Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
llama-3.2-1b-georiskKD-kl-conservative – AI Model by vukien2301 | AlphaNeural AI
You can deploy this model and start earning money today!
vukien2301
/
llama-3.2-1b-georiskKD-kl-conservative
like
0
transformers
safetensors
llama
text-generation
alignment-handbook
generated_from_trainer
conversational
pvdhihihi/ultra-feedback
vukien2301/llama-3.2-1b-deita-sft-student
finetune
llama3.2
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
llama-3.2-1b-georiskKD-kl-conservative
This model is a fine-tuned version of
vukien2301/llama-3.2-1b-deita-sft-student
on the pvdhihihi/ultra-feedback 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: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 16
total_eval_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1
Training results
Framework versions
Transformers 4.51.3
Pytorch 2.8.0+cu128
Datasets 4.8.5
Tokenizers 0.21.4
