RichardErkhov/Vivian12300_-_en_sw-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

en_sw - GGUF

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

Name	Quant method	Size
en_sw.Q2_K.gguf	Q2_K	2.96GB
en_sw.IQ3_XS.gguf	IQ3_XS	3.28GB
en_sw.IQ3_S.gguf	IQ3_S	3.43GB
en_sw.Q3_K_S.gguf	Q3_K_S	3.41GB
en_sw.IQ3_M.gguf	IQ3_M	3.52GB
en_sw.Q3_K.gguf	Q3_K	3.74GB
en_sw.Q3_K_M.gguf	Q3_K_M	3.74GB
en_sw.Q3_K_L.gguf	Q3_K_L	4.03GB
en_sw.IQ4_XS.gguf	IQ4_XS	4.18GB
en_sw.Q4_0.gguf	Q4_0	4.34GB
en_sw.IQ4_NL.gguf	IQ4_NL	4.38GB
en_sw.Q4_K_S.gguf	Q4_K_S	4.37GB
en_sw.Q4_K.gguf	Q4_K	4.58GB
en_sw.Q4_K_M.gguf	Q4_K_M	4.58GB
en_sw.Q4_1.gguf	Q4_1	4.78GB
en_sw.Q5_0.gguf	Q5_0	5.21GB
en_sw.Q5_K_S.gguf	Q5_K_S	5.21GB
en_sw.Q5_K.gguf	Q5_K	5.34GB
en_sw.Q5_K_M.gguf	Q5_K_M	5.34GB
en_sw.Q5_1.gguf	Q5_1	5.65GB
en_sw.Q6_K.gguf	Q6_K	6.14GB
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: en_sw results: []

en_sw

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:

• 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