Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
DeepSeek-LLM-7B-Base-TagPrediction-Top5-Editorial – AI Model by Sauron0019 | AlphaNeural AI
You can deploy this model and start earning money today!
Sauron0019
/
DeepSeek-LLM-7B-Base-TagPrediction-Top5-Editorial
like
0
peft
safetensors
llama-factory
lora
generated_from_trainer
deepseek-ai/deepseek-llm-7b-base
adapter
other
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
train_2025-05-16-10-50-14_final
This model is a fine-tuned version of
deepseek-ai/deepseek-llm-7b-base
on the top_5_training_dataset 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: 3e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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: cosine_with_restarts
lr_scheduler_warmup_steps: 200
num_epochs: 5.0
label_smoothing_factor: 0.05
Training results
Framework versions
PEFT 0.15.1
Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1
