RichardErkhov/RyanYr_-_gemma-2-2b-it_CoT-it_SFT-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gemma-2-2b-itCoT-itSFT - GGUF

• —Model creator: https://huggingface.co/RyanYr/
• —Original model: https://huggingface.co/RyanYr/gemma-2-2b-itCoT-itSFT/

Original model description: --- libraryname: transformers license: gemma basemodel: google/gemma-2-2b-it tags:

• —trl
• —sft
• —generatedfromtrainer model-index:
• —name: gemma-2-2b-itCoT-itSFT results: [] ---

<!-- 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. -->

gemma-2-2b-itCoT-itSFT

This model is a fine-tuned version of google/gemma-2-2b-it on an unknown 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: 2e-06
• —trainbatchsize: 1
• —evalbatchsize: 1
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 4
• —gradientaccumulationsteps: 64
• —totaltrainbatch_size: 256
• —totalevalbatch_size: 4
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.03
• —num_epochs: 1

Training results

Framework versions

• —Transformers 4.44.2
• —Pytorch 2.4.0+cu121
• —Datasets 3.0.0
• —Tokenizers 0.19.1