Quantization made by Richard Erkhov.

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

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

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


sparse_ft_en_sw - GGUF
- Model creator: https://huggingface.co/Vivian12300/
- Original model: https://huggingface.co/Vivian12300/sparse_ft_en_sw/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [sparse_ft_en_sw.Q2_K.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q2_K.gguf) | Q2_K | 2.96GB |
| [sparse_ft_en_sw.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
| [sparse_ft_en_sw.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.IQ3_S.gguf) | IQ3_S | 3.43GB |
| [sparse_ft_en_sw.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
| [sparse_ft_en_sw.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.IQ3_M.gguf) | IQ3_M | 3.52GB |
| [sparse_ft_en_sw.Q3_K.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q3_K.gguf) | Q3_K | 3.74GB |
| [sparse_ft_en_sw.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
| [sparse_ft_en_sw.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
| [sparse_ft_en_sw.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
| [sparse_ft_en_sw.Q4_0.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q4_0.gguf) | Q4_0 | 4.34GB |
| [sparse_ft_en_sw.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
| [sparse_ft_en_sw.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
| [sparse_ft_en_sw.Q4_K.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q4_K.gguf) | Q4_K | 4.58GB |
| [sparse_ft_en_sw.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
| [sparse_ft_en_sw.Q4_1.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q4_1.gguf) | Q4_1 | 4.78GB |
| [sparse_ft_en_sw.Q5_0.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q5_0.gguf) | Q5_0 | 5.21GB |
| [sparse_ft_en_sw.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
| [sparse_ft_en_sw.Q5_K.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q5_K.gguf) | Q5_K | 5.34GB |
| [sparse_ft_en_sw.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
| [sparse_ft_en_sw.Q5_1.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q5_1.gguf) | Q5_1 | 5.65GB |
| [sparse_ft_en_sw.Q6_K.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q6_K.gguf) | Q6_K | 6.14GB |
| [sparse_ft_en_sw.Q8_0.gguf](https://huggingface.co/RichardErkhov/Vivian12300_-_sparse_ft_en_sw-gguf/blob/main/sparse_ft_en_sw.Q8_0.gguf) | Q8_0 | 7.95GB |




Original model description:
---
library_name: transformers
license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: sparse_ft_en_sw
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# sparse_ft_en_sw

This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the generator dataset.

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use adafactor and the args are:
No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5

### Training results



### Framework versions

- Transformers 4.46.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.20.3