Metrics

PPL arc_easy arc_challenge piqa winogrande hellaswag mmlu QA Avg
11.99 41.96 ± 1.01 24.32 ± 1.25 66.21 ± 1.10 50.28 ± 1.41 39.00 ± 0.49 - 44.35

Training method based on BitDistiller Paper

  • License: mit
  • Finetuned from: TinyLlama/TinyLlama_v1.1
Downloads last month
2
Safetensors
Model size
1.1B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for fredericowieser/TinyLlama_v1.1_3bit_int_3_bit_int

Finetuned
(53)
this model