Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
llama2-7b-sft-lora – AI Model by aengusl | AlphaNeural AI
You can deploy this model and start earning money today!
aengusl
/
llama2-7b-sft-lora
like
0
peft
tensorboard
safetensors
trl
sft
generated_from_trainer
generator
meta-llama/Llama-2-7b-chat-hf
adapter
llama2
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Visualize in Weights & Biases
llama2-7b-sft-lora
This model is a fine-tuned version of
meta-llama/Llama-2-7b-chat-hf
on the generator 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-05
train_batch_size: 4
eval_batch_size: 8
seed: 4
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 32
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
training_steps: 2000
Framework versions
Transformers 4.41.0
Pytorch 2.1.0+cu121
Datasets 2.14.6
Tokenizers 0.19.1
Training procedure
Framework versions
PEFT 0.6.1
