Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
thanhtunguet_-_gpt2-address-standardizer-prompted-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
thanhtunguet_-_gpt2-address-standardizer-prompted-gguf
like
0
endpoints_compatible
gguf
template
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Quantization made by Richard Erkhov.
Github
Discord
Request more models
gpt2-address-standardizer-prompted - GGUF
Model creator:
https://huggingface.co/thanhtunguet/
Original model:
https://huggingface.co/thanhtunguet/gpt2-address-standardizer-prompted/
Name
Quant method
Size
gpt2-address-standardizer-prompted.Q2_K.gguf
Q2_K
0.17GB
gpt2-address-standardizer-prompted.IQ3_XS.gguf
IQ3_XS
0.18GB
gpt2-address-standardizer-prompted.IQ3_S.gguf
IQ3_S
0.19GB
gpt2-address-standardizer-prompted.Q3_K_S.gguf
Q3_K_S
0.19GB
gpt2-address-standardizer-prompted.IQ3_M.gguf
IQ3_M
0.2GB
gpt2-address-standardizer-prompted.Q3_K.gguf
Q3_K
0.21GB
gpt2-address-standardizer-prompted.Q3_K_M.gguf
Q3_K_M
0.21GB
gpt2-address-standardizer-prompted.Q3_K_L.gguf
Q3_K_L
0.23GB
gpt2-address-standardizer-prompted.IQ4_XS.gguf
IQ4_XS
0.22GB
gpt2-address-standardizer-prompted.Q4_0.gguf
Q4_0
0.23GB
gpt2-address-standardizer-prompted.IQ4_NL.gguf
IQ4_NL
0.23GB
gpt2-address-standardizer-prompted.Q4_K_S.gguf
Q4_K_S
0.23GB
gpt2-address-standardizer-prompted.Q4_K.gguf
Q4_K
0.25GB
gpt2-address-standardizer-prompted.Q4_K_M.gguf
Q4_K_M
0.25GB
gpt2-address-standardizer-prompted.Q4_1.gguf
Q4_1
0.25GB
gpt2-address-standardizer-prompted.Q5_0.gguf
Q5_0
0.27GB
gpt2-address-standardizer-prompted.Q5_K_S.gguf
Q5_K_S
0.27GB
gpt2-address-standardizer-prompted.Q5_K.gguf
Q5_K
0.29GB
gpt2-address-standardizer-prompted.Q5_K_M.gguf
Q5_K_M
0.29GB
gpt2-address-standardizer-prompted.Q5_1.gguf
Q5_1
0.29GB
gpt2-address-standardizer-prompted.Q6_K.gguf
Q6_K
0.32GB
gpt2-address-standardizer-prompted.Q8_0.gguf
Q8_0
0.41GB
Original model description:
library_name: transformers license: mit base_model: gpt2-medium tags:
generated_from_trainer model-index:
name: gpt2-address-standardizer-prompted results: []
gpt2-address-standardizer-prompted
This model is a fine-tuned version of
gpt2-medium
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.2648
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-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
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: linear
num_epochs: 3
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
No log
1.0
62
0.2822
No log
2.0
124
0.2680
No log
3.0
186
0.2648
Framework versions
Transformers 4.46.2
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3
