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
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
Base model
TinyLlama/TinyLlama_v1.1