Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Llama-3.2-3B-Instruct-InfoRAG – AI Model by chengyili2005 | AlphaNeural AI
You can deploy this model and start earning money today!
chengyili2005
/
Llama-3.2-3B-Instruct-InfoRAG
like
0
peft
tensorboard
safetensors
adapter
lora
sft
transformers
trl
unsloth
text-generation
conversational
en
wikimedia/wikipedia
llama3.2
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Llama-3.2-3B-Instruct InfoRag - Chengyi Li
This model is a fine-tuned version of
unsloth/Llama-3.2-3B-Instruct
on the psgs_w100 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: 0.0003
train_batch_size: 2
eval_batch_size: 8
seed: 0
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_steps: 500
training_steps: 3000
Training results
Framework versions
PEFT 0.18.1
Transformers 4.57.6
Pytorch 2.10.0+cu128
Datasets 4.3.0
Tokenizers 0.22.2
