Add hardware specifications
Browse files
README.md
CHANGED
|
@@ -102,6 +102,10 @@ python convert-hf-to-gguf.py Mambaoutai
|
|
| 102 |
./main -m Mambaoutai/ggml-model-f16.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e -ngl 1
|
| 103 |
```
|
| 104 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
### Model hyperparameters
|
| 106 |
|
| 107 |
More details about the model hyperparameters are given in the table below :
|
|
|
|
| 102 |
./main -m Mambaoutai/ggml-model-f16.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e -ngl 1
|
| 103 |
```
|
| 104 |
|
| 105 |
+
### Training Hardware
|
| 106 |
+
|
| 107 |
+
The model checkpoints with no instruction data have been fully trained on an NVIDIA DGX H100 provided by OVH Cloud, whereas the decay phases with instruction data have been carried out on an HPE Cray with 8xH100 on Orange Cloud Avenue.
|
| 108 |
+
|
| 109 |
### Model hyperparameters
|
| 110 |
|
| 111 |
More details about the model hyperparameters are given in the table below :
|