Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
amharic_llama2_qa_rag_qlora – AI Model by Desalegnn | AlphaNeural AI
You can deploy this model and start earning money today!
Desalegnn
/
amharic_llama2_qa_rag_qlora
like
0
peft
safetensors
adapter
lora
transformers
text-generation
meta-llama/Llama-2-7b-hf
llama2
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
amharic_llama2_qa_rag_qlora
This model is a fine-tuned version of
meta-llama/Llama-2-7b-hf
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.4192
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: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3
Training results
Training Loss
Epoch
Step
Validation Loss
0.6201
1.0
306
0.5929
0.4691
2.0
612
0.4640
0.3887
3.0
918
0.4192
Framework versions
PEFT 0.18.0
Transformers 4.57.2
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1
