Microsoft
Copied!
Model
Microsoft
Phi-3.5-Mini-Instruct-ONNX-INT4-RTXThe NVIDIA Phi-3.5-mini-Instruct INT4 ONNX model is the quantized version of the Microsoft Phi-3.5-mini-Instruct model which has 3.8B parameters and is a dense decoder-only Transformer model using the same tokenizer as Phi-3 Mini.
Copied!
| Name | Size | Updated | Actions |
|---|---|---|---|
3rd_party_licenses.txt | 2.34 KB | February 28, 2025 UTC | |
genai_config.json | 1.69 KB | February 28, 2025 UTC | |
License.txt | 319 B | February 28, 2025 UTC | |
model.onnx | 355.22 KB | February 28, 2025 UTC | |
model.onnx_data | 2.13 GB | February 28, 2025 UTC | |
notice.txt | 36 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 | 599 B | February 28, 2025 UTC | |
tokenizer_config.json | 3.41 KB | February 28, 2025 UTC | |
tokenizer.json | 1.85 MB | February 28, 2025 UTC | |
tokenizer.model | 488.01 KB | February 28, 2025 UTC |