Update README.md
#2
by
RestingCodeFace
- opened
README.md
CHANGED
@@ -27,7 +27,7 @@ Developers looking to take off the shelf pre-quantized models for deployment <br
|
|
27 |
Huggingface 05/09/2025 via https://huggingface.co/nvidia/Llama-3.3-70B-Instruct-FP8 <br>
|
28 |
|
29 |
## Model Architecture:
|
30 |
-
**Architecture Type:**
|
31 |
**Network Architecture:** Llama3.3 <br>
|
32 |
|
33 |
## Input:
|
@@ -61,8 +61,8 @@ The model is quantized with nvidia-modelopt **v0.23.0** <br>
|
|
61 |
|
62 |
## Datasets:
|
63 |
* Calibration Dataset: [cnn_dailymail](https://huggingface.co/datasets/abisee/cnn_dailymail) <br>
|
64 |
-
** Data collection method: Automated
|
65 |
-
** Labeling method: Unknown
|
66 |
|
67 |
|
68 |
## Inference:
|
|
|
27 |
Huggingface 05/09/2025 via https://huggingface.co/nvidia/Llama-3.3-70B-Instruct-FP8 <br>
|
28 |
|
29 |
## Model Architecture:
|
30 |
+
**Architecture Type:** Transformer <br>
|
31 |
**Network Architecture:** Llama3.3 <br>
|
32 |
|
33 |
## Input:
|
|
|
61 |
|
62 |
## Datasets:
|
63 |
* Calibration Dataset: [cnn_dailymail](https://huggingface.co/datasets/abisee/cnn_dailymail) <br>
|
64 |
+
** Data collection method: Automated <br>
|
65 |
+
** Labeling method: Unknown <br>
|
66 |
|
67 |
|
68 |
## Inference:
|