Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
emillykkejensen_-_Phi-3-mini-4k-instruct-dansk-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
Phi-3-mini-4k-instruct-dansk - GGUF
Model creator:
https://huggingface.co/emillykkejensen/
Original model:
https://huggingface.co/emillykkejensen/Phi-3-mini-4k-instruct-dansk/
Name
Quant method
Size
Phi-3-mini-4k-instruct-dansk.Q2_K.gguf
Q2_K
1.32GB
Phi-3-mini-4k-instruct-dansk.IQ3_XS.gguf
IQ3_XS
1.51GB
Phi-3-mini-4k-instruct-dansk.IQ3_S.gguf
IQ3_S
1.57GB
Phi-3-mini-4k-instruct-dansk.Q3_K_S.gguf
Q3_K_S
1.57GB
Phi-3-mini-4k-instruct-dansk.IQ3_M.gguf
IQ3_M
1.73GB
Phi-3-mini-4k-instruct-dansk.Q3_K.gguf
Q3_K
1.82GB
Phi-3-mini-4k-instruct-dansk.Q3_K_M.gguf
Q3_K_M
1.82GB
Phi-3-mini-4k-instruct-dansk.Q3_K_L.gguf
Q3_K_L
1.94GB
Phi-3-mini-4k-instruct-dansk.IQ4_XS.gguf
IQ4_XS
1.93GB
Phi-3-mini-4k-instruct-dansk.Q4_0.gguf
Q4_0
2.03GB
Phi-3-mini-4k-instruct-dansk.IQ4_NL.gguf
IQ4_NL
2.04GB
Phi-3-mini-4k-instruct-dansk.Q4_K_S.gguf
Q4_K_S
2.04GB
Phi-3-mini-4k-instruct-dansk.Q4_K.gguf
Q4_K
2.23GB
Phi-3-mini-4k-instruct-dansk.Q4_K_M.gguf
Q4_K_M
2.23GB
Phi-3-mini-4k-instruct-dansk.Q4_1.gguf
Q4_1
2.24GB
Phi-3-mini-4k-instruct-dansk.Q5_0.gguf
Q5_0
2.46GB
Phi-3-mini-4k-instruct-dansk.Q5_K_S.gguf
Q5_K_S
2.46GB
Phi-3-mini-4k-instruct-dansk.Q5_K.gguf
Q5_K
2.62GB
Phi-3-mini-4k-instruct-dansk.Q5_K_M.gguf
Q5_K_M
2.62GB
Phi-3-mini-4k-instruct-dansk.Q5_1.gguf
Q5_1
2.68GB
Phi-3-mini-4k-instruct-dansk.Q6_K.gguf
Q6_K
2.92GB
Phi-3-mini-4k-instruct-dansk.Q8_0.gguf
Q8_0
3.78GB
Original model description:
license: mit base_model: microsoft/Phi-3-mini-4k-instruct tags:
trl
sft
generated_from_trainer
danish datasets:
kobprof/skolegpt-instruct model-index:
name: Phi-3-mini-4k-instruct-dansk results: []
Visualize in Weights & Biases
Phi-3-mini-4k-instruct-dansk
This model is a fine-tuned version of
microsoft/Phi-3-mini-4k-instruct
on the
kobprof/skolegpt-instruct
dataset. It achieves the following results on the evaluation set:
Loss: 1.5493
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: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 16
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.2
num_epochs: 1
Training results
Framework versions
Transformers 4.41.0.dev0
Pytorch 2.2.0
Datasets 2.19.0
Tokenizers 0.19.1
