Update README.md
Browse files
README.md
CHANGED
|
@@ -80,6 +80,7 @@ Notably, RLHF for alignment, when used as a pre-step, boosts the model’s compl
|
|
| 80 |
|
| 81 |
## Usage Recommendations
|
| 82 |
|
|
|
|
| 83 |
We recommend using RoPE scaling with the [YaRN](https://arxiv.org/abs/2309.00071) method for better long-context support. This can be enabled by updating the model’s `config.json` as shown below:
|
| 84 |
```json
|
| 85 |
{
|
|
|
|
| 80 |
|
| 81 |
## Usage Recommendations
|
| 82 |
|
| 83 |
+
For local deployment, we recommend setting the sampling parameters to temperature = 0.6, top_p = 0.95.
|
| 84 |
We recommend using RoPE scaling with the [YaRN](https://arxiv.org/abs/2309.00071) method for better long-context support. This can be enabled by updating the model’s `config.json` as shown below:
|
| 85 |
```json
|
| 86 |
{
|