UVLabs
/

HyperLLM-4b

Text Generation

Model card Files Files and versions

Commit History

v0.6: +15.2% accuracy with robust extraction (90.2% overall)

b44ff24

bebis1 commited on Mar 18

Upload tokenizer.json with huggingface_hub

e883931
verified

bebis1 commited on Mar 18

Upload training_args.bin with huggingface_hub

781da04
verified

bebis1 commited on Mar 18

Upload tokenizer_config.json with huggingface_hub

99682aa
verified

bebis1 commited on Mar 18

Upload adapter_config.json with huggingface_hub

9596184
verified

bebis1 commited on Mar 18

v0.6: Update model card with corrected evaluation results

83adfce
verified

bebis1 commited on Mar 18

Upload HyperLLM v0.4 - DoRA + DPO training with +11.1% accuracy improvement

aef556a
verified

bebis1 commited on Mar 13

Update README with corrected eval results (extraction bug fix)

b45908b
verified

bebis1 commited on Mar 6

Upload HyperLLM v0.3 - SFT+DPO trained model

b8aa575
verified

bebis1 commited on Mar 6

Upload HyperLLM v0.2

63bdbf7
verified

bebis1 commited on Mar 6

Update README.md

566a5fb
verified

bebis1 commited on Mar 3

Initial release v0.1 - experimental

6c36bf7
verified

bebis1 commited on Mar 3

initial commit

58fc7ea
verified

bebis1 commited on Mar 3