Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Vivian12300_-_sparse_ft_en_sw_context-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
Vivian12300_-_sparse_ft_en_sw_context-gguf
like
0
conversational
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
sparse_ft_en_sw_context - GGUF
Model creator:
https://huggingface.co/Vivian12300/
Original model:
https://huggingface.co/Vivian12300/sparse_ft_en_sw_context/
Name
Quant method
Size
sparse_ft_en_sw_context.Q2_K.gguf
Q2_K
2.96GB
sparse_ft_en_sw_context.IQ3_XS.gguf
IQ3_XS
3.28GB
sparse_ft_en_sw_context.IQ3_S.gguf
IQ3_S
3.43GB
sparse_ft_en_sw_context.Q3_K_S.gguf
Q3_K_S
3.41GB
sparse_ft_en_sw_context.IQ3_M.gguf
IQ3_M
3.52GB
sparse_ft_en_sw_context.Q3_K.gguf
Q3_K
3.74GB
sparse_ft_en_sw_context.Q3_K_M.gguf
Q3_K_M
3.74GB
sparse_ft_en_sw_context.Q3_K_L.gguf
Q3_K_L
4.03GB
sparse_ft_en_sw_context.IQ4_XS.gguf
IQ4_XS
4.18GB
sparse_ft_en_sw_context.Q4_0.gguf
Q4_0
4.34GB
sparse_ft_en_sw_context.IQ4_NL.gguf
IQ4_NL
4.38GB
sparse_ft_en_sw_context.Q4_K_S.gguf
Q4_K_S
4.37GB
sparse_ft_en_sw_context.Q4_K.gguf
Q4_K
4.58GB
sparse_ft_en_sw_context.Q4_K_M.gguf
Q4_K_M
4.58GB
sparse_ft_en_sw_context.Q4_1.gguf
Q4_1
4.78GB
sparse_ft_en_sw_context.Q5_0.gguf
Q5_0
5.21GB
sparse_ft_en_sw_context.Q5_K_S.gguf
Q5_K_S
5.21GB
sparse_ft_en_sw_context.Q5_K.gguf
Q5_K
5.34GB
sparse_ft_en_sw_context.Q5_K_M.gguf
Q5_K_M
5.34GB
sparse_ft_en_sw_context.Q5_1.gguf
Q5_1
5.65GB
sparse_ft_en_sw_context.Q6_K.gguf
Q6_K
6.14GB
sparse_ft_en_sw_context.Q8_0.gguf
Q8_0
7.95GB
Original model description:
library_name: transformers license: llama3.1 base_model: Vivian12300/sparse_ft_en_sw tags:
trl
sft
generated_from_trainer datasets:
generator model-index:
name: sparse_ft_en_sw_context results: []
sparse_ft_en_sw_context
This model is a fine-tuned version of
Vivian12300/sparse_ft_en_sw
on the generator 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: 5e-05
train_batch_size: 1
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Use adafactor and the args are: No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 30
Training results
Framework versions
Transformers 4.46.3
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.20.3
