QuantFactory/LLaMA-O1-Base-1127-GGUF

This is quantized version of SimpleBerry/LLaMA-O1-Base-1127 created using llama.cpp

Original Model Card

SimpleBerry/LLaMA-O1-Base-1127

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the longcot_pt dataset.

Do not use this model without supervised training, please use LLaMA-O1-Supervised-1129 for directly usage.

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: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 24
• total_train_batch_size: 24
• total_eval_batch_size: 192
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 4.0

Training results

Framework versions

• Transformers 4.46.2
• Pytorch 2.3.1
• Datasets 3.1.0
• Tokenizers 0.20.1