Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
Youliang_-_llama3-8b-derta-4bits – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
Youliang_-_llama3-8b-derta-4bits
like
0
safetensors
llama
2407.09121
4-bit
bitsandbytes
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Quantization made by Richard Erkhov.
Github
Discord
Request more models
llama3-8b-derta - bnb 4bits
Model creator:
https://huggingface.co/Youliang/
Original model:
https://huggingface.co/Youliang/llama3-8b-derta/
Original model description:
base_model: meta-llama/Meta-Llama-3-8B tags:
generated_from_trainer model-index:
name: Meta-Llama-3-8B_derta results: [] license: apache-2.0
Meta-Llama-3-8B_derta
This model is a fine-tuned version of
meta-llama/Meta-Llama-3-8B
on the
Evol-Instruct
and
BeaverTails
dataset.
Model description
Please refer to the paper
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
and GitHub
DeRTa
.
Input format:
[INST] Your Instruction [\INST]
Intended uses & limitations
The model is trained with DeRTa, showing a high safety performance.
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: 16
weight_decay: 2e-5
eval_batch_size: 1
seed: 1
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 128
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 2.0
Training results
Framework versions
Transformers 4.40.0
Pytorch 2.2.0+cu118
Datasets 2.10.0
Tokenizers 0.19.1
