vllm (pretrained=nm-testing/Llama-3_1-Nemotron-Ultra-253B-v1-FP8-dynamic,tensor_parallel_size=8,max_model_len=10000,trust_remote_code=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.9401|±  |0.0065|
|     |       |strict-match    |     5|exact_match|↑  |0.9401|±  |0.0065|

Downloads last month: 180

Safetensors

Model size

253B params

Tensor type

BF16

F8_E4M3

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for nm-testing/Llama-3_1-Nemotron-Ultra-253B-v1-FP8-dynamic

Base model

nvidia/Llama-3_1-Nemotron-Ultra-253B-v1

Quantized

(4)

this model