Chilliwiddit
/

Openi-llama3.1-8B-WeightedLoss-large20

Model card Files Files and versions

Model Card for Model ID

Basically used to summarize text from the Open-i dataset

Training Details

Training Data

I used the Open-i dataset

Training Hyperparameters

Training regime: [More Information Needed]
16 Mixed Precision
LR of 0.0-1
5 Epochs
lambda medical weight of 20 and lambda negation weight of 20
Used 2nd iteration of summary medical concepts file

Downloads last month: -

Model tree for Chilliwiddit/Openi-llama3.1-8B-WeightedLoss-large20

Base model

meta-llama/Llama-3.1-8B

Quantized

unsloth/Meta-Llama-3.1-8B-bnb-4bit

Adapter

(55)

this model