zephyr-7b-gemma-sft-african-ultrachat-200k-GGUF

Quantized GGUF model files for zephyr-7b-gemma-sft-african-ultrachat-200k from masakhane

Original Model Card:

zephyr-7b-gemma-sft-african-ultrachat-2000k

This model is a fine-tuned version of google/gemma-7b on the masakhane/african-ultrachat and the israel/untrachat_en datasets. It achieves the following results on the evaluation set:

  • Loss: 1.1549

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: 1e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.0785 1.0 17748 1.2602
0.6614 2.0 35496 1.1089
0.2983 3.0 53244 1.1549

Framework versions

  • Transformers 4.39.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.14.6
  • Tokenizers 0.15.2
Downloads last month
99
GGUF
Model size
8.54B params
Architecture
gemma

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for afrideva/zephyr-7b-gemma-sft-african-ultrachat-200k-GGUF

Base model

google/gemma-7b
Quantized
(1)
this model

Datasets used to train afrideva/zephyr-7b-gemma-sft-african-ultrachat-200k-GGUF