You can deploy this model and start earning money today!

BEE-spoke-data/
smol_llama-101M-midjourney-messages

Name: smol_llama-101M-midjourney-messages
Availability: InStock

pszemraj/midjourney-messages-cleaned

BEE-spoke-data/smol_llama-101M-GQA

finetune

apache-2.0

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

smol_llama-101M-midjourney-messages

Given a 'partial prompt' for a text2image model, this generates additional relevant text to include for a full prompt.

dalle3:

Model description

This model is a fine-tuned version of BEE-spoke-data/smol_llama-101M-GQA on the pszemraj/midjourney-messages-cleaned dataset. It achieves the following results on the evaluation set:

Loss: 2.8431
Accuracy: 0.4682

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.00025
train_batch_size: 4
eval_batch_size: 4
seed: 17056
gradient_accumulation_steps: 16
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
lr_scheduler_type: inverse_sqrt
lr_scheduler_warmup_ratio: 0.05
num_epochs: 1.0

BEE-spoke-data/smol_llama-101M-midjourney-messages

smol_llama-101M-midjourney-messages

Model description

Training procedure

Training hyperparameters

BEE-spoke-data/
smol_llama-101M-midjourney-messages