DYG_TiBERT_v2

TSingye/DYG_TiBERT_v2

DYG_TiBERT_v2 is a text generation model from TSingye. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

20% of all-time downloads

All-time downloads

Public

Parameters

83.5M

334 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors334 MB · 99%

At a glance

Task: Text Generation
Library: transformers
License: mit
Model type: roberta
Access: Public
Created: May 17, 2024
Updated: May 17, 2024
SHA: b0b36896

Try a prompt

Base models

sangjeedondrub/tibetan-roberta-causal-base

Model card

From the Hugging Face model README

DYG_TiBERT_v2

This model is a fine-tuned version of sangjeedondrub/tibetan-roberta-causal-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.2134

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: 0.001
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	8	3.1386
No log	2.0	16	2.1665
No log	3.0	24	1.6217
No log	4.0	32	1.3016
No log	5.0	40	1.2134

Framework versions

Transformers 4.40.2
Pytorch 2.2.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Task: Text Generation
Library: transformers
Type: roberta
License: mit
Created: May 17, 2024
Updated: May 17, 2024