tangledgroup
/

tangled-llama-v-128k-base-v0.1

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

tangled-llama-v-128k-base-v0.1 / scripts /TRAIN.md

Commit History

benchmark

9e90c28

mtasic85 commited on 21 days ago

pretrain model, extend from 5 to 8 epochs

951a420

mtasic85 commited on 26 days ago

smaller pretrain dataset

854297e

mtasic85 commited on 27 days ago

trained new 128k tokenizer

fd468b1

mtasic85 commited on 28 days ago