Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
mistral-7b_qlora_experiment – AI Model by kexinz | AlphaNeural AI
You can deploy this model and start earning money today!
kexinz
/
mistral-7b_qlora_experiment
like
0
peft
safetensors
generated_from_trainer
mistralai/Mistral-7B-v0.1
adapter
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
mistral-7b_qlora_experiment
This model is a fine-tuned version of
mistralai/Mistral-7B-v0.1
on an unknown dataset.
Model description
mistral-7b quantized with QLoRA and fine-tuned with 5% MMLU axiliary training (with custom format for individual testcase comparison)
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 2.5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
training_steps: 500
Framework versions
PEFT 0.9.1.dev0
Transformers 4.38.2
Pytorch 2.2.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2
