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

Safetensors

Model size

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

Base model

Finetuned

(53)

this model