tian-ft8bit

Sirawipa/tian-ft8bit

tian-ft8bit is a machine learning model from Sirawipa. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.

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

Downloads · 30 days

25% of all-time downloads

All-time downloads

Public

Parameters

7.3B

8.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors8.2 GB · 100%

Parameter types

How the weights are stored.

I87B · 96%

Base models

openthaigpt/openthaigpt-1.0.0-7b-chat

Model card

From the Hugging Face model README

tian-ft8bit

This model is a fine-tuned version of openthaigpt/openthaigpt-1.0.0-7b-chat on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3650

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: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.6818	0.9362	11	1.2394
0.7417	1.9574	23	0.4204
0.3016	2.9787	35	0.3303
0.1401	4.0	47	0.3590
0.0825	4.9362	58	0.3573
0.0601	5.9574	70	0.3517
0.0515	6.9787	82	0.3590
0.0483	8.0	94	0.3617
0.05	8.9362	105	0.3620
0.0393	9.3617	110	0.3650

Framework versions

PEFT 0.10.0
Transformers 4.41.0
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.19.1

Library: peft
Type: mistral
License: apache-2.0
Created: May 23, 2024
Updated: May 23, 2024