_K_S | 3.63GB |
| [lucky52-bloom-7b1-no-5.IQ3_M.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.IQ3_M.gguf) | IQ3_M | 3.9GB |
| [lucky52-bloom-7b1-no-5.Q3_K.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q3_K.gguf) | Q3_K | 4.14GB |
| [lucky52-bloom-7b1-no-5.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q3_K_M.gguf) | Q3_K_M | 4.14GB |
| [lucky52-bloom-7b1-no-5.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q3_K_L.gguf) | Q3_K_L | 4.42GB |
| [lucky52-bloom-7b1-no-5.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.IQ4_XS.gguf) | IQ4_XS | 4.33GB |
| [lucky52-bloom-7b1-no-5.Q4_0.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q4_0.gguf) | Q4_0 | 4.51GB |
| [lucky52-bloom-7b1-no-5.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.IQ4_NL.gguf) | IQ4_NL | 4.53GB |
| [lucky52-bloom-7b1-no-5.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q4_K_S.gguf) | Q4_K_S | 4.53GB |
| [lucky52-bloom-7b1-no-5.Q4_K.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q4_K.gguf) | Q4_K | 4.91GB |
| [lucky52-bloom-7b1-no-5.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q4_K_M.gguf) | Q4_K_M | 4.91GB |
| [lucky52-bloom-7b1-no-5.Q4_1.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q4_1.gguf) | Q4_1 | 4.92GB |
| [lucky52-bloom-7b1-no-5.Q5_0.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q5_0.gguf) | Q5_0 | 5.33GB |
| [lucky52-bloom-7b1-no-5.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q5_K_S.gguf) | Q5_K_S | 5.33GB |
| [lucky52-bloom-7b1-no-5.Q5_K.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q5_K.gguf) | Q5_K | 5.63GB |
| [lucky52-bloom-7b1-no-5.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q5_K_M.gguf) | Q5_K_M | 5.63GB |
| [lucky52-bloom-7b1-no-5.Q5_1.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q5_1.gguf) | Q5_1 | 5.74GB |
| [lucky52-bloom-7b1-no-5.Q6_K.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q6_K.gguf) | Q6_K | 6.2GB |
| [lucky52-bloom-7b1-no-5.Q8_0.gguf](https://huggingface.co/RichardErkhov/MaLA-LM_-_lucky52-bloom-7b1-no-5-gguf/blob/main/lucky52-bloom-7b1-no-5.Q8_0.gguf) | Q8_0 | 8.03GB |




Original model description:

---
library_name: transformers
pipeline_tag: text-generation
language:
- multilingual
tags:
- generation
- question answering
- instruction tuning
datasets:
- MBZUAI/Bactrian-X
license: cc-by-nc-4.0
---

###  Model Description

This HF repository hosts instruction fine-tuned multilingual BLOOM model using the parallel instruction dataset called Bactrain-X in 52 languages. 
We progressively add a language during instruction fine-tuning at each time, and train 52 models in total. Then, we evaluate those models in three multilingual benchmarks. 

Please refer to [our paper](https://arxiv.org/abs/2404.04850) for more details.

* Base model: [BLOOM 7B1](https://huggingface.co/bigscience/bloom-7b1)
* Instruction languages: English, Chinese, Afrikaans, Arabic, Azerbaijani
* Instruction language codes: en, zh, af, ar, az
* Training method: full-parameter fine-tuning.

### Usage
The model checkpoint should be loaded using `transformers` library.

```python
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-5")
model = AutoModelForCausalLM.from_pretrained("MaLA-LM/lucky52-bloom-7b1-no-5")
```

### Citation
```
@inproceedings{ji2025lucky52,
      title={How Many Languages Make Good Multilingual Instruction Tuning? A Case Study on BLOOM}, 
      author={Shaoxiong Ji and Pinzhen Chen},
      year={2025},
      booktitle={Proceedings of COLING},
      url={https://arxiv.org/abs/2404.04850}, 
}
```