Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
llama-dpo-r1 – AI Model by skyai798 | AlphaNeural AI
You can deploy this model and start earning money today!
skyai798
/
llama-dpo-r1
like
0
transformers
safetensors
llama
text-generation
llama-factory
full
generated_from_trainer
conversational
thu-ml/STAIR-Llama-3.1-8B-SFT
finetune
other
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
safe_40000_helpful_40000_beta_0.2_lr_5.0e-7_seed_99
This model is a fine-tuned version of
skyai798/llama-cot-sft-seed99
on the safe_40000_helpful_40000 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: 5e-07
train_batch_size: 2
eval_batch_size: 8
seed: 99
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1.0
Training results
Framework versions
Transformers 4.45.2
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.20.1
