Metrics
| PPL | arc_easy | arc_challenge | piqa | winogrande | hellaswag | mmlu | QA Avg |
|---|---|---|---|---|---|---|---|
| 47917.22 | 25.00 ± 0.89 | 23.89 ± 1.25 | 53.43 ± 1.16 | 50.20 ± 1.41 | 25.62 ± 0.44 | - | 35.63 |
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
HF Inference deployability: The model has no library tag.
Model tree for BrownianNotion/TinyLlama_v1.1_random
Base model
TinyLlama/TinyLlama_v1.1