Model
The NVIDIA Gemma-2b-it INT4 ONNX model is the quantized version of the Google Gemma-2b-it model which is a text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants.
Use the NGC CLI to download:
Copied!
| Name | Size | Updated | Actions |
|---|---|---|---|
3rd_party_licenses.txt | 2.34 KB | February 28, 2025 UTC | |
genai_config.json | 1.61 KB | February 28, 2025 UTC | |
License.txt | 287 B | February 28, 2025 UTC | |
model.onnx | 197.71 KB | February 28, 2025 UTC | |
model.onnx_data | 2.91 GB | February 28, 2025 UTC | |
Notice.txt | 96 B | February 28, 2025 UTC | |
Prohibited_Use_Policy.txt | 41 B | February 28, 2025 UTC | |
readme.txt | 0 B | February 28, 2025 UTC | |
Readme.txt | 536 B | February 28, 2025 UTC | |
special_tokens_map.json | 670 B | February 28, 2025 UTC | |
tokenizer_config.json | 41.37 KB | February 28, 2025 UTC | |
tokenizer.json | 16.71 MB | February 28, 2025 UTC | |
tokenizer.model | 4.04 MB | February 28, 2025 UTC |