Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
smollm2-1.7-kurdi – AI Model by chaishirin | AlphaNeural AI
You can deploy this model and start earning money today!
chaishirin
/
smollm2-1.7-kurdi
like
0
transformers
pytorch
tensorboard
llama
text-generation
alignment-handbook
trl
sft
generated_from_trainer
chaishirin/xala-full
HuggingFaceTB/SmolLM2-1.7B
finetune
apache-2.0
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
smollm2-1.7-kurdi
This model is a fine-tuned version of
HuggingFaceTB/SmolLM2-1.7B
on the chaishirin/xala-full 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: 0.0002
train_batch_size: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 3
total_train_batch_size: 6
total_eval_batch_size: 12
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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1
Training results
Framework versions
Transformers 4.48.3
Pytorch 2.6.0+cu126
Datasets 3.2.0
Tokenizers 0.21.0
