Quantization made by Richard Erkhov.

Github

Discord

Request more models

newwikimodel_de - GGUF

• Model creator: https://huggingface.co/Vivian12300/
• Original model: https://huggingface.co/Vivian12300/newwikimodel_de/

Name	Quant method	Size
newwikimodelde.Q2K.gguf	Q2_K	2.96GB
newwikimodelde.IQ3XS.gguf	IQ3_XS	3.28GB
newwikimodelde.IQ3S.gguf	IQ3_S	3.43GB
newwikimodelde.Q3KS.gguf	Q3KS	3.41GB
newwikimodelde.IQ3M.gguf	IQ3_M	3.52GB
newwikimodelde.Q3K.gguf	Q3_K	3.74GB
newwikimodelde.Q3KM.gguf	Q3KM	3.74GB
newwikimodelde.Q3KL.gguf	Q3KL	4.03GB
newwikimodelde.IQ4XS.gguf	IQ4_XS	4.18GB
newwikimodelde.Q40.gguf	Q4_0	4.34GB
newwikimodelde.IQ4NL.gguf	IQ4_NL	4.38GB
newwikimodelde.Q4KS.gguf	Q4KS	4.37GB
newwikimodelde.Q4K.gguf	Q4_K	4.58GB
newwikimodelde.Q4KM.gguf	Q4KM	4.58GB
newwikimodelde.Q41.gguf	Q4_1	4.78GB
newwikimodelde.Q50.gguf	Q5_0	5.21GB
newwikimodelde.Q5KS.gguf	Q5KS	5.21GB
newwikimodelde.Q5K.gguf	Q5_K	5.34GB
newwikimodelde.Q5KM.gguf	Q5KM	5.34GB
newwikimodelde.Q51.gguf	Q5_1	5.65GB
newwikimodelde.Q6K.gguf	Q6_K	6.14GB
newwikimodelde.Q80.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
• generatedfromtrainer

datasets:

• generator

model-index:

• name: newwikimodel_de

results: []

---

newwikimodel_de

This model is a fine-tuned version of 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:

• learningrate: 5e-05
• trainbatchsize: 1
• evalbatchsize: 2
• seed: 42
• gradientaccumulationsteps: 16
• totaltrainbatchsize: 16
• optimizer: Use adafactor and the args are:

No additional optimizer arguments

• lrschedulertype: linear
• num_epochs: 30

Training results

Framework versions

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