backup_0202_llamafactory_Compcap_l0_0_90-llava-mistral

htlou/backup_0202_llamafactory_Compcap_l0_0_90-llava-mistral

backup_0202_llamafactory_Compcap_l0_0_90-llava-mistral is a image-text-to-text model from htlou. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.

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

Downloads · 30 days

38% of all-time downloads

All-time downloads

Public

Parameters

7.6B

15.1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors15.1 GB · 100%

At a glance

Task: Image-Text-to-Text
Library: transformers
License: other
Model type: llava_next
Access: Public
Created: Feb 3, 2025
Updated: Feb 3, 2025
SHA: 0bee6b0a

Try a prompt

Base models

llava-hf/llava-v1.6-mistral-7b-hf

Model card

From the Hugging Face model README

Compcap_l0_0_90

This model is a fine-tuned version of llava-hf/llava-v1.6-mistral-7b-hf on the Compcap_l0_0_90 dataset. It achieves the following results on the evaluation set:

Loss: 0.7734

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: 1e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 256
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.9397	0.1505	50	0.9223
0.9027	0.3010	100	0.8662
0.8711	0.4515	150	0.8410
0.8628	0.6020	200	0.8240
0.8283	0.7524	250	0.8112
0.7989	0.9029	300	0.8007
0.7415	1.0534	350	0.7968
0.7347	1.2039	400	0.7904
0.7181	1.3544	450	0.7858
0.7435	1.5049	500	0.7818
0.7384	1.6554	550	0.7777
0.719	1.8059	600	0.7739
0.7179	1.9564	650	0.7713
0.6837	2.1068	700	0.7764
0.6684	2.2573	750	0.7755
0.6869	2.4078	800	0.7743
0.6717	2.5583	850	0.7738
0.6793	2.7088	900	0.7734
0.6685	2.8593	950	0.7734

Framework versions

Transformers 4.45.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.20.3

Task: Image-Text-to-Text
Library: transformers
Type: llava_next
License: other
Created: Feb 3, 2025
Updated: Feb 3, 2025