Metrics

PPL arc_easy arc_challenge piqa winogrande hellaswag mmlu QA Avg
10394.78 24.92 ± 0.89 22.95 ± 1.23 52.99 ± 1.16 48.62 ± 1.40 25.99 ± 0.44 - 35.09

Training method based on BitDistiller Paper

  • License: mit
  • Finetuned from: TinyLlama/TinyLlama_v1.1
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for BrownianNotion/TinyLlama_v1.1_2_int_clipped_untrained

Finetuned
(53)
this model