RichardErkhov/HPLT_-_sft-fpft-cs-bloom-560m-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

sft-fpft-cs-bloom-560m - GGUF

• Model creator: https://huggingface.co/HPLT/
• Original model: https://huggingface.co/HPLT/sft-fpft-cs-bloom-560m/

Name	Quant method	Size
sft-fpft-cs-bloom-560m.Q2_K.gguf	Q2_K	0.39GB
sft-fpft-cs-bloom-560m.IQ3_XS.gguf	IQ3_XS	0.43GB
sft-fpft-cs-bloom-560m.IQ3_S.gguf	IQ3_S	0.43GB
sft-fpft-cs-bloom-560m.Q3_K_S.gguf	Q3_K_S	0.43GB
sft-fpft-cs-bloom-560m.IQ3_M.gguf	IQ3_M	0.45GB
sft-fpft-cs-bloom-560m.Q3_K.gguf	Q3_K	0.46GB
sft-fpft-cs-bloom-560m.Q3_K_M.gguf	Q3_K_M	0.46GB
sft-fpft-cs-bloom-560m.Q3_K_L.gguf	Q3_K_L	0.47GB
sft-fpft-cs-bloom-560m.IQ4_XS.gguf	IQ4_XS	0.49GB
sft-fpft-cs-bloom-560m.Q4_0.gguf	Q4_0	0.5GB
sft-fpft-cs-bloom-560m.IQ4_NL.gguf	IQ4_NL	0.5GB
sft-fpft-cs-bloom-560m.Q4_K_S.gguf	Q4_K_S	0.5GB
sft-fpft-cs-bloom-560m.Q4_K.gguf	Q4_K	0.52GB
sft-fpft-cs-bloom-560m.Q4_K_M.gguf	Q4_K_M	0.52GB
sft-fpft-cs-bloom-560m.Q4_1.gguf	Q4_1	0.53GB
sft-fpft-cs-bloom-560m.Q5_0.gguf	Q5_0	0.57GB
sft-fpft-cs-bloom-560m.Q5_K_S.gguf	Q5_K_S	0.57GB
sft-fpft-cs-bloom-560m.Q5_K.gguf	Q5_K	0.58GB
sft-fpft-cs-bloom-560m.Q5_K_M.gguf	Q5_K_M	0.58GB
sft-fpft-cs-bloom-560m.Q5_1.gguf	Q5_1	0.6GB
sft-fpft-cs-bloom-560m.Q6_K.gguf	Q6_K	0.64GB
sft-fpft-cs-bloom-560m.Q8_0.gguf	Q8_0	0.82GB

Original model description:

---

language: - cs tags: - generation - question answering - instruction tuning license: cc-by-nc-4.0

Model Description

This HF repository contains base LLMs instruction tuned (SFT) with full-parameter fine-tuning and then used to study whether monolingual or multilingual instruction tuning is more favourable.

• GitHub
• Paper

Instruction tuning details

• Base model: bloom-560m
• Instruction tuning language: Czech
• Training method: full-parameter fine-tuning.
• Best checkpoint: best cross-entropy on a validation set, trained for 3 epochs.
• Dataset: machine-translated from yahma/alpaca-cleaned. You can download our data HERE.

Usage

The model checkpoint should be loaded using transformers library.

Please refer to our Github repository HERE for inference and training instructions.

Citation

@inproceedings{chen-etal-2024-monolingual,
  title="Monolingual or multilingual instruction tuning: Which makes a better {Alpaca}",
  author="Pinzhen Chen and Shaoxiong Ji and Nikolay Bogoychev and Andrey Kutuzov and Barry Haddow and Kenneth Heafield",
  year="2024",
  booktitle = "Findings of the Association for Computational Linguistics: EACL 2024",
}