koshirowada_-_pythia_160m_sft-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

pythia_160m_sft - AWQ

• Model creator: https://huggingface.co/koshirowada/
• Original model: https://huggingface.co/koshirowada/pythia_160m_sft/

Original model description:

library_name: transformers license: apache-2.0 base_model: EleutherAI/pythia-160m tags:

• generated_from_trainer model-index:
• name: pythia_160m_sft results: [] datasets:
• tatsu-lab/alpaca_farm

---

<!-- 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. -->

pythia_160m_sft

This model is a fine-tuned version of EleutherAI/pythia-160m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9831

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: 2e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3